neuralmathematics Wiki Rss Feedhttps://neuralmathematics.codeplex.com/neuralmathematics Wiki Rss DescriptionUpdated Wiki: Documentationhttps://neuralmathematics.codeplex.com/documentation?version=16<div class="wikidoc"><b>Documentation</b><br /><br />All documentation documents are translated in English here with an automatic translator (Microsoft Translator).<br /><br /><br /><b>List of documents</b><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Key-Type&referringTitle=Documentation">SP-Key-Type</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Element-Nom&referringTitle=Documentation">SP-Element-Nom</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Check-Type&referringTitle=Documentation">SP-Check-Type</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Data-Class&referringTitle=Documentation">SP-Data-Class</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Neural-Command&referringTitle=Documentation">SP-Neural-Command</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Named-Neural&referringTitle=Documentation">SP-Named-Neural</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Operation-ar&referringTitle=Documentation">SP-Operation-ar</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Serialization&referringTitle=Documentation">SP-Serialization</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Distribution&referringTitle=Documentation">SP-Distribution</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Heuristic&referringTitle=Documentation">SP-Heuristic</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Commutative&referringTitle=Documentation">SP-Commutative</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Factorization&referringTitle=Documentation">SP-Factorization</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Inversion&referringTitle=Documentation">SP-Inversion</a><br /><br /><br /><br /><br /><br /></div><div class="ClearBoth"></div>skercrowSun, 18 Dec 2016 09:52:12 GMTUpdated Wiki: Documentation 20161218095212AUpdated Wiki: SP-Inversionhttps://neuralmathematics.codeplex.com/wikipage?title=SP-Inversion&version=1<div class="wikidoc"><h1>Implementation of the algebraic operation of inversion</h1>
<h2>Presentation</h2>
<h3>Document concerned</h3>
This document deals with the algebraic operation of inversion. I am writing this short document to clarify the necessary programming work.<br />
<h3>Versions</h3>
13/12/2016: initial version<br />
<h3>Author</h3>
Invisible Media<br />
<h2>Project</h2>
Framework of the project This project is a digital and algebraic calculation software. This project is a way to train very long and tedious equations and to factor them according to a common approach. Goal: solve equations, find all the solutions algebraically and get an equation based on parameters and fixed digital data.<br />
<h3>All the features</h3>
The set of features is detailed in this document: All features (unbundled) .xlsx<br />
<h3>Name of the feature covered here</h3>
<br />Neurons of inversion<br />
<h2>Relative need</h2>
<br />Neurons are elements of graph also called node. In each node in the graph, there may be 0 to N branches or arc where the other end is the next node.<br /><br />The arithmetic operations are one together recurring that perfectly fits the notion of graph. In particular, a complete equation is a tree set of operations. We're talking about graph when a node has multiple parents. An equation where some words are repeated will form a graph where a repeated word is associated with a single node, and each parent node will go on this node.<br /><br />The neurons of algebraic distribution concern all the multiplication of terms.</div><div class="ClearBoth"></div>skercrowSun, 18 Dec 2016 09:51:38 GMTUpdated Wiki: SP-Inversion 20161218095138AUpdated Wiki: Documentationhttps://neuralmathematics.codeplex.com/documentation?version=15<div class="wikidoc"><b>Documentation</b><br /><br />All documentation documents are translated in English here with an automatic translator (Microsoft Translator).<br /><br /><br /><b>List of documents</b><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Key-Type&referringTitle=Documentation">SP-Key-Type</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Element-Nom&referringTitle=Documentation">SP-Element-Nom</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Check-Type&referringTitle=Documentation">SP-Check-Type</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Data-Class&referringTitle=Documentation">SP-Data-Class</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Neural-Command&referringTitle=Documentation">SP-Neural-Command</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Named-Neural&referringTitle=Documentation">SP-Named-Neural</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Operation-ar&referringTitle=Documentation">SP-Operation-ar</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Serialization&referringTitle=Documentation">SP-Serialization</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Distribution&referringTitle=Documentation">SP-Distribution</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Heuristic&referringTitle=Documentation">SP-Heuristic</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Commutative&referringTitle=Documentation">SP-Commutative</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Factorization&referringTitle=Documentation">SP-Factorization</a><br /><br /><br /><br /><br /><br /><br /></div><div class="ClearBoth"></div>skercrowSun, 18 Dec 2016 09:44:27 GMTUpdated Wiki: Documentation 20161218094427AUpdated Wiki: SP-Factorizationhttps://neuralmathematics.codeplex.com/wikipage?title=SP-Factorization&version=3<div class="wikidoc"><h1>Implementation of factorization</h1>
<h2>Presentation</h2>
<h3>Document concerned</h3>
This document deals with algebraic factoring operations. I am writing this short document to clarify the necessary programming work.<br />
<h3>Versions</h3>
13/12/2016: initial version<br />
<h3>Author</h3>
Invisible Media<br />
<h2>Project</h2>
<h3>Framework of the project</h3>
This project is a digital and algebraic calculation software. This project is a way to train very long and tedious equations and to factor them according to a common approach. Goal: solve equations, find all the solutions algebraically and get an equation based on parameters and fixed digital data.<br />
<h3>All the features</h3>
The set of features is detailed in this document: All features (unbundled) .xlsx<br />
<h3>Name of the feature covered here</h3>
Neurons of algebraic factorization<br />
<h1>Relative need</h1>
Neurons are elements of graph also called node. In each node in the graph, there may be 0 to N branches or arc where the other end is the next node.<br /><br /><br />
<h2>Explanations</h2>
<h2>Graphic view</h2>
The neurons of algebraic distribution concern all the multiplication of terms.<br /><br />
<h2>Relationship with other features</h2>
We note each node on a two-dimensional grid the number of links that connect two different nodes (in both directions). The diagonal axis of the grid corresponds to a diagonal of numbers zero, with the understanding that there is no node in relation to himself.<br /><br />The factorization of an equation is to form a grouping of common terms that make it up. From a general point of view, consider the factorization of an equation find the algebraic form the simplest, most convenient (because there are fewer calculations) and elegant.<br />Also, the computer must learn to save equations obtained by factoring (guided by humans) and give a formula to resolve other more complex equations.<br /><br />Here's the graphic view of a neuron where how it graphically represents a neuron.<br /><br /><br /><img src="http://download-codeplex.sec.s-msft.com/Download?ProjectName=neuralmathematics&DownloadId=1625328" alt="add-2-number.png" title="add-2-number.png" /> <img src="http://download-codeplex.sec.s-msft.com/Download?ProjectName=neuralmathematics&DownloadId=1625329" alt="add-one-par.png" title="add-one-par.png" /> <img src="http://download-codeplex.sec.s-msft.com/Download?ProjectName=neuralmathematics&DownloadId=1625330" alt="add-one-x.png" title="add-one-x.png" /> <img src="http://download-codeplex.sec.s-msft.com/Download?ProjectName=neuralmathematics&DownloadId=1625331" alt="add-x-par.png" title="add-x-par.png" /><br /><br /><br />The two branches on the right are the operands of the operation (here the addition). For each operation, there are 6 configurations.<br /><br />
<h2>Manufacture of neurons</h2>
<br />Other operators are necessary to allow a set of mathematical sequences. Some instructions are needed:<br />
<ol><li>declaring a free variable</li>
<li>declaration of a bound variable </li>
<li>declaration of an unknown variable </li>
<li>equality operator to check </li>
<li>own equality operator </li>
<li>comparison operators</li>
<li>conditional operator: a comparison test, a new sequence if the test result is checked, a new sequence (optional) if the test result is refuted.</li></ol>
<br />These instructions are defined by templates of neurons. The construction of neurons is done during syntactic analysis of these instructions.<br /><br />The factorization operates on an equation. The intervention of the human guide the machine by selecting terms to factor out together; the machine takes care of the algebraic operations and taking common terms.<br /><br /><br /></div><div class="ClearBoth"></div>skercrowSun, 18 Dec 2016 09:43:41 GMTUpdated Wiki: SP-Factorization 20161218094341AUpdated Wiki: SP-Factorizationhttps://neuralmathematics.codeplex.com/wikipage?title=SP-Factorization&version=2<div class="wikidoc"><h1>Implementation of factorization</h1>
<h2>Presentation</h2>
<h3>Document concerned</h3>
This document deals with algebraic factoring operations. I am writing this short document to clarify the necessary programming work.<br />
<h3>Versions</h3>
13/12/2016: initial version<br />
<h3>Author</h3>
Invisible Media<br />
<h2>Project</h2>
<h3>Framework of the project</h3>
This project is a digital and algebraic calculation software. This project is a way to train very long and tedious equations and to factor them according to a common approach. Goal: solve equations, find all the solutions algebraically and get an equation based on parameters and fixed digital data.<br />
<h3>All the features</h3>
The set of features is detailed in this document: All features (unbundled) .xlsx<br />
<h3>Name of the feature covered here</h3>
Neurons of algebraic factorization<br />
<h1>Relative need</h1>
Neurons are elements of graph also called node. In each node in the graph, there may be 0 to N branches or arc where the other end is the next node.<br /><br /><br />
<h2>Explanations</h2>
<h2>Graphic view</h2>
The neurons of algebraic distribution concern all the multiplication of terms.<br /><br />
<h2>Relationship with other features</h2>
We note each node on a two-dimensional grid the number of links that connect two different nodes (in both directions). The diagonal axis of the grid corresponds to a diagonal of numbers zero, with the understanding that there is no node in relation to himself.<br /><br />The factorization of an equation is to form a grouping of common terms that make it up. From a general point of view, consider the factorization of an equation find the algebraic form the simplest, most convenient (because there are fewer calculations) and elegant.<br />Also, the computer must learn to save equations obtained by factoring (guided by humans) and give a formula to resolve other more complex equations.<br /><br />Here's the graphic view of a neuron where how it graphically represents a neuron.<br /><br /><br /><img src="http://download-codeplex.sec.s-msft.com/Download?ProjectName=neuralmathematics&DownloadId=1625328" alt="add-2-number.png" title="add-2-number.png" /> <img src="http://download-codeplex.sec.s-msft.com/Download?ProjectName=neuralmathematics&DownloadId=1625329" alt="add-one-par.png" title="add-one-par.png" /> <img src="http://download-codeplex.sec.s-msft.com/Download?ProjectName=neuralmathematics&DownloadId=1625330" alt="add-one-x.png" title="add-one-x.png" /> <img src="http://download-codeplex.sec.s-msft.com/Download?ProjectName=neuralmathematics&DownloadId=1625331" alt="add-x-par.png" title="add-x-par.png" /></div><div class="ClearBoth"></div>skercrowSun, 18 Dec 2016 09:42:13 GMTUpdated Wiki: SP-Factorization 20161218094213AUpdated Wiki: SP-Factorizationhttps://neuralmathematics.codeplex.com/wikipage?title=SP-Factorization&version=1<div class="wikidoc"><h1>Implementation of factorization</h1>
<h2>Presentation</h2>
<h3>Document concerned</h3>
This document deals with algebraic factoring operations. I am writing this short document to clarify the necessary programming work.<br />
<h3>Versions</h3>
13/12/2016: initial version<br />
<h3>Author</h3>
Invisible Media<br />
<h2>Project</h2>
<h3>Framework of the project</h3>
This project is a digital and algebraic calculation software. This project is a way to train very long and tedious equations and to factor them according to a common approach. Goal: solve equations, find all the solutions algebraically and get an equation based on parameters and fixed digital data.<br />
<h3>All the features</h3>
The set of features is detailed in this document: All features (unbundled) .xlsx<br />
<h3>Name of the feature covered here</h3>
Neurons of algebraic factorization<br />
<h1>Relative need</h1>
Neurons are elements of graph also called node. In each node in the graph, there may be 0 to N branches or arc where the other end is the next node.<br /><br /><br />
<h2>Explanations</h2>
<h2>Graphic view</h2>
The neurons of algebraic distribution concern all the multiplication of terms.<br /><br />
<h2>Relationship with other features</h2>
We note each node on a two-dimensional grid the number of links that connect two different nodes (in both directions). The diagonal axis of the grid corresponds to a diagonal of numbers zero, with the understanding that there is no node in relation to himself.<br /><br />The factorization of an equation is to form a grouping of common terms that make it up. From a general point of view, consider the factorization of an equation find the algebraic form the simplest, most convenient (because there are fewer calculations) and elegant.<br />Also, the computer must learn to save equations obtained by factoring (guided by humans) and give a formula to resolve other more complex equations.<br /><br />Here's the graphic view of a neuron where how it graphically represents a neuron.<br /></div><div class="ClearBoth"></div>skercrowSun, 18 Dec 2016 09:40:41 GMTUpdated Wiki: SP-Factorization 20161218094041AUpdated Wiki: Homehttps://neuralmathematics.codeplex.com/wikipage?version=5<div class="wikidoc"><b>Project Description</b><br />Le projet Neuronal Mathematics se propose de résoudre les équations polynomiales et autres formes en utilisant une méthode algébrique commune.<br /><br /><b>Introduction</b><br /><br />Le projet Neuronal Mathematics se propose de résoudre les équations polynomiales et autres formes en utilisant une méthode algébrique commune à toutes les équations polynomiales.<br /><br />La résolution des autres formes d'équations recherche le calcul des résidus par la recherche des termes de progressions.<br /><br /><b>Detailed Project</b><br /><br />Go to <a href="https://neuralmathematics.codeplex.com/documentation?referringTitle=Home">Documentation</a> to view through the documentation items<br /><br /><b>Contribute</b><br /><br />This software is in the process of the first iteration. Some features are not started and the first version is not complete at this moment. I encourage some developers to join the team to begin work. All features can be explained very large and no free code will come in the project. Then, developers will be managed very closely in order to make the best code as it must be done.<br /><br />Documentation is clearly written in french. This software is designed by a french manager then, french developers are welcome.<br /><br /></div><div class="ClearBoth"></div>skercrowSun, 18 Dec 2016 09:35:29 GMTUpdated Wiki: Home 20161218093529AUpdated Wiki: Homehttps://neuralmathematics.codeplex.com/wikipage?version=4<div class="wikidoc"><b>Project Description</b><br />Le projet Neuronal Mathematics se propose de résoudre les équations polynomiales et autres formes en utilisant une méthode algébrique commune.<br /><br /><b>Introduction</b><br /><br />Le projet Neuronal Mathematics se propose de résoudre les équations polynomiales et autres formes en utilisant une méthode algébrique commune à toutes les équations polynomiales.<br /><br />La résolution des autres formes d'équations recherche le calcul des résidus par la recherche des termes de progressions.<br />
<ul><li>Detailed Project *</li></ul>
<br />Go to <a href="https://neuralmathematics.codeplex.com/documentation?referringTitle=Home">Documentation</a> to view through the documentation items<br /><br /><b>Contribute</b><br /><br />This software is in the process of the first iteration. Some features are not started and the first version is not complete at this moment. I encourage some developers to join the team to begin work. All features can be explained very large and no free code will come in the project. Then, developers will be managed very closely in order to make the best code as it must be done.<br /><br />Documentation is clearly written in french. This software is designed by a french manager then, french developers are welcome.<br /><br /></div><div class="ClearBoth"></div>skercrowSun, 18 Dec 2016 09:35:11 GMTUpdated Wiki: Home 20161218093511AUpdated Wiki: Documentationhttps://neuralmathematics.codeplex.com/documentation?version=14<div class="wikidoc"><b>Documentation</b><br /><br />All documentation documents are translated in English here with an automatic translator (Microsoft Translator).<br /><br /><br /><b>List of documents</b><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Key-Type&referringTitle=Documentation">SP-Key-Type</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Element-Nom&referringTitle=Documentation">SP-Element-Nom</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Check-Type&referringTitle=Documentation">SP-Check-Type</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Data-Class&referringTitle=Documentation">SP-Data-Class</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Neural-Command&referringTitle=Documentation">SP-Neural-Command</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Named-Neural&referringTitle=Documentation">SP-Named-Neural</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Operation-ar&referringTitle=Documentation">SP-Operation-ar</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Serialization&referringTitle=Documentation">SP-Serialization</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Distribution&referringTitle=Documentation">SP-Distribution</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Heuristic&referringTitle=Documentation">SP-Heuristic</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Commutative&referringTitle=Documentation">SP-Commutative</a><br /><br /><br /><br /><br /><br /><br /><br /></div><div class="ClearBoth"></div>skercrowSun, 18 Dec 2016 09:33:03 GMTUpdated Wiki: Documentation 20161218093303AUpdated Wiki: SP-Commutativehttps://neuralmathematics.codeplex.com/wikipage?title=SP-Commutative&version=2<div class="wikidoc"><h1>Implementation of commutative</h1>
<h2>Presentation</h2>
<h3>Document concerned</h3>
This document deals with algebraic operations of commutative. I am writing this short document to clarify the necessary programming work.<br />
<h3>Versions</h3>
13/12/2016: initial version<br />
<h3>Author Invisible Media</h3>
<h2>Project</h2>
<h3>Framework of the project</h3>
This project is a digital and algebraic calculation software. This project is a way to train very long and tedious equations and to factor them according to a common approach. Goal: solve equations, find all the solutions algebraically and get an equation based on parameters and fixed digital data.<br />
<h3>All the features</h3>
The set of features is detailed in this document: All features (unbundled) .xlsx<br />
<h3>Name of the feature covered here</h3>
Neurons of commutative<br />
<h3>Relative need</h3>
Neurons are elements of graph also called node. In each node in the graph, there may be 0 to N branches or arc where the other end is the next node.<br /><br /><br />
<h2>Explanations</h2>
<br />
<h3>Graphic view</h3>
The neurons of algebraic distribution concern all the multiplication of terms.<br /><br />
<h3>Relationship with other features</h3>
<br />We note each node on a two-dimensional grid the number of links that connect two different nodes (in both directions). The diagonal axis of the grid corresponds to a diagonal of numbers zero, with the understanding that there is no node in relation to himself.<br /><br />But this definition is insufficient to explain the real problem. Commutative is the difficulty of obtaining a canonical form of the equation any. The commutative means that the Organization of an equation has no impact on the result. the Organization of an equation has an impact on its schematic and semantic representation.<br /><br />Therefore, commutative must be applied to form the equation according to the clearest possible. The canonical shape was presented in document MS-heuristic.<br /><br />I note that transitivity is not addressed. Indeed, the logical graph composed after the reading of an equation is a directed graph of width 0 to infinity; This means that a node of the graph will have as many links as there are operands with the same operation.<br /><br />Here's the graphic view of a neuron where how it graphically represents a neuron.<br /><br /><img src="http://download-codeplex.sec.s-msft.com/Download?ProjectName=neuralmathematics&DownloadId=1625322" alt="add-2-number.png" title="add-2-number.png" /> <img src="http://download-codeplex.sec.s-msft.com/Download?ProjectName=neuralmathematics&DownloadId=1625323" alt="add-one-par.png" title="add-one-par.png" /> <img src="http://download-codeplex.sec.s-msft.com/Download?ProjectName=neuralmathematics&DownloadId=1625324" alt="add-one-x.png" title="add-one-x.png" /> <img src="http://download-codeplex.sec.s-msft.com/Download?ProjectName=neuralmathematics&DownloadId=1625325" alt="add-x-par.png" title="add-x-par.png" /><br /><br />The two branches on the right are the operands of the operation (here the addition). For each operation, there are 6 configurations.<br /><br />Other operators are necessary to allow a set of mathematical sequences.<br /><br />Some instructions are needed:
<ol><li>declaring a free variable </li>
<li>declaration of a bound variable </li>
<li>declaration of an unknown variable </li>
<li>equality operator to check </li>
<li>own equality operator </li>
<li>comparison operators</li>
<li>conditional operator: a comparison test, a new sequence if the test result is checked, a new sequence (optional) if the test result is refuted.</li></ol>
<br /><br />These instructions are defined by templates of neurons. The construction of neurons is done during syntactic analysis of these instructions.<br /><br /><br />I note that here are prefabricated neurons. A given equation, to break down the equation in terms of operations and build the graph of this equation using the templates available to neurons.<br />So there is an initial background where each neuron has its own function and its own form. I also note that there is only a single main command for an equation: calculate the result of the equation giving a numerical value to each variable. Related variables, to always express the values by using the equation of this variable. For free variables, any numeric value is correct. Finally, for the unknown variables it comes to seek his equation based on the knowledge of the equations on the variables and the values of the free variables.<br />The search of the canonical form algorithm considers the States in descending order and begins in-depth research by the larger Member States, i.e. Forms of unwanted equations. To evaluate the first as the largest State, simply calculate the smallest possible state by the calculation of the number of operands. Commutative are permutations for operands on a same operation; suffice to say that if the algorithm is not optimized then the processing time will be too big and memory availability will be insufficient.<br /><br /><br /></div><div class="ClearBoth"></div>skercrowSun, 18 Dec 2016 09:32:45 GMTUpdated Wiki: SP-Commutative 20161218093245AUpdated Wiki: SP-Commutativehttps://neuralmathematics.codeplex.com/wikipage?title=SP-Commutative&version=1<div class="wikidoc">tt</div><div class="ClearBoth"></div>skercrowSun, 18 Dec 2016 09:30:43 GMTUpdated Wiki: SP-Commutative 20161218093043AUpdated Wiki: Documentationhttps://neuralmathematics.codeplex.com/documentation?version=13<div class="wikidoc"><b>Documentation</b><br /><br />All documentation documents are translated in English here with an automatic translator (Microsoft Translator).<br /><br /><br /><b>List of documents</b><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Key-Type&referringTitle=Documentation">SP-Key-Type</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Element-Nom&referringTitle=Documentation">SP-Element-Nom</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Check-Type&referringTitle=Documentation">SP-Check-Type</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Data-Class&referringTitle=Documentation">SP-Data-Class</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Neural-Command&referringTitle=Documentation">SP-Neural-Command</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Named-Neural&referringTitle=Documentation">SP-Named-Neural</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Operation-ar&referringTitle=Documentation">SP-Operation-ar</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Serialization&referringTitle=Documentation">SP-Serialization</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Distribution&referringTitle=Documentation">SP-Distribution</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Heuristic&referringTitle=Documentation">SP-Heuristic</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=Commutative&referringTitle=Documentation">Commutative</a><br /><br /><br /><br /><br /><br /><br /><br /></div><div class="ClearBoth"></div>skercrowSun, 18 Dec 2016 09:29:55 GMTUpdated Wiki: Documentation 20161218092955AUpdated Wiki: Commutativehttps://neuralmathematics.codeplex.com/wikipage?title=Commutative&version=2<div class="wikidoc"><h1>Implementation of commutative</h1>
<h2>Presentation</h2>
<h3>Document concerned</h3>
This document deals with algebraic operations of commutative. I am writing this short document to clarify the necessary programming work.<br />
<h3>Versions</h3>
13/12/2016: initial version<br />
<h3>Author Invisible Media</h3>
<h2>Project</h2>
<h3>Framework of the project</h3>
This project is a digital and algebraic calculation software. This project is a way to train very long and tedious equations and to factor them according to a common approach. Goal: solve equations, find all the solutions algebraically and get an equation based on parameters and fixed digital data.<br />
<h3>All the features</h3>
The set of features is detailed in this document: All features (unbundled) .xlsx<br />
<h3>Name of the feature covered here</h3>
Neurons of commutative<br />
<h3>Relative need</h3>
Neurons are elements of graph also called node. In each node in the graph, there may be 0 to N branches or arc where the other end is the next node.<br /><br /><br />
<h2>Explanations</h2>
<br />
<h3>Graphic view</h3>
The neurons of algebraic distribution concern all the multiplication of terms.<br /><br />
<h3>Relationship with other features</h3>
<br />We note each node on a two-dimensional grid the number of links that connect two different nodes (in both directions). The diagonal axis of the grid corresponds to a diagonal of numbers zero, with the understanding that there is no node in relation to himself.<br /><br />But this definition is insufficient to explain the real problem. Commutative is the difficulty of obtaining a canonical form of the equation any. The commutative means that the Organization of an equation has no impact on the result. the Organization of an equation has an impact on its schematic and semantic representation.<br /><br />Therefore, commutative must be applied to form the equation according to the clearest possible. The canonical shape was presented in document MS-heuristic.<br /><br />I note that transitivity is not addressed. Indeed, the logical graph composed after the reading of an equation is a directed graph of width 0 to infinity; This means that a node of the graph will have as many links as there are operands with the same operation.<br /><br />Here's the graphic view of a neuron where how it graphically represents a neuron.<br /><br /><img src="http://download-codeplex.sec.s-msft.com/Download?ProjectName=neuralmathematics&DownloadId=1625318" alt="add-2-number.png" title="add-2-number.png" /> <img src="http://download-codeplex.sec.s-msft.com/Download?ProjectName=neuralmathematics&DownloadId=1625319" alt="add-one-par.png" title="add-one-par.png" /> <img src="http://download-codeplex.sec.s-msft.com/Download?ProjectName=neuralmathematics&DownloadId=1625320" alt="add-one-x.png" title="add-one-x.png" /> <img src="http://download-codeplex.sec.s-msft.com/Download?ProjectName=neuralmathematics&DownloadId=1625321" alt="add-x-par.png" title="add-x-par.png" /><br /><br />The two branches on the right are the operands of the operation (here the addition). For each operation, there are 6 configurations.<br /><br />Other operators are necessary to allow a set of mathematical sequences.<br /><br />Some instructions are needed:
<ol><li>declaring a free variable </li>
<li>declaration of a bound variable </li>
<li>declaration of an unknown variable </li>
<li>equality operator to check </li>
<li>own equality operator </li>
<li>comparison operators</li>
<li>conditional operator: a comparison test, a new sequence if the test result is checked, a new sequence (optional) if the test result is refuted.</li></ol>
<br /><br />These instructions are defined by templates of neurons. The construction of neurons is done during syntactic analysis of these instructions.<br /><br /><br />I note that here are prefabricated neurons. A given equation, to break down the equation in terms of operations and build the graph of this equation using the templates available to neurons.<br />So there is an initial background where each neuron has its own function and its own form. I also note that there is only a single main command for an equation: calculate the result of the equation giving a numerical value to each variable. Related variables, to always express the values by using the equation of this variable. For free variables, any numeric value is correct. Finally, for the unknown variables it comes to seek his equation based on the knowledge of the equations on the variables and the values of the free variables.<br />The search of the canonical form algorithm considers the States in descending order and begins in-depth research by the larger Member States, i.e. Forms of unwanted equations. To evaluate the first as the largest State, simply calculate the smallest possible state by the calculation of the number of operands. Commutative are permutations for operands on a same operation; suffice to say that if the algorithm is not optimized then the processing time will be too big and memory availability will be insufficient.<br /><br /><br /></div><div class="ClearBoth"></div>skercrowSun, 18 Dec 2016 08:48:18 GMTUpdated Wiki: Commutative 20161218084818AUpdated Wiki: Commutativehttps://neuralmathematics.codeplex.com/wikipage?title=Commutative&version=1<div class="wikidoc"><h1>Implementation of commutative</h1>
<h2>Presentation</h2>
<h3>Document concerned</h3>
This document deals with algebraic operations of commutative. I am writing this short document to clarify the necessary programming work.<br />
<h3>Versions</h3>
13/12/2016: initial version<br />
<h3>Author Invisible Media</h3>
<h2>Project</h2>
<h3>Framework of the project</h3>
This project is a digital and algebraic calculation software. This project is a way to train very long and tedious equations and to factor them according to a common approach. Goal: solve equations, find all the solutions algebraically and get an equation based on parameters and fixed digital data.<br />
<h3>All the features</h3>
The set of features is detailed in this document: All features (unbundled) .xlsx<br />
<h3>Name of the feature covered here</h3>
Neurons of commutative<br />
<h3>Relative need</h3>
Neurons are elements of graph also called node. In each node in the graph, there may be 0 to N branches or arc where the other end is the next node.<br /><br /><br />
<h2>Explanations</h2>
<br />
<h3>Graphic view</h3>
The neurons of algebraic distribution concern all the multiplication of terms.<br /><br />
<h3>Relationship with other features</h3>
<br />We note each node on a two-dimensional grid the number of links that connect two different nodes (in both directions). The diagonal axis of the grid corresponds to a diagonal of numbers zero, with the understanding that there is no node in relation to himself.<br /><br />But this definition is insufficient to explain the real problem. Commutative is the difficulty of obtaining a canonical form of the equation any. The commutative means that the Organization of an equation has no impact on the result. the Organization of an equation has an impact on its schematic and semantic representation.<br /><br />Therefore, commutative must be applied to form the equation according to the clearest possible. The canonical shape was presented in document MS-heuristic.<br /><br />I note that transitivity is not addressed. Indeed, the logical graph composed after the reading of an equation is a directed graph of width 0 to infinity; This means that a node of the graph will have as many links as there are operands with the same operation.<br /><br />Here's the graphic view of a neuron where how it graphically represents a neuron.<br /><br /></div><div class="ClearBoth"></div>skercrowSun, 18 Dec 2016 08:40:38 GMTUpdated Wiki: Commutative 20161218084038AUpdated Wiki: Documentationhttps://neuralmathematics.codeplex.com/documentation?version=12<div class="wikidoc"><b>Documentation</b><br /><br />All documentation documents are translated in English here with an automatic translator (Microsoft Translator).<br /><br /><br /><b>List of documents</b><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Key-Type&referringTitle=Documentation">SP-Key-Type</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Element-Nom&referringTitle=Documentation">SP-Element-Nom</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Check-Type&referringTitle=Documentation">SP-Check-Type</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Data-Class&referringTitle=Documentation">SP-Data-Class</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Neural-Command&referringTitle=Documentation">SP-Neural-Command</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Named-Neural&referringTitle=Documentation">SP-Named-Neural</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Operation-ar&referringTitle=Documentation">SP-Operation-ar</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Serialization&referringTitle=Documentation">SP-Serialization</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Distribution&referringTitle=Documentation">SP-Distribution</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Heuristic&referringTitle=Documentation">SP-Heuristic</a><br /><br /><br /><br /><br /></div><div class="ClearBoth"></div>skercrowSun, 11 Dec 2016 23:02:39 GMTUpdated Wiki: Documentation 20161211110239PUpdated Wiki: Documentationhttps://neuralmathematics.codeplex.com/documentation?version=11<div class="wikidoc"><b>Documentation</b><br /><br />All documentation documents are translated in English here with an automatic translator (Microsoft Translator).<br /><br /><br /><b>List of documents</b><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Key-Type&referringTitle=Documentation">SP-Key-Type</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Element-Nom&referringTitle=Documentation">SP-Element-Nom</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Check-Type&referringTitle=Documentation">SP-Check-Type</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Data-Class&referringTitle=Documentation">SP-Data-Class</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Neural-Command&referringTitle=Documentation">SP-Neural-Command</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Named-Neural&referringTitle=Documentation">SP-Named-Neural</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Operation-ar&referringTitle=Documentation">SP-Operation-ar</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Serialization&referringTitle=Documentation">SP-Serialization</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Distribution&referringTitle=Documentation">SP-Distribution</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Heuristic&referringTitle=Documentation">SP-Heuristic</a><br /></div><div class="ClearBoth"></div>skercrowSun, 11 Dec 2016 23:02:19 GMTUpdated Wiki: Documentation 20161211110219PUpdated Wiki: SP-Heuristichttps://neuralmathematics.codeplex.com/wikipage?title=SP-Heuristic&version=2<div class="wikidoc"><h1>Establishment of the heuristic calculations</h1>
<h2>Presentation</h2>
<h3>Document concerned</h3>
This document covers the features of heuristic calculations. I am writing this short document to clarify the necessary programming work.<br />
<h3>Versions</h3>
07/12/2016: initial version<br />
<h3>Author</h3>
Invisible Media<br /><br />
<h2>Project</h2>
<h3>Framework of the project</h3>
This project is a digital and algebraic calculation software. This project is a way to train very long and tedious equations and to factor them according to a common approach. Goal: solve equations, find all the solutions algebraically and get an equation based on parameters and fixed digital data.<br />
<h3>All the features</h3>
The set of features is detailed in this document: All features (unbundled) .xlsx<br />
<h3>Name of the feature covered here</h3>
Heuristic<br />
<h3>Relative need</h3>
Neurons are elements of graph also called node. In each node in the graph, there may be 0 to N branches or arc where the other end is the next node.<br /><br />The arithmetic operations are one together recurring that perfectly fits the notion of graph. In particular, a complete equation is a tree set of operations. We're talking about graph when a node has multiple parents. An equation where some words are repeated will form a graph where a repeated word is associated with a single node, and each parent node will go on this node.<br />The neurons of algebraic distribution concern all the multiplication of terms.<br />
<h2>Relationship with other features</h2>
<h3>Use</h3>
<br />Neurons are objects that can communicate with each other. From the programming point of view, neurons form a directed graph. Then, each neuron with an application that is unique, the application traverses the graph through the neurons that react differently depending on the settings.<br /><br /><br />We note each node on a two-dimensional grid where is the number of nodes. Each square of the grid hosts a number positive or zero. This number is the number of links that connect two different nodes (in both directions). The diagonal axis of the grid corresponds to a diagonal of numbers zero, with the understanding that there is no node in relation to himself.<br /><br />
<h2>Explanations</h2>
Different heuristics are implemented. Each heuristic has its own objectives. <br />
<h3>Canonical heuristic</h3>
The first important heuristic is the canonical form of an equation. To save time by searching the terms in the equations, I consider a canonical form which operations are always organized in the same way; I also note that, as usual, we present equations in a canonical way. For example:<br /><br /> y = a x ^ 2 + b x + c <br /><br /><br /><br />This equation has the following standard properties:<br />
<ol><li>terms them to the left of each sum are constant terms or constant numeric values.</li>
<li>then, on the right the unknown terms. </li>
<li>Finally, the sum is organized left to right starting with the end of greater power and each term is declining.</li></ol>
<br /><br />A heuristic calculates different situations in terms of the order of the products and the order of the additions. <br /><br />Division and subtraction are the same conditions except that the sign belongs to the number.<br /><br />Then in a second step, it will take into account the fact that:<br />
<ol><li>operations with numerical terms are Computable to give a number or possibly a Euclidean division.</li>
<li>operations terms coefficients are posted simultaneously after the selection of the heuristic: If a coefficient is divided by a coefficient then the coefficient disappears. Hence, the General transformation</li>
<li>operations of terms are and differences are grouped when unfamiliar terms are formed by the same powers. The terms coefficient and the numerical terms form an equation with products and sums. Their order is the same as for unknown terms.</li></ol>
<br />It is important to save time in calculating both perform the heuristic search and algebraically admitted simplifications. Clearly: priority to simplified product heuristics and heuristics of sums. Then back to the amount inside each product heuristics simplified by are heuristics (heuristics produces are supposed to be without effect at this stage).<br /><br /><br /></div><div class="ClearBoth"></div>skercrowSun, 11 Dec 2016 23:01:44 GMTUpdated Wiki: SP-Heuristic 20161211110144PUpdated Wiki: SP-Heuristichttps://neuralmathematics.codeplex.com/wikipage?title=SP-Heuristic&version=1<div class="wikidoc"><h1>Establishment of the heuristic calculations</h1>
<h2>Presentation</h2>
<h3>Document concerned</h3>
This document covers the features of heuristic calculations. I am writing this short document to clarify the necessary programming work.<br />
<h3>Versions</h3>
07/12/2016: initial version<br />
<h3>Author</h3>
Invisible Media<br /><br />
<h2>Project</h2>
<h3>Framework of the project</h3>
This project is a digital and algebraic calculation software. This project is a way to train very long and tedious equations and to factor them according to a common approach. Goal: solve equations, find all the solutions algebraically and get an equation based on parameters and fixed digital data.<br />
<h3>All the features</h3>
The set of features is detailed in this document: All features (unbundled) .xlsx<br />
<h3>Name of the feature covered here</h3>
Heuristic<br />
<h3>Relative need</h3>
Neurons are elements of graph also called node. In each node in the graph, there may be 0 to N branches or arc where the other end is the next node.<br /><br />The arithmetic operations are one together recurring that perfectly fits the notion of graph. In particular, a complete equation is a tree set of operations. We're talking about graph when a node has multiple parents. An equation where some words are repeated will form a graph where a repeated word is associated with a single node, and each parent node will go on this node.<br />The neurons of algebraic distribution concern all the multiplication of terms.<br />
<h2>Relationship with other features</h2>
<h3>Use</h3>
<br />Neurons are objects that can communicate with each other. From the programming point of view, neurons form a directed graph. Then, each neuron with an application that is unique, the application traverses the graph through the neurons that react differently depending on the settings.<br /><br /><br />We note each node on a two-dimensional grid where is the number of nodes. Each square of the grid hosts a number positive or zero. This number is the number of links that connect two different nodes (in both directions). The diagonal axis of the grid corresponds to a diagonal of numbers zero, with the understanding that there is no node in relation to himself.<br /><br />
<h2>Explanations</h2>
Different heuristics are implemented. Each heuristic has its own objectives. <br />
<h3>Canonical heuristic</h3>
The first important heuristic is the canonical form of an equation. To save time by searching the terms in the equations, I consider a canonical form which operations are always organized in the same way; I also note that, as usual, we present equations in a canonical way. For example:<br /><br /><br />This equation has the following standard properties:<br />
<ol><li>terms them to the left of each sum are constant terms or constant numeric values.</li>
<li>then, on the right the unknown terms. 3 Finally, the sum is organized left to right starting with the end of greater power and each term is declining.</li></ol>
<br /><br />A heuristic calculates different situations in terms of the order of the products and the order of the additions. <br /><br />Division and subtraction are the same conditions except that the sign belongs to the number.<br /><br />Then in a second step, it will take into account the fact that:<br />
<ol><li>operations with numerical terms are Computable to give a number or possibly a Euclidean division.</li>
<li>operations terms coefficients are posted simultaneously after the selection of the heuristic: If a coefficient is divided by a coefficient then the coefficient disappears. Hence, the General transformation</li>
<li>operations of terms are and differences are grouped when unfamiliar terms are formed by the same powers. The terms coefficient and the numerical terms form an equation with products and sums. Their order is the same as for unknown terms.</li></ol>
<br />It is important to save time in calculating both perform the heuristic search and algebraically admitted simplifications. Clearly: priority to simplified product heuristics and heuristics of sums. Then back to the amount inside each product heuristics simplified by are heuristics (heuristics produces are supposed to be without effect at this stage).<br /><br /><br /></div><div class="ClearBoth"></div>skercrowSun, 11 Dec 2016 22:59:50 GMTUpdated Wiki: SP-Heuristic 20161211105950PUpdated Wiki: Documentationhttps://neuralmathematics.codeplex.com/documentation?version=10<div class="wikidoc"><b>Documentation</b><br /><br />All documentation documents are translated in English here with an automatic translator (Microsoft Translator).<br /><br /><br /><b>List of documents</b><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Key-Type&referringTitle=Documentation">SP-Key-Type</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Element-Nom&referringTitle=Documentation">SP-Element-Nom</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Check-Type&referringTitle=Documentation">SP-Check-Type</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Data-Class&referringTitle=Documentation">SP-Data-Class</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Neural-Command&referringTitle=Documentation">SP-Neural-Command</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Named-Neural&referringTitle=Documentation">SP-Named-Neural</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Operation-ar&referringTitle=Documentation">SP-Operation-ar</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Serialization&referringTitle=Documentation">SP-Serialization</a><br /><a href="https://neuralmathematics.codeplex.com/wikipage?title=SP-Distribution&referringTitle=Documentation">SP-Distribution</a><br /><br /></div><div class="ClearBoth"></div>skercrowSun, 11 Dec 2016 22:48:56 GMTUpdated Wiki: Documentation 20161211104856PUpdated Wiki: SP-Distributionhttps://neuralmathematics.codeplex.com/wikipage?title=SP-Distribution&version=3<div class="wikidoc"><h1>Implementation of algebraic distribution</h1>
<h2>Presentation</h2>
<h3>Document concerned</h3>
This document deals with algebraic operations of distribution. I am writing this short document to clarify the necessary programming work.<br /><br />
<h3>Versions</h3>
07/12/2016: initial version<br /><br />
<h3>Author</h3>
Invisible Media<br /><br />
<h2>Project</h2>
<h3>Framework of the project</h3>
This project is a digital and algebraic calculation software. This project is a way to train very long and tedious equations and to factor them according to a common approach. Goal: solve equations, find all the solutions algebraically and get an equation based on parameters and fixed digital data.<br />
<h3>All the features</h3>
The set of features is detailed in this document: All features (unbundled) .xlsx<br />
<h3>Name of the feature covered here</h3>
Neurons of algebraic distribution<br /><br />
<h2>Relative need</h2>
Neurons are elements of graph also called node. In each node in the graph, there may be 0 to N branches or arc where the other end is the next node.<br /><br />The arithmetic operations are one together recurring that perfectly fits the notion of graph. In particular, a complete equation is a tree set of operations. We're talking about graph when a node has multiple parents. An equation where some words are repeated will form a graph where a repeated word is associated with a single node, and each parent node will go on this node.<br /><br />The neurons of algebraic distribution concern all the multiplication of terms.<br />
<h2>Relationship with other features</h2>
<h3>Use</h3>
Neurons are objects that can communicate with each other. From the programming point of view, neurons form a directed graph. Then, each neuron with an application that is unique, the application traverses the graph through the neurons that react differently depending on the settings.<br /><br /><br />We note each node on a two-dimensional grid where is the number of nodes. Each square of the grid hosts a number positive or zero. This number is the number of links that connect two different nodes (in both directions). The diagonal axis of the grid corresponds to a diagonal of numbers zero, with the understanding that there is no node in relation to himself.<br /><br />
<h3>Explanations</h3>
Algebraic distribution sees both terms and and the product form a factorization that it should be distributed.<br /><br />Also, when and/or shall include at least an addition or subtraction so distribution is to multiply each term the sum of by each term sum of .<br /><br />Generally speaking, the distribution is to develop each term sum one by one.<br /><br /><img src="http://download-codeplex.sec.s-msft.com/Download?ProjectName=neuralmathematics&DownloadId=1623735" alt="distribute.png" title="distribute.png" /><br />
<ol><li>initial process </li></ol>
Develop the first term of each product <br />
<ol><li>iterative process
<ol><li>calculate the term following multiplied by the previous term </li>
<li>calculate the term following multiplied by the previous term </li>
<li>develop the term following each product 3 final process </li></ol></li></ol>
<ol><li>Cancel and cancel</li></ol>
<br /><br />It will take alternate distribution and the simplification of the product.<br /><br />There are more than 2 items produced to distribute, to first simplify the products obtained with the first two elements then repeat with two following. A special case of the product of terms is the term raised to the power ; What is the product of equal terms ??<br /><br />
<h2>Graphic view</h2>
Here's the graphic view of a neuron where how it graphically represents a neuron.<br /><br /><img src="http://download-codeplex.sec.s-msft.com/Download?ProjectName=neuralmathematics&DownloadId=1623736" alt="add-2-val.png" title="add-2-val.png" /> <img src="http://download-codeplex.sec.s-msft.com/Download?ProjectName=neuralmathematics&DownloadId=1623737" alt="add-2-var.png" title="add-2-var.png" /> <img src="http://download-codeplex.sec.s-msft.com/Download?ProjectName=neuralmathematics&DownloadId=1623738" alt="add-val-var.png" title="add-val-var.png" /> <img src="http://download-codeplex.sec.s-msft.com/Download?ProjectName=neuralmathematics&DownloadId=1623739" alt="add-var-val.png" title="add-var-val.png" /><br /><br />The two branches on the right are the operands of the operation (here the addition). For each operation, there are 6 configurations.<br />
<h2>Manufacture of neurons</h2>
I note that here are prefabricated neurons. A given equation, to break down the equation in terms of operations and build the graph of this equation using the templates available to neurons.<br /><br />So there is an initial background where each neuron has its own function and its own form. I also note that there is only a single main command for an equation: calculate the result of the equation giving a numerical value to each variable. Related variables, to always express the values by using the equation of this variable. For free variables, any numeric value is correct. Finally, for the unknown variables it comes to seek his equation based on the knowledge of the equations on the variables and the values of the free variables.<br /><br />To calculate the unknown variables, it must be remembered that the mathematical reasoning and algebra accept 2/3 variables to numeric values and one unknown. And usually, for a real function to a real variable, there is that two unknown variables; It is necessary and sufficient to create an intermediate unknown variable to get actually 2/3 variables to numeric values and one unknown.<br /><br /><br />Other operators are necessary to allow a set of mathematical sequences. Some instructions are needed:<br />
<ol><li>declaring a free variable </li>
<li>declaration of a bound variable</li>
<li>declaration of an unknown variable </li>
<li>equality operator to check</li>
<li>5 own equality operator</li>
<li>6 comparison operators</li>
<li>7 conditional operator: a comparison test, a new sequence if the test result is checked, a new sequence (optional) if the test result is denied.</li></ol>
<br /><br />These instructions are defined by templates of neurons. Construction of neurons is done during syntactic analysis of these instructions by specializing each template.<br /><br /><br />The constructive form is just the composition of the operator according to a human-readable representation. Also, the first neuron is called the whole equation.<br /><br />Finally, a heuristic decides the best form to give an equation considering the different models of algebraic operations: <br />
<ol><li>commutativity. </li>
<li>neutral elements,</li>
<li>absorbing elements,</li>
<li>distribution.</li>
<li>factorization.</li></ol>
<br /><br /><br /><br /></div><div class="ClearBoth"></div>skercrowSun, 11 Dec 2016 22:48:28 GMTUpdated Wiki: SP-Distribution 20161211104828P