SethTrowbridge/nn
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Compare commits

base: SethTrowbridge:cleanup
Branches Tags
SethTrowbridge:master
SethTrowbridge:cleanup
SethTrowbridge:network
SethTrowbridge:debug
SethTrowbridge:typescript
..
compare: SethTrowbridge:master
Branches Tags
SethTrowbridge:cleanup
SethTrowbridge:master
SethTrowbridge:network
SethTrowbridge:debug
SethTrowbridge:typescript

No commits in common. "cleanup" and "master" have entirely different histories.
cleanup ... master

9 changed files with 977 additions and 308 deletions
Show Stats Expand all files Collapse all files

717
index.html Normal file
View File

@ -0,0 +1,717 @@
<script>
/* Vector Library */
/*
Works with n-dimensional vectors: represented as arrays of numbers
*/
var V = {};
V.Subtract = function(inV1, inV2)
{
var out = [];
for(var i=0; i<inV1.length; i++)
{
out[i] = inV1[i] - inV2[i];
}
return out;
};
V.Add = function(inV1, inV2)
{
var out = [];
for(var i=0; i<inV1.length; i++)
{
out[i] = inV1[i] + inV2[i];
}
return out;
};
V.Distance = function(inV1, inV2)
{
return V.Length(V.Subtract(inV1, inV2))
};
V.Dot = function(inV1, inV2)
{
var out = 0;
for(var i=0; i<inV1.length; i++)
{
out += inV1[i] * inV2[i];
}
return out;
};
V.Multiply = function(inV1, inV2)
{
var out = [];
for(var i=0; i<inV1.length; i++)
{
out[i] = inV1[i] * inV2[i];
}
return out;
};
V.Length = function(inV1)
{
return Math.sqrt(V.Dot(inV1, inV1));
};
V.Scale = function(inV1, inScalar)
{
var out = [];
for(var i=0; i<inV1.length; i++)
{
out[i] = inV1[i] * inScalar;
}
return out;
};
V.Normalize = function(inV1)
{
return V.Scale(inV1, 1/V.Length(inV1));
};
V.Clone = function(inV1)
{
var out = [];
var i;
for(i=0; i<inV1.length; i++)
{
out[i] = inV1[i];
}
return out;
};
var M = {};
/**************************
M A T R I X
*/
// transform inC with inM
// returns the transformed inC
M.Transform = function(inM, inC)
{
var outM = [];
var outV = [];
var i, j;
for(i=0; i<inC.length; i++)
{
outV = [];
for(j=0; j<inM.length; j++)
{
outV[j] = V.Dot(inM[j], inC[i]);
}
outM.push(outV);
}
return outM;
};
// flip rows for columns in inM
// returns the modified Matrix
M.Transpose = function(inM)
{
var dimensions = inM[0].length;
var i, j;
var outM = [];
var outV = [];
for(i=0; i<dimensions; i++)
{
outV = [];
for(j=0; j<inM.length; j++)
{
//the Ith componenth of the Jth member
outV[j] = inM[j][i];
}
outM.push(outV);
}
return outM;
}
// returns a matrix that is the result of the outer product of inV1 and inV2
// where the Nth member of outM is a copy of V1, scaled by the Nth component of V2
M.Outer = function(inV1, inV2)
{
var outM = [];
var i;
for(i=0; i<inV2.length; i++)
{
outM.push(V.Scale(inV1, inV2[i]));
}
return outM;
};
/**************************
B A T C H
*/
//smash the members of inM with a softmax
M.Sigmoid = function(inM)
{
var i, j;
var outM = [];
var outV = [];
for(i=0; i<inM.length; i++)
{
outV = [];
for(j=0; j<inM[i].length; j++)
{
outV[j] = 1/(1 + Math.pow(Math.E, -inM[i][j]));
}
outM.push(outV);
}
return outM;
};
// return the derivatives of the members of inM (that have been run through the softmax)
M.Derivative = function(inM)
{
var i, j;
var component;
var outM = [];
var outV = [];
for(i=0; i<inM.length; i++)
{
outV = [];
for(j=0; j<inM[i].length; j++)
{
component = inM[i][j];
outV[j] = component*(1 - component);
}
outM.push(outV);
}
return outM;
};
// batch multiply these pairs of vectors
M.Multiply = function(inCloud1, inCloud2)
{
var i;
var outM = [];
for(i=0; i<inCloud1.length; i++)
{
outM.push(V.Multiply(inCloud1[i], inCloud2[i]));
};
return outM;
};
// batch add
M.Add = function(inCloud1, inCloud2)
{
var outM = [];
var i;
for(i=0; i<inCloud1.length; i++)
{
outM.push(V.Add(inCloud1[i], inCloud2[i]));
}
return outM;
};
M.Subtract = function(inCloud1, inCloud2)
{
var outM = [];
var i;
for(i=0; i<inCloud1.length; i++)
{
outM.push(V.Subtract(inCloud1[i], inCloud2[i]));
}
return outM;
};
M.Scale = function(inCloud1, inScalar)
{
var outM = [];
var i;
for(i=0; i<inCloud1.length; i++)
{
outM.push(V.Scale(inCloud1[i], inScalar));
}
return outM;
};
M.Clone = function(inM)
{
var i;
var outM;
var outV;
outM =[];
for(i=0; i<inM.length; i++)
{
outM.push(V.Clone(inM[i]));
}
return outM;
};
/**************************
B O U N D S
*/
// return the bounding box of inM as a two-member Matrix
M.Bounds = function(inM)
{
var dimensions = inM[0].length;
var i, j;
var min = [];
var max = [];
for(i=0; i<dimensions; i++)
{
min[i] = 9999999;
max[i] = -999999;
}
for(i=0; i<inM.length; i++)
{
for(j=0; j<dimensions; j++)
{
if(inM[i][j] < min[j])
{
min[j] = inM[i][j];
}
if(inM[i][j] > max[j])
{
max[j] = inM[i][j];
}
}
}
return [min, max];
};
// find the local coordinates for all the members of inM, within the bounding box inB
// returns a new Matrix of relative vectors
M.GlobalToLocal = function(inM, inB)
{
var dimensions = inB[0].length;
var i, j;
var outM = [];
var outV = [];
var size;
var min;
var denominator;
for(i=0; i<inM.length; i++)
{
outV = [];
for(j=0; j<dimensions; j++)
{
denominator = inB[1][j] - inB[0][j];
if(denominator == 0)
{
outV[j] = inB[1][j];// if min and max are the same, just output max
}
else
{
outV[j] = (inM[i][j] - inB[0][j])/denominator;
}
}
outM.push(outV);
}
return outM;
};
// find the global coordinates for all the members of inM, within the bounding box inB
// returns a new Matrix of global vectors
M.LocalToGlobal = function(inM, inB)
{
var dimensions = inB[0].length;
var i, j;
var outM = [];
var outV = [];
var size;
var min;
for(i=0; i<inM.length; i++)
{
outV = [];
for(j=0; j<dimensions; j++)
{
outV[j] = inB[0][j] + inM[i][j] * (inB[1][j] - inB[0][j]);
}
outM.push(outV);
}
return outM;
};
/**************************
C L O U D
*/
// return some number of points from inM as a new Matrix
M.Reduce = function(inM, inCount)
{
var largeGroupSize;
var largeGroupCount;
var smallGroupSize;
var outM = [];
largeGroupSize = Math.floor(inM.length/inM);
smallGroupSize = inM.length%inCount
for(i=0; i<inM-1; i++)
{
index = i*largeGroupSize + Math.floor(Math.random()*largeGroupSize);
outM.push( V.Clone(inM[index]) );
}
if(smallGroupSize != 0)
{
index = i*largeGroupSize + Math.floor(Math.random()*smallGroupSize)
outM.push( V.Clone(inM[index]) );
}
return outM;
};
// return a Matrix of length inCount, where all the members fall within the circle paramemters, including a bias
M.Circle = function(inCenter, inRadius, inBias, inCount)
{
var i, j;
var vector;
var length;
var outM = [];
for(i=0; i<inCount; i++)
{
//generate a random vector
vector = [];
for(j=0; j<inCenter.length; j++)
{
vector[j] = (Math.random() - 0.5);
}
//normalize the vector
vector = V.Scale(vector, 1/V.Length(vector));
//set a random length (with a bias)
length = Math.pow(Math.random(), Math.log(inBias)/Math.log(0.5))*inRadius;
vector = V.Scale(vector, length);
//move the vector to the center
vector = V.Add(vector, inCenter);
outM.push(vector);
}
return outM;
};
// return a Matrix of length inCount, where all the members fall within inBounds
M.Box = function(inBounds, inCount)
{
var vector;
var dimensions = inBounds[0].length;
var i, j;
var min, max;
var outM = [];
for(i=0; i<inCount; i++)
{
vector = [];
for(j=0; j<dimensions; j++)
{
min = inBounds[0][j];
max = inBounds[1][j];
vector[j] = min + Math.random()*(max - min);
}
outM.push(vector);
}
return outM;
};
//combine all the matricies in inList into one long Matrix
M.Combine = function(inList)
{
var i, j;
var outM = [];
for(i=0; i<inList.length; i++)
{
for(j=0; j<inList[i].length; j++)
{
outM.push(V.Clone(inList[i][j]));
}
}
return outM;
};
/*
PLEASE NOTE: These padding routines are unique to this library in that they
actually modify the input object(s) rather than returning modified copies!
*/
// add a new component (set to '1') to each member of inM
M.Pad = function(inM)
{
var i;
for(i=0; i<inM.length; i++)
{
inM[i].push(1);
}
return inM;
};
// remove the last component of each memeber of inM
M.Unpad = function(inM)
{
var i;
for(i=0; i<inM.length; i++)
{
inM[i].pop();
}
return inM;
};
// set the last component of each member of inM to 1
M.Repad = function(inM)
{
var i;
var last = inM[0].length-1;
for(i=0; i<inM.length; i++)
{
inM[i][last] = 1;
}
return inM;
};
</script>
<script>
var NN = {};
NN.TrainingSet = {};
NN.TrainingSet.Instances = [];
NN.TrainingSet.Create = function()
{
var obj = {};
obj.Input = [];
obj.Output = [];
obj.Order = [];
NN.TrainingSet.Instances.push(obj);
return obj;
};
NN.TrainingSet.AddPoint = function(inTrainingSet, inType, inData)
{
inTrainingSet.Input.push(inData);
inTrainingSet.Output.push(inType);
inTrainingSet.Order.push(inTrainingSet.Order.length);
};
NN.TrainingSet.AddCloud = function(inTrainingSet, inLabel, inCloud)
{
var i;
for(i=0; i<inCloud.length; i++)
{
NN.TrainingSet.AddPoint(inTrainingSet, inLabel, inCloud[i]);
}
};
NN.TrainingSet.Randomize = function(inTrainingSet)
{
var newOrder = [];
var selection;
while(inTrainingSet.Order.length != 0)
{
selection = Math.floor(inTrainingSet.Order.length * Math.random());
inTrainingSet.Order.splice(selection, 1);
newOrder.push(selection);
}
inTrainingSet.Order = newOrder;
};
NN.Layer = {};
NN.Layer.Create = function(sizeIn, sizeOut)
{
var i;
var min = [];
var max = [];
var obj = {};
sizeIn++;
obj.Forward = {};
for(i=0; i<sizeIn; i++)
{
min.push(-1);
max.push(1);
}
obj.Forward.Matrix = M.Box([min, max], sizeOut);
obj.Forward.StageInput = [];
obj.Forward.StageAffine = [];
obj.Forward.StageSigmoid = [];
obj.Forward.StageDerivative = [];
obj.Backward = {};
obj.Backward.Matrix = M.Transpose(obj.Forward.Matrix);
obj.Backward.StageInput = [];
obj.Backward.StageDerivative = [];
obj.Backward.StageAffine = [];
return obj;
};
NN.Layer.Forward = function(inLayer, inInput)
{
inLayer.Forward.StageInput = M.Pad(inInput); // Pad the input
inLayer.Forward.StageAffine = M.Transform(inLayer.Forward.Matrix, inLayer.Forward.StageInput);
inLayer.Forward.StageSigmoid = M.Sigmoid(inLayer.Forward.StageAffine);
return inLayer.Forward.StageSigmoid;
};
NN.Layer.Error = function(inLayer, inTarget)
{
return M.Subtract(inLayer.Forward.StageSigmoid, inTarget);
};
NN.Layer.Backward = function(inLayer, inInput)
{
/* We need the derivative of the forward pass, but only during the backward pass.
That's why-- even though it "belongs" to the forward pass-- it is being calculated here. */
inLayer.Forward.StageDerivative = M.Derivative(inLayer.Forward.StageSigmoid);
/* This transpose matrix is for sending the error back to a previous layer.
And again, even though it is derived directly from the forward matrix, it is only needed during the backward pass so we calculate it here.*/
inLayer.Backward.Matrix = M.Transpose(inLayer.Forward.Matrix);
/* When the error vector arrives at a layer, it always needs to be multiplied (read 'supressed') by the derivative of
what the layer output earlier during the forward pass.
So despite its name, Backward.StageDerivative contains the result of this *multiplication* and not some new derivative calculation.*/
inLayer.Backward.StageInput = inInput;
inLayer.Backward.StageDerivative = M.Multiply(inLayer.Backward.StageInput, inLayer.Forward.StageDerivative);
inLayer.Backward.StageAffine = M.Transform(inLayer.Backward.Matrix, inLayer.Backward.StageDerivative);
return M.Unpad(inLayer.Backward.StageAffine);// Unpad the output
};
NN.Layer.Adjust = function(inLayer, inLearningRate)
{
var deltas;
var vector;
var scalar;
var i, j;
for(i=0; i<inLayer.Forward.StageInput.length; i++)
{
deltas = M.Outer(inLayer.Forward.StageInput[i], inLayer.Backward.StageDerivative[i]);
deltas = M.Scale(deltas, inLearningRate);
inLayer.Forward.Matrix = M.Subtract(inLayer.Forward.Matrix, deltas);
}
};
NN.Layer.Stochastic = function(inLayer, inTrainingSet, inIterations)
{
/* this method is ONLY for testing individual layers, and does not translate to network-level training */
var i, j;
var current;
var error;
for(i=0; i<inIterations; i++)
{
NN.TrainingSet.Randomize(inTrainingSet);
for(j=0; j<inTrainingSet.Order.length; j++)
{
current = inTrainingSet.Order[j];
NN.Layer.Forward(inLayer, [inTrainingSet.Input[current]]);
error = M.Subtract(inLayer.Forward.StageSigmoid, [inTrainingSet.Output[current]]);
NN.Layer.Backward(inLayer, error);
NN.Layer.Adjust(inLayer, 0.1);
}
}
};
NN.Network = {};
NN.Network.Instances = [];
NN.Network.Create = function()
{
var obj = {};
var i;
obj.Layers = [];
obj.LearningRate = 0.1;
obj.Error = [];
for(i=0; i<arguments.length-1; i++)
{
obj.Layers.push(NN.Layer.Create(arguments[i], arguments[i+1]));
}
NN.Network.Instances.push(obj);
return obj;
};
NN.Network.Observe = function(inNetwork, inBatch)
{
var input = M.Clone(inBatch);
var i;
for(i=0; i<inNetwork.Layers.length; i++)
{
input = NN.Layer.Forward(inNetwork.Layers[i], input);
}
return inNetwork.Layers[inNetwork.Layers.length-1].Forward.StageSigmoid;
};
NN.Network.Error = function(inNetwork, inTraining)
{
return M.Subtract(inNetwork.Layers[inNetwork.Layers.length-1].Forward.StageSigmoid, inTraining);
};
NN.Network.Learn = function(inNetwork, inError)
{
var input = inError;
var i;
for(i=inNetwork.Layers.length-1; i>=0; i--)
{
input = NN.Layer.Backward(inNetwork.Layers[i], input);
NN.Layer.Adjust(inNetwork.Layers[i], inNetwork.LearningRate);
}
};
NN.Network.Batch = function(inNetwork, inTrainingSet, inIterations)
{
var i;
for(i=0; i<inIterations; i++)
{
NN.Network.Observe(inNetwork, inTrainingSet.Input);
inNetwork.Error = NN.Network.Error(inNetwork, inTrainingSet.Output)
NN.Network.Learn(inNetwork, inNetwork.Error);
}
};
NN.Network.Stochastic = function(inNetwork, inTrainingSet, inIterations)
{
var i, j;
var current;
for(i=0; i<inIterations; i++)
{
NN.TrainingSet.Randomize(inTrainingSet);
for(j=0; j<inTrainingSet.Order.length; j++)
{
current = inTrainingSet.Order[j];
NN.Network.Observe(inNetwork, [inTrainingSet.Input[current]]);
inNetwork.Error = NN.Network.Error(inNetwork, [inTrainingSet.Output[current]]);
NN.Network.Learn(inNetwork, inNetwork.Error);
}
}
};
</script>
<script>
let matrix1 = [
[-0.43662948305036675, -0.368590640707799, -0.23227179558890843],
[-0.004292653969505622, 0.38670055222186317, -0.2478421495365568],
[0.738181366836224, 0.3389203747353555, 0.4920200816404332]
];
let matrix2 = [
[0.7098703863463034, 0.35485944251238033, 0.7642849892333241, 0.03046174288491077],
[-0.30655426258144347, 0.45509633551425077, -0.5013795222004322, -0.3421292736637427]
];
let input = [
[ 0.1, 0.05],
[ 0.0, -0.06],
[ 0.99, 0.85],
[ 1.2, 1.05]
];
let output = [
[1, 0],
[1, 0],
[0, 1],
[0, 1]
];
let nn1 = NN.Network.Create(2, 3, 2);
nn1.Layers[0].Forward.Matrix = matrix1;
nn1.Layers[1].Forward.Matrix = matrix2;
nn1.LearningRate = 0.1;
//let logLayers = inNN => inNN.Layers.forEach(L=>console.log(L.Forward.Matrix));
NN.Network.Batch(nn1, {Input:input, Output:output}, 1000);
console.log(NN.Network.Observe(nn1, input));
</script>

10
index.js
View File

@ -1,10 +0,0 @@
import { Build, Learn, Label } from "./nn.ts";
import { default as Clean } from "./iris.js";
let [ inputs, labels ] = Clean();
let layers = Build(4, 10, 3);
let errors = Learn(inputs, layers, labels, 500, 0.1);
let output = Label(inputs, layers, true);
console.log(output);

238
iris.js
View File

@ -1,238 +0,0 @@
export default () =>
{
let inputs = [];
let labels = [];
let min = [999, 999, 999, 999];
let max = [-99, -99, -99, -99];
DataBig.split("\n").forEach((inRowValue, inRowIndex)=>
{
let currentInput = [];
let currentLabel = [];
if(inRowIndex == 0){ return; }
inRowValue.split(",").forEach((inCellValue, inCellIndex)=>
{
if(inCellIndex == 4)
{
switch(inCellValue)
{
case `"Setosa"`:
currentLabel = [1, 0, 0];
break;
case `"Versicolor"` :
currentLabel = [0, 1, 0];
break;
case `"Virginica"` :
currentLabel = [0, 0, 1];
break;
}
}
else
{
let value = parseFloat(inCellValue);
if(min[inCellIndex] > value){ min[inCellIndex] = value; }
if(max[inCellIndex] < value){ max[inCellIndex] = value; }
currentInput.push(value);
}
});
inputs.push(currentInput);
labels.push(currentLabel);
});
console.log(min, max);
inputs.forEach((inRowValue, inRowIndex)=>
{
inRowValue.forEach((inCellValue, inCellIndex)=>
{
inputs[inRowIndex][inCellIndex] = (inCellValue - min[inCellIndex])/(max[inCellIndex] - min[inCellIndex]);
});
})
return [ inputs, labels ];
};
const Data = `"sepal.length","sepal.width","petal.length","petal.width","variety"
5.1,3.5,1.4,.2,"Setosa"
4.9,3,1.4,.2,"Setosa"
4.7,3.2,1.3,.2,"Setosa"
4.6,3.1,1.5,.2,"Setosa"
5,3.6,1.4,.2,"Setosa"
5.4,3.9,1.7,.4,"Setosa"
4.6,3.4,1.4,.3,"Setosa"
7,3.2,4.7,1.4,"Versicolor"
6.4,3.2,4.5,1.5,"Versicolor"
6.9,3.1,4.9,1.5,"Versicolor"
5.5,2.3,4,1.3,"Versicolor"
6.5,2.8,4.6,1.5,"Versicolor"
5.7,2.8,4.5,1.3,"Versicolor"
6.3,3.3,4.7,1.6,"Versicolor"
4.9,2.4,3.3,1,"Versicolor"
6.6,2.9,4.6,1.3,"Versicolor"
5.2,2.7,3.9,1.4,"Versicolor"
5,2,3.5,1,"Versicolor"
5.7,2.5,5,2,"Virginica"
5.8,2.8,5.1,2.4,"Virginica"
6.4,3.2,5.3,2.3,"Virginica"
6.5,3,5.5,1.8,"Virginica"
7.7,3.8,6.7,2.2,"Virginica"
7.7,2.6,6.9,2.3,"Virginica"
6,2.2,5,1.5,"Virginica"
6.9,3.2,5.7,2.3,"Virginica"
5.6,2.8,4.9,2,"Virginica"
7.7,2.8,6.7,2,"Virginica"
6.3,2.7,4.9,1.8,"Virginica"
6.7,3.3,5.7,2.1,"Virginica"`;
const DataBig = `"sepal.length","sepal.width","petal.length","petal.width","variety"
5.1,3.5,1.4,.2,"Setosa"
4.9,3,1.4,.2,"Setosa"
4.7,3.2,1.3,.2,"Setosa"
4.6,3.1,1.5,.2,"Setosa"
5,3.6,1.4,.2,"Setosa"
5.4,3.9,1.7,.4,"Setosa"
4.6,3.4,1.4,.3,"Setosa"
5,3.4,1.5,.2,"Setosa"
4.4,2.9,1.4,.2,"Setosa"
4.9,3.1,1.5,.1,"Setosa"
5.4,3.7,1.5,.2,"Setosa"
4.8,3.4,1.6,.2,"Setosa"
4.8,3,1.4,.1,"Setosa"
4.3,3,1.1,.1,"Setosa"
5.8,4,1.2,.2,"Setosa"
5.7,4.4,1.5,.4,"Setosa"
5.4,3.9,1.3,.4,"Setosa"
5.1,3.5,1.4,.3,"Setosa"
5.7,3.8,1.7,.3,"Setosa"
5.1,3.8,1.5,.3,"Setosa"
5.4,3.4,1.7,.2,"Setosa"
5.1,3.7,1.5,.4,"Setosa"
4.6,3.6,1,.2,"Setosa"
5.1,3.3,1.7,.5,"Setosa"
4.8,3.4,1.9,.2,"Setosa"
5,3,1.6,.2,"Setosa"
5,3.4,1.6,.4,"Setosa"
5.2,3.5,1.5,.2,"Setosa"
5.2,3.4,1.4,.2,"Setosa"
4.7,3.2,1.6,.2,"Setosa"
4.8,3.1,1.6,.2,"Setosa"
5.4,3.4,1.5,.4,"Setosa"
5.2,4.1,1.5,.1,"Setosa"
5.5,4.2,1.4,.2,"Setosa"
4.9,3.1,1.5,.2,"Setosa"
5,3.2,1.2,.2,"Setosa"
5.5,3.5,1.3,.2,"Setosa"
4.9,3.6,1.4,.1,"Setosa"
4.4,3,1.3,.2,"Setosa"
5.1,3.4,1.5,.2,"Setosa"
5,3.5,1.3,.3,"Setosa"
4.5,2.3,1.3,.3,"Setosa"
4.4,3.2,1.3,.2,"Setosa"
5,3.5,1.6,.6,"Setosa"
5.1,3.8,1.9,.4,"Setosa"
4.8,3,1.4,.3,"Setosa"
5.1,3.8,1.6,.2,"Setosa"
4.6,3.2,1.4,.2,"Setosa"
5.3,3.7,1.5,.2,"Setosa"
5,3.3,1.4,.2,"Setosa"
7,3.2,4.7,1.4,"Versicolor"
6.4,3.2,4.5,1.5,"Versicolor"
6.9,3.1,4.9,1.5,"Versicolor"
5.5,2.3,4,1.3,"Versicolor"
6.5,2.8,4.6,1.5,"Versicolor"
5.7,2.8,4.5,1.3,"Versicolor"
6.3,3.3,4.7,1.6,"Versicolor"
4.9,2.4,3.3,1,"Versicolor"
6.6,2.9,4.6,1.3,"Versicolor"
5.2,2.7,3.9,1.4,"Versicolor"
5,2,3.5,1,"Versicolor"
5.9,3,4.2,1.5,"Versicolor"
6,2.2,4,1,"Versicolor"
6.1,2.9,4.7,1.4,"Versicolor"
5.6,2.9,3.6,1.3,"Versicolor"
6.7,3.1,4.4,1.4,"Versicolor"
5.6,3,4.5,1.5,"Versicolor"
5.8,2.7,4.1,1,"Versicolor"
6.2,2.2,4.5,1.5,"Versicolor"
5.6,2.5,3.9,1.1,"Versicolor"
5.9,3.2,4.8,1.8,"Versicolor"
6.1,2.8,4,1.3,"Versicolor"
6.3,2.5,4.9,1.5,"Versicolor"
6.1,2.8,4.7,1.2,"Versicolor"
6.4,2.9,4.3,1.3,"Versicolor"
6.6,3,4.4,1.4,"Versicolor"
6.8,2.8,4.8,1.4,"Versicolor"
6.7,3,5,1.7,"Versicolor"
6,2.9,4.5,1.5,"Versicolor"
5.7,2.6,3.5,1,"Versicolor"
5.5,2.4,3.8,1.1,"Versicolor"
5.5,2.4,3.7,1,"Versicolor"
5.8,2.7,3.9,1.2,"Versicolor"
6,2.7,5.1,1.6,"Versicolor"
5.4,3,4.5,1.5,"Versicolor"
6,3.4,4.5,1.6,"Versicolor"
6.7,3.1,4.7,1.5,"Versicolor"
6.3,2.3,4.4,1.3,"Versicolor"
5.6,3,4.1,1.3,"Versicolor"
5.5,2.5,4,1.3,"Versicolor"
5.5,2.6,4.4,1.2,"Versicolor"
6.1,3,4.6,1.4,"Versicolor"
5.8,2.6,4,1.2,"Versicolor"
5,2.3,3.3,1,"Versicolor"
5.6,2.7,4.2,1.3,"Versicolor"
5.7,3,4.2,1.2,"Versicolor"
5.7,2.9,4.2,1.3,"Versicolor"
6.2,2.9,4.3,1.3,"Versicolor"
5.1,2.5,3,1.1,"Versicolor"
5.7,2.8,4.1,1.3,"Versicolor"
6.3,3.3,6,2.5,"Virginica"
5.8,2.7,5.1,1.9,"Virginica"
7.1,3,5.9,2.1,"Virginica"
6.3,2.9,5.6,1.8,"Virginica"
6.5,3,5.8,2.2,"Virginica"
7.6,3,6.6,2.1,"Virginica"
4.9,2.5,4.5,1.7,"Virginica"
7.3,2.9,6.3,1.8,"Virginica"
6.7,2.5,5.8,1.8,"Virginica"
7.2,3.6,6.1,2.5,"Virginica"
6.5,3.2,5.1,2,"Virginica"
6.4,2.7,5.3,1.9,"Virginica"
6.8,3,5.5,2.1,"Virginica"
5.7,2.5,5,2,"Virginica"
5.8,2.8,5.1,2.4,"Virginica"
6.4,3.2,5.3,2.3,"Virginica"
6.5,3,5.5,1.8,"Virginica"
7.7,3.8,6.7,2.2,"Virginica"
7.7,2.6,6.9,2.3,"Virginica"
6,2.2,5,1.5,"Virginica"
6.9,3.2,5.7,2.3,"Virginica"
5.6,2.8,4.9,2,"Virginica"
7.7,2.8,6.7,2,"Virginica"
6.3,2.7,4.9,1.8,"Virginica"
6.7,3.3,5.7,2.1,"Virginica"
7.2,3.2,6,1.8,"Virginica"
6.2,2.8,4.8,1.8,"Virginica"
6.1,3,4.9,1.8,"Virginica"
6.4,2.8,5.6,2.1,"Virginica"
7.2,3,5.8,1.6,"Virginica"
7.4,2.8,6.1,1.9,"Virginica"
7.9,3.8,6.4,2,"Virginica"
6.4,2.8,5.6,2.2,"Virginica"
6.3,2.8,5.1,1.5,"Virginica"
6.1,2.6,5.6,1.4,"Virginica"
7.7,3,6.1,2.3,"Virginica"
6.3,3.4,5.6,2.4,"Virginica"
6.4,3.1,5.5,1.8,"Virginica"
6,3,4.8,1.8,"Virginica"
6.9,3.1,5.4,2.1,"Virginica"
6.7,3.1,5.6,2.4,"Virginica"
6.9,3.1,5.1,2.3,"Virginica"
5.8,2.7,5.1,1.9,"Virginica"
6.8,3.2,5.9,2.3,"Virginica"
6.7,3.3,5.7,2.5,"Virginica"
6.7,3,5.2,2.3,"Virginica"
6.3,2.5,5,1.9,"Virginica"
6.5,3,5.2,2,"Virginica"
6.2,3.4,5.4,2.3,"Virginica"
5.9,3,5.1,1.8,"Virginica"`;

31
m.test.js
View File

@ -11,10 +11,10 @@ Deno.test("Iterate.Loop", ()=>
assertEquals(cloud[0][0], 0); assertEquals(cloud[0][0], 0);
assertEquals(cloud[3][2], 5, "correct output"); assertEquals(cloud[3][2], 5, "correct output");
}); });
Deno.test("Iterate.Copy", ()=> Deno.test("Iterate.Edit", ()=>
{ {
const c = [[1, 2], [3, 4]] const c = [[1, 2], [3, 4]]
const t = M.Iterate.Copy(c, (i)=>i); const t = M.Iterate.Edit(c, (i)=>i);
assertEquals(t.length, c.length, "correct count"); assertEquals(t.length, c.length, "correct count");
assertEquals(t[0][0], c[0][0], "correct dimensions"); assertEquals(t[0][0], c[0][0], "correct dimensions");
assertEquals(t[1][1], c[1][1], "correct placement"); assertEquals(t[1][1], c[1][1], "correct placement");
@ -146,39 +146,20 @@ Deno.test("Batch.Subtract", ()=>
assertEquals(t[0].length, 2, "correct dimensions"); assertEquals(t[0].length, 2, "correct dimensions");
assertEquals(t[1][0], 2.5, "correct placement"); assertEquals(t[1][0], 2.5, "correct placement");
}); });
Deno.test("Batch.Sig", ()=> Deno.test("Batch.Sigmoid", ()=>
{ {
const m = [[-1000, 1000]]; const m = [[-1000, 1000]];
const t = M.Batch.Sig(m); const t = M.Batch.Sigmoid(m);
assertEquals(t.length, 1, "correct count"); assertEquals(t.length, 1, "correct count");
assertEquals(t[0].length, 2, "correct dimensions"); assertEquals(t[0].length, 2, "correct dimensions");
assert(t[0][0]>=0 && t[0][0]<0.5); assert(t[0][0]>=0 && t[0][0]<0.5);
assert(t[0][1]<=1 && t[0][1]>0.5, "correct placement"); assert(t[0][1]<=1 && t[0][1]>0.5, "correct placement");
}); });
Deno.test("Batch.SigDeriv", ()=> Deno.test("Batch.Derivative", ()=>
{ {
const m = [[-1000, 0, 1000]]; const m = [[-1000, 0, 1000]];
const t = M.Batch.SigDeriv(M.Batch.Sig(m)); const t = M.Batch.Derivative(M.Batch.Sigmoid(m));
assertEquals(t.length, 1, "correct count"); assertEquals(t.length, 1, "correct count");
assertEquals(t[0].length, 3, "correct dimensions"); assertEquals(t[0].length, 3, "correct dimensions");
assert(t[0][0]<t[0][1] && t[0][1]>t[0][2]); assert(t[0][0]<t[0][1] && t[0][1]>t[0][2]);
}); });
Deno.test("Batch.Rec", ()=>
{
const m = [[-1, 1, 10]];
const t = M.Batch.Rec(m);
assert(t[0][0] == 0);
assert(t[0][1] == 1);
assert(t[0][2] == 10);
});
Deno.test("Batch.RecDeriv", ()=>
{
const m = [[-1, 1, 10]];
const t = M.Batch.RecDeriv(m);
assert(t[0][0] == 0);
assert(t[0][1] == 1);
assert(t[0][2] == 1);
});

26
m.ts
View File

@ -16,27 +16,35 @@ const Methods = {
for(i=0; i<inCount; i++) for(i=0; i<inCount; i++)
{ {
outputVector = []; outputVector = [];
for(j=0; j<inDimensions; j++){ outputVector.push(inFunction(j, i, outputVector)); } for(j=0; j<inDimensions; j++)
{
outputVector.push(inFunction(j, i, outputVector));
}
outputCloud.push(outputVector); outputCloud.push(outputVector);
} }
return outputCloud; return outputCloud;
}, },
Copy: (inCloud:Cloud.M, inFunction:Cloud.HandleEdit):Cloud.M=> inCloud.map((row:Cloud.V):Cloud.V=> row.map(inFunction)), Edit: (inCloud:Cloud.M, inFunction:Cloud.HandleEdit):Cloud.M=> inCloud.map((row:Cloud.V):Cloud.V=>row.map(inFunction))
Edit: (inCloud:Cloud.M, inFunction:Cloud.HandleEdit):void => inCloud.forEach((row:Cloud.V):void=>row.forEach(inFunction))
}, },
Create: Create:
{ {
Box: (inV1:Cloud.V, inV2:Cloud.V, inCount:number):Cloud.M=> Methods.Iterate.Loop(inV1.length, inCount, i=> inV1[i]+(inV2[i]-inV1[i])*Math.random()), Box: (inV1:Cloud.V, inV2:Cloud.V, inCount:number):Cloud.M=> Methods.Iterate.Loop(inV1.length, inCount, i=> inV1[i]+(inV2[i]-inV1[i])*Math.random()),
Transpose: (inCloud:Cloud.M):Cloud.M=> Methods.Iterate.Loop(inCloud.length, inCloud[0].length, (i, row)=> inCloud[i][row]), Transpose: (inCloud:Cloud.M):Cloud.M=> Methods.Iterate.Loop(inCloud.length, inCloud[0].length, (i, row)=> inCloud[i][row]),
Outer: (inV1:Cloud.V, inV2:Cloud.V):Cloud.M=> Methods.Iterate.Loop(inV1.length, inV2.length, (i, row)=> inV1[i]*inV2[row]), Outer: (inV1:Cloud.V, inV2:Cloud.V):Cloud.M=> Methods.Iterate.Loop(inV1.length, inV2.length, (i, row)=> inV1[i]*inV2[row]),
Clone: (inCloud:Cloud.M):Cloud.M=> Methods.Iterate.Copy(inCloud, i=> i), Clone: (inCloud:Cloud.M):Cloud.M=> Methods.Iterate.Edit(inCloud, i=> i)
Padded: (inCloud:Cloud.M):Cloud.M=> inCloud.map((row:Cloud.V)=> [...row, 1])
}, },
Mutate: Mutate:
{ {
Pad: (inCloud:Cloud.M):Cloud.M=> {inCloud.forEach((row:Cloud.V)=> row.push(1)); return inCloud; }, Pad: (inCloud:Cloud.M):Cloud.M=> {inCloud.forEach((row:Cloud.V)=> row.push(1)); return inCloud; },
Unpad: (inCloud:Cloud.M):Cloud.M=> {inCloud.forEach((row:Cloud.V)=> row.pop()); return inCloud; } Unpad: (inCloud:Cloud.M):Cloud.M=> {inCloud.forEach((row:Cloud.V)=> row.pop()); return inCloud; }
}, },
Test:
{
Dot:(v1:Cloud.V, v2:Cloud.V):number=>
{
return v1.reduce((sum, current, index)=> sum + current*v2[index]);
}
},
Single: Single:
{ {
Subtract: (inV1:Cloud.V, inV2:Cloud.V):Cloud.V=> inV1.map((component, i)=> component-inV2[i]), Subtract: (inV1:Cloud.V, inV2:Cloud.V):Cloud.V=> inV1.map((component, i)=> component-inV2[i]),
@ -48,11 +56,9 @@ const Methods = {
Subtract: (inCloud1:Cloud.M, inCloud2:Cloud.M):Cloud.M=> inCloud1.map((row:Cloud.V, rowIndex:number)=> Methods.Single.Subtract(row, inCloud2[rowIndex])), Subtract: (inCloud1:Cloud.M, inCloud2:Cloud.M):Cloud.M=> inCloud1.map((row:Cloud.V, rowIndex:number)=> Methods.Single.Subtract(row, inCloud2[rowIndex])),
Multiply: (inCloud1:Cloud.M, inCloud2:Cloud.M):Cloud.M=> inCloud1.map((row:Cloud.V, rowIndex:number)=> Methods.Single.Multiply(row, inCloud2[rowIndex])), Multiply: (inCloud1:Cloud.M, inCloud2:Cloud.M):Cloud.M=> inCloud1.map((row:Cloud.V, rowIndex:number)=> Methods.Single.Multiply(row, inCloud2[rowIndex])),
Affine: (inCloud1:Cloud.M, inCloud2:Cloud.M):Cloud.M=> inCloud1.map((row:Cloud.V)=> Methods.Single.Affine(row, inCloud2)), Affine: (inCloud1:Cloud.M, inCloud2:Cloud.M):Cloud.M=> inCloud1.map((row:Cloud.V)=> Methods.Single.Affine(row, inCloud2)),
Sig: (inCloud:Cloud.M):Cloud.M=> Methods.Iterate.Copy(inCloud, i=>1/(1+Math.pow(Math.E, -i))), Sigmoid: (inCloud:Cloud.M):Cloud.M=> Methods.Iterate.Edit(inCloud, i=>1/(1+Math.pow(Math.E, -i))),
SigDeriv: (inCloud:Cloud.M):Cloud.M=> Methods.Iterate.Copy(inCloud, i=>i*(1-i)), Derivative: (inCloud:Cloud.M):Cloud.M=> Methods.Iterate.Edit(inCloud, i=>i*(1-i)),
Rec: (inCloud:Cloud.M):Cloud.M=> Methods.Iterate.Copy(inCloud, i=> i<=0 ? 0 : i), Scale: (inCloud:Cloud.M, inScalar:number):Cloud.M=> Methods.Iterate.Edit(inCloud, i=>i*inScalar)
RecDeriv: (inCloud:Cloud.M):Cloud.M=> Methods.Iterate.Copy(inCloud, i=> i<=0 ? 0 : 1),
Scale: (inCloud:Cloud.M, inScalar:number):Cloud.M=> Methods.Iterate.Copy(inCloud, i=>i*inScalar)
} }
}; };

14
methods.md Normal file
View File

@ -0,0 +1,14 @@
box(boundingBox, count) // done
transpose(inMatrix) // done
outer(inv1, inv2) // done
clone(inCloud) // done
pad(inCloud) // done
unpad(inCloud) // done
transform(inCloud, inMatrix) // done
sigmoid(inCloud) // 1/(1+e^x) // done
derivative(inCloud) // x*(1-x) // done
scale(inCloud1, inV) // done
subtract(inCloud1, inCloud2) // done
multiply(inCloud1, inCloud2) // done

7
nn.test.js
View File

@ -18,7 +18,7 @@ Deno.test("NN.Split", ()=>
assert(output); assert(output);
assertEquals(input.length, output.length, "data split into equal input and output"); assertEquals(input.length, output.length, "data split into equal input and output");
assertEquals(input[0].length, 2, "unpadded input"); assertEquals(input[0].length, 3, "padded input");
assertEquals(output[0].length, 2, "unpadded output"); assertEquals(output[0].length, 2, "unpadded output");
}); });
@ -27,7 +27,7 @@ Deno.test("NN.Build", ()=>
layers = Build(2, 5, 2); layers = Build(2, 5, 2);
assertEquals(layers.length, 2, "correct number of matrices"); assertEquals(layers.length, 2, "correct number of matrices");
assertEquals(layers[0][0].length, input[0].length+1, "input: padded input"); assertEquals(layers[0][0].length, input[0].length, "input: padded input");
assertEquals(layers[0].length, 5, "input: unpadded output"); assertEquals(layers[0].length, 5, "input: unpadded output");
assertEquals(layers[1][0].length, 6, "hidden: padded input"); assertEquals(layers[1][0].length, 6, "hidden: padded input");
@ -43,8 +43,7 @@ Deno.test("NN.Label", ()=>
Deno.test("NN.Learn", ()=> Deno.test("NN.Learn", ()=>
{ {
let error = Learn(input, layers, output, 50, 0.2); let error = Learn(input, layers, output, 1000, 0.1);
console.log(error);
assertEquals(error.length, output.length); assertEquals(error.length, output.length);
let total = 0; let total = 0;
let count = error.length*error[0].length; let count = error.length*error[0].length;

31
nn.ts
View File

@ -5,8 +5,7 @@ const Forward = (inData:Cloud.M, inLayers:N):N =>
{ {
let i:number; let i:number;
let stages:N = [inData]; let stages:N = [inData];
let nonLinear = (inIndex:number):any=> inIndex >= inLayers.length-1 ? M.Batch.Sig : M.Batch.Rec; let process = (index:number):Cloud.M => M.Batch.Sigmoid(M.Batch.Affine(stages[index], inLayers[index]));
let process = (index:number):Cloud.M => nonLinear(index)(M.Batch.Affine(stages[index], inLayers[index]));
for(i=0; i<inLayers.length-1; i++){ stages[i+1] = M.Mutate.Pad(process(i)); } for(i=0; i<inLayers.length-1; i++){ stages[i+1] = M.Mutate.Pad(process(i)); }
stages[i+1] = process(i); stages[i+1] = process(i);
@ -16,11 +15,10 @@ const Backward = (inStages:N, inLayers:N, inGoals:Cloud.M, inRate:number):N =>
{ {
let i:number; let i:number;
let errorBack:Cloud.M = M.Batch.Subtract(inStages[inStages.length-1], inGoals); let errorBack:Cloud.M = M.Batch.Subtract(inStages[inStages.length-1], inGoals);
let nonLinear = (inIndex:number):any=> inIndex >= inLayers.length-1 ? M.Batch.SigDeriv : M.Batch.RecDeriv;
for(i=inLayers.length-1; i>=0; i--) for(i=inLayers.length-1; i>=0; i--)
{ {
let errorScaled:Cloud.M = M.Batch.Multiply(errorBack, nonLinear(i)(inStages[i+1])); let errorScaled:Cloud.M = M.Batch.Multiply(errorBack, M.Batch.Derivative(inStages[i+1]));
errorBack = M.Batch.Affine(errorScaled, M.Create.Transpose(inLayers[i])); errorBack = M.Batch.Affine(errorScaled, M.Create.Transpose(inLayers[i]));
errorScaled.forEach((inScaledError:Cloud.V, inIndex:number)=> errorScaled.forEach((inScaledError:Cloud.V, inIndex:number)=>
{ {
@ -42,8 +40,10 @@ const Split = (inTrainingSet:Cloud.M, inHeaderLabel:Cloud.V, inHeaderKeep:Cloud.
} }
inTrainingSet.forEach((row:Cloud.V):void => inTrainingSet.forEach((row:Cloud.V):void =>
{ {
data.push( inHeaderKeep.map((i:number)=>row[i]) ); let vectorData = [ ...inHeaderKeep.map((i:number)=>row[i]), 1];
label.push( inHeaderLabel.map((i:number)=>row[i]) ); let vectorLabel = inHeaderLabel.map((i:number)=>row[i])
data.push( vectorData );
label.push( vectorLabel );
}); });
return [ data, label ]; return [ data, label ];
}; };
@ -58,28 +58,17 @@ const Build = (...inLayers:Array<number>):N =>
} }
return output; return output;
}; };
const Label = (inData:Cloud.M, inLayers:N, inRound:boolean):Cloud.M => const Label = (inData:Cloud.M, inLayers:N):Cloud.M =>
{ {
let stages:N = Forward(M.Create.Padded(inData), inLayers); let stages:N = Forward(inData, inLayers);
let output = stages[stages.length-1]; return stages[stages.length-1];
if(inRound)
{
output.forEach(row=>
{
row.forEach((cell, i)=>
{
row[i] = (Math.round(cell * 100) / 100);
});
});
}
return output;
}; };
const Learn = (inData:Cloud.M, inLayers:N, inLabels:Cloud.M, inIterations:number, inRate:number):Cloud.M => const Learn = (inData:Cloud.M, inLayers:N, inLabels:Cloud.M, inIterations:number, inRate:number):Cloud.M =>
{ {
let stages:N = []; let stages:N = [];
for(let i=0; i<inIterations; i++) for(let i=0; i<inIterations; i++)
{ {
stages = Forward(M.Create.Padded(inData), inLayers); stages = Forward(inData, inLayers);
Backward(stages, inLayers, inLabels, inRate); Backward(stages, inLayers, inLabels, inRate);
} }
return M.Batch.Subtract(stages[stages.length-1], inLabels); return M.Batch.Subtract(stages[stages.length-1], inLabels);

211
nn_old.js Normal file
View File

@ -0,0 +1,211 @@
var NN = {};
NN.TrainingSet = {};
NN.TrainingSet.Instances = [];
NN.TrainingSet.Create = function()
{
var obj = {};
obj.Input = [];
obj.Output = [];
obj.Order = [];
NN.TrainingSet.Instances.push(obj);
return obj;
};
NN.TrainingSet.AddPoint = function(inTrainingSet, inType, inData)
{
inTrainingSet.Input.push(inData);
inTrainingSet.Output.push(inType);
inTrainingSet.Order.push(inTrainingSet.Order.length);
};
NN.TrainingSet.AddCloud = function(inTrainingSet, inLabel, inCloud)
{
var i;
for(i=0; i<inCloud.length; i++)
{
NN.TrainingSet.AddPoint(inTrainingSet, inLabel, inCloud[i]);
}
};
NN.TrainingSet.Randomize = function(inTrainingSet)
{
var newOrder = [];
var selection;
while(inTrainingSet.Order.length != 0)
{
selection = Math.floor(inTrainingSet.Order.length * Math.random());
inTrainingSet.Order.splice(selection, 1);
newOrder.push(selection);
}
inTrainingSet.Order = newOrder;
};
NN.Layer = {};
NN.Layer.Create = function(sizeIn, sizeOut)
{
var i;
var min = [];
var max = [];
var obj = {};
sizeIn++;
obj.Forward = {};
for(i=0; i<sizeIn; i++)
{
min.push(-1);
max.push(1);
}
obj.Forward.Matrix = M.Box([min, max], sizeOut);
obj.Forward.StageInput = [];
obj.Forward.StageAffine = [];
obj.Forward.StageSigmoid = [];
obj.Forward.StageDerivative = [];
obj.Backward = {};
obj.Backward.Matrix = M.Transpose(obj.Forward.Matrix);
obj.Backward.StageInput = [];
obj.Backward.StageDerivative = [];
obj.Backward.StageAffine = [];
return obj;
};
NN.Layer.Forward = function(inLayer, inInput)
{
inLayer.Forward.StageInput = M.Pad(inInput); // Pad the input
inLayer.Forward.StageAffine = M.Transform(inLayer.Forward.Matrix, inLayer.Forward.StageInput);
inLayer.Forward.StageSigmoid = M.Sigmoid(inLayer.Forward.StageAffine);
return inLayer.Forward.StageSigmoid;
};
NN.Layer.Error = function(inLayer, inTarget)
{
return M.Subtract(inLayer.Forward.StageSigmoid, inTarget);
};
NN.Layer.Backward = function(inLayer, inInput)
{
/* We need the derivative of the forward pass, but only during the backward pass.
That's why-- even though it "belongs" to the forward pass-- it is being calculated here. */
inLayer.Forward.StageDerivative = M.Derivative(inLayer.Forward.StageSigmoid);
/* This transpose matrix is for sending the error back to a previous layer.
And again, even though it is derived directly from the forward matrix, it is only needed during the backward pass so we calculate it here.*/
inLayer.Backward.Matrix = M.Transpose(inLayer.Forward.Matrix);
/* When the error vector arrives at a layer, it always needs to be multiplied (read 'supressed') by the derivative of
what the layer output earlier during the forward pass.
So despite its name, Backward.StageDerivative contains the result of this *multiplication* and not some new derivative calculation.*/
inLayer.Backward.StageInput = inInput;
inLayer.Backward.StageDerivative = M.Multiply(inLayer.Backward.StageInput, inLayer.Forward.StageDerivative);
inLayer.Backward.StageAffine = M.Transform(inLayer.Backward.Matrix, inLayer.Backward.StageDerivative);
return M.Unpad(inLayer.Backward.StageAffine);// Unpad the output
};
NN.Layer.Adjust = function(inLayer, inLearningRate)
{
var deltas;
var vector;
var scalar;
var i, j;
for(i=0; i<inLayer.Forward.StageInput.length; i++)
{
deltas = M.Outer(inLayer.Forward.StageInput[i], inLayer.Backward.StageDerivative[i]);
deltas = M.Scale(deltas, inLearningRate);
inLayer.Forward.Matrix = M.Subtract(inLayer.Forward.Matrix, deltas);
}
};
NN.Layer.Stochastic = function(inLayer, inTrainingSet, inIterations)
{
/* this method is ONLY for testing individual layers, and does not translate to network-level training */
var i, j;
var current;
var error;
for(i=0; i<inIterations; i++)
{
NN.TrainingSet.Randomize(inTrainingSet);
for(j=0; j<inTrainingSet.Order.length; j++)
{
current = inTrainingSet.Order[j];
NN.Layer.Forward(inLayer, [inTrainingSet.Input[current]]);
error = M.Subtract(inLayer.Forward.StageSigmoid, [inTrainingSet.Output[current]]);
NN.Layer.Backward(inLayer, error);
NN.Layer.Adjust(inLayer, 0.1);
}
}
};
NN.Network = {};
NN.Network.Instances = [];
NN.Network.Create = function()
{
var obj = {};
var i;
obj.Layers = [];
obj.LearningRate = 0.8;
obj.Error = [];
for(i=0; i<arguments.length-1; i++)
{
obj.Layers.push(NN.Layer.Create(arguments[i], arguments[i+1]));
}
NN.Network.Instances.push(obj);
return obj;
};
NN.Network.Observe = function(inNetwork, inBatch)
{
var input = M.Clone(inBatch);
var i;
for(i=0; i<inNetwork.Layers.length; i++)
{
input = NN.Layer.Forward(inNetwork.Layers[i], input);
}
return inNetwork.Layers[inNetwork.Layers.length-1].Forward.StageSigmoid;
};
NN.Network.Error = function(inNetwork, inTraining)
{
return M.Subtract(inNetwork.Layers[inNetwork.Layers.length-1].Forward.StageSigmoid, inTraining);
};
NN.Network.Learn = function(inNetwork, inError)
{
var input = inError;
var i;
for(i=inNetwork.Layers.length-1; i>=0; i--)
{
input = NN.Layer.Backward(inNetwork.Layers[i], input);
NN.Layer.Adjust(inNetwork.Layers[i], inNetwork.LearningRate);
}
};
NN.Network.Batch = function(inNetwork, inTrainingSet, inIterations)
{
var i;
for(i=0; i<inIterations; i++)
{
NN.Network.Observe(inNetwork, inTrainingSet.Input);
inNetwork.Error = NN.Network.Error(inNetwork, inTrainingSet.Output)
NN.Network.Learn(inNetwork, inNetwork.Error);
}
};
NN.Network.Stochastic = function(inNetwork, inTrainingSet, inIterations)
{
var i, j;
var current;
for(i=0; i<inIterations; i++)
{
NN.TrainingSet.Randomize(inTrainingSet);
for(j=0; j<inTrainingSet.Order.length; j++)
{
current = inTrainingSet.Order[j];
NN.Network.Observe(inNetwork, [inTrainingSet.Input[current]]);
inNetwork.Error = NN.Network.Error(inNetwork, [inTrainingSet.Output[current]]);
NN.Network.Learn(inNetwork, inNetwork.Error);
}
}
};