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

netowrk functions started

Browse Source
This commit is contained in:
TreetopFlyer 2021-07-29 14:51:00 -04:00
parent 1e644a70dc
commit 68aafafc0d
3 changed files with 74 additions and 43 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
index.html
View File

@ -708,13 +708,10 @@ NN.Network.Stochastic = function(inNetwork, inTrainingSet, inIterations)
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));
let logLayers = inNN => inNN.Layers.forEach(L=>console.log(L.Forward.Matrix));
logLayers(nn1);
NN.Network.Batch(nn1, {Input:input, Output:output}, 100);
logLayers(nn1);
NN.Network.Batch(nn1, {Input:input, Output:output}, 1000);
console.log(NN.Network.Observe(nn1, input));
</script>

23
nn.test.js
View File

@ -1,5 +1,5 @@
import { assert, assertEquals } from "https://deno.land/std@0.102.0/testing/asserts.ts";
import { Label, Forward, Backward } from "./nn.ts";
import { Split, Forward, Backward } from "./nn.ts";
import { default as M } from "./m.ts";
import { default as Methods } from "./m.ts";
@ -17,7 +17,7 @@ let typeB = [
];
Deno.test("check.forward", ()=>
Deno.test("check forward/backward", ()=>
{
let matrix1 = [
[-0.43662948305036675, -0.368590640707799, -0.23227179558890843],
@ -44,14 +44,25 @@ Deno.test("check.forward", ()=>
];
let layers = [matrix1, matrix2];
console.log("BEFORE", layers);
for(let i=0; i<100; i++)
let stages = [];
for(let i=0; i<1000; i++)
{
let stages = Forward(Methods.Mutate.Pad(input), layers);
stages = Forward(Methods.Mutate.Pad(input), layers);
Backward(stages, layers, output, 0.1);
}
console.log("AFTER", layers);
stages = Forward(input, layers);
console.log(stages[stages.length-1]);
});
Deno.test("NN.Split", ()=>
{
let data = [
[3, 2, 1, 0, 1],
[6, 5, 4, 1, 0]
]
let split = Split(data, [3, 4]);
console.log(split);
});

83
nn.ts
View File

@ -1,31 +1,13 @@
import { default as M, Cloud } from "./m.ts";
export type N = Array<Array<Array<number>>>
const Label = (inSet:any, inData:Cloud.M, inLabel:Cloud.V):N =>
{
if(!inSet){inSet = [[], []];}
if(inSet.length == 0){inSet.push([]);}
if(inSet.length == 1){inSet.push([]);}
inData.forEach((row:Cloud.V) =>
{
row.push(1);
inSet[0].push(row);
inSet[1].push(inLabel);
});
return inSet;
};
const Forward = (inData:Cloud.M, inLayers:N):N =>
{
let i:number;
let stages = [inData];
let stages:N = [inData];
let process = (index:number):Cloud.M => M.Batch.Sigmoid(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);
return stages;
};
@ -36,20 +18,61 @@ const Backward = (inStages:N, inLayers:N, inGoals:Cloud.M, inRate:number):N =>
for(i=inLayers.length-1; i>=0; i--)
{
let layerInput:Cloud.M = inStages[i];
let layerOutput:Cloud.M = inStages[i+1];
let errorScaled:Cloud.M = M.Batch.Multiply(errorBack, M.Batch.Derivative(layerOutput));
let errorScaled:Cloud.M = M.Batch.Multiply(errorBack, M.Batch.Derivative(inStages[i+1]));
errorBack = M.Batch.Affine(errorScaled, M.Create.Transpose(inLayers[i]));
errorScaled.forEach((inScaledError:Cloud.V, inIndex:number)=> {
const deltas = M.Batch.Scale(M.Create.Outer(layerInput[inIndex], inScaledError), inRate);
inLayers[i] = M.Batch.Subtract(inLayers[i], deltas);
errorScaled.forEach((inScaledError:Cloud.V, inIndex:number)=>
{
inLayers[i] = M.Batch.Subtract(
inLayers[i],
M.Batch.Scale(M.Create.Outer(inStages[i][inIndex], inScaledError), inRate)
);
});
}
return inLayers;
};
const Split = (inTrainingSet:Cloud.M, inHeaderLabel:Cloud.V, inHeaderKeep:Cloud.V = []):N =>
{
let data:Cloud.M = [];
let label:Cloud.M = [];
if(!inHeaderKeep.length)
{
inTrainingSet[0].forEach( (item:number, index:number)=> inHeaderLabel.includes(index) ? false : inHeaderKeep.push(index) );
}
inTrainingSet.forEach((row:Cloud.V) =>
{
data.push( [...inHeaderKeep.map((i:number)=>row[i]), 1] );
label.push( inHeaderLabel.map((i:number)=>row[i]) );
});
return [ data, label ];
};
const Build = (...inLayers:Array<number>):N =>
{
let i:number;
let output:N = [];
let rand = (inDimensions:number, inCount:number):Cloud.M => M.Create.Box( new Array(inDimensions).fill(-1), new Array(inDimensions).fill(1), inCount);
for(i=0; i<inLayers.length-1; i++)
{
output.push(rand( inLayers[i]+1, inLayers[i+1]));
}
output.push( rand( inLayers[i-1], inLayers[i]) );
return output;
};
const Label = (inData:Cloud.M, inLayers:N):Cloud.M =>
{
let stages:N = Forward(inData, inLayers);
return stages[stages.length-1];
};
const Learn = (inData:Cloud.M, inLayers:N, inLabels:Cloud.M, inIterations:number, inRate:number):Cloud.M =>
{
let stages:N = [];
for(let i=0; i<inIterations; i++)
{
stages = Forward(inData, inLayers);
Backward(stages, inLayers, inLabels, inRate);
}
return M.Batch.Subtract(stages[stages.length-1], inLabels);
};
const Error = M.Batch.Subtract;
export { Label, Forward, Backward };
export { Split, Build, Label, Learn, Error, Forward, Backward };
export type { Cloud };