shin/NeuralNetworkLib
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

refactored propagation

Browse Source
This commit is contained in:
Shin
2016-10-31 15:03:27 +01:00
parent 8749b3eb03
commit 77b38dec65
19 changed files with 285 additions and 548 deletions
Download Patch File Download Diff File Expand all files Collapse all files

83
include/NeuralNetwork/Learning/BackPropagation.h
View File

@@ -1,10 +1,6 @@
#pragma once
#include <vector>
#include <cmath>
#include <NeuralNetwork/FeedForward/Network.h>
#include "CorrectionFunction/Linear.h"
#include "BatchPropagation.h"
namespace NeuralNetwork {
namespace Learning {
@@ -12,23 +8,17 @@ namespace Learning {
/** @class BackPropagation
* @brief
*/
class BackPropagation {
class BackPropagation : public BatchPropagation {
public:
inline BackPropagation(FeedForward::Network &feedForwardNetwork, CorrectionFunction::CorrectionFunction *correction = new CorrectionFunction::Linear()):
network(feedForwardNetwork), correctionFunction(correction),learningCoefficient(0.4), slopes() {
BackPropagation(FeedForward::Network &feedForwardNetwork, std::shared_ptr<CorrectionFunction::CorrectionFunction> correction = std::make_shared<CorrectionFunction::Linear>()):
BatchPropagation(feedForwardNetwork,correction), learningCoefficient(0.4) {
resize();
}
virtual ~BackPropagation() {
delete correctionFunction;
}
BackPropagation(const BackPropagation&)=delete;
BackPropagation& operator=(const NeuralNetwork::Learning::BackPropagation&) = delete;
void teach(const std::vector<float> &input, const std::vector<float> &output);
inline virtual void setLearningCoefficient (const float& coefficient) { learningCoefficient=coefficient; }
float getMomentumWeight() const {
@@ -48,75 +38,22 @@ namespace Learning {
weightDecay=wd;
}
std::size_t getBatchSize() const {
return batchSize;
}
void setBatchSize(std::size_t size) {
batchSize = size;
}
protected:
virtual inline void resize() {
if(slopes.size()!=network.size())
slopes.resize(network.size());
for(std::size_t i=0; i < network.size(); i++) {
if(slopes[i].size()!=network[i].size())
slopes[i].resize(network[i].size());
}
if(deltas.size() != network.size())
deltas.resize(network.size());
bool resized = false;
for(std::size_t i = 0; i < network.size(); i++) {
if(deltas[i].size() != network[i].size()) {
deltas[i].resize(network[i].size());
resized = true;
if(i > 0) {
for(std::size_t j = 0; j < deltas[i].size(); j++) {
deltas[i][j].resize(network[i - 1].size());
std::fill(deltas[i][j].begin(),deltas[i][j].end(),0.0);
}
}
}
}
if(momentumWeight > 0.0 && (resized || lastDeltas.size() != deltas.size())) {
lastDeltas = deltas;
virtual inline void resize() override {
BatchPropagation::resize();
if(momentumWeight > 0.0) {
_lastDeltas = _gradients;
}
}
virtual void computeDeltas(const std::vector<float> &input);
void updateWeights();
virtual void computeSlopes(const std::vector<float> &expectation);
virtual void endBatch() {
}
FeedForward::Network &network;
CorrectionFunction::CorrectionFunction *correctionFunction;
virtual void updateWeightsAndEndBatch() override;
float learningCoefficient;
float momentumWeight = 0.0;
float weightDecay = 0.0;
std::size_t batchSize = 1;
std::size_t currentBatchSize = 0;
std::vector<std::vector<float>> slopes;
std::vector<std::vector<std::vector<float>>> deltas = {};
std::vector<std::vector<std::vector<float>>> lastDeltas = {};
std::vector<std::vector<std::vector<float>>> _lastDeltas = {};
};
}