0
一些背景:C++單層多輸出感知器怪異行爲
我在C++中編寫了一個單層多輸出感知器類。它使用典型的WX + b判別式功能並允許用戶定義的激活功能。我已經完全測試了所有的東西,而且這一切似乎都在按照我的預期工作。我注意到我的代碼中存在一個小的邏輯錯誤,當我嘗試修復它時,網絡的性能比以前差得多。錯誤如下:
我用下面的代碼評估在每個輸出神經元的值:
output[i] =
activate_(std::inner_product(weights_[i].begin(), weights_[i].end(),
features.begin(), -1 * biases_[i]));
在這裏,我把偏置輸入作爲固定-1,但是當我申請學習規則每個偏見,我把輸入視爲+1。
// Bias can be treated as a weight with a constant feature value of 1.
biases_[i] = weight_update(1, error, learning_rate_, biases_[i]);
所以我試圖修復通過改變調用我的錯誤weight_updated與產出評價被conistent:
biases_[i] = weight_update(-1, error, learning_rate_, biases_[i]);
但這樣做的結果在精度下降20%! 過去幾天我一直在拉我的頭髮,試圖在我的代碼中發現一些其他邏輯錯誤,這可能會解釋這種奇怪的行爲,但卻是空手而歸。任何擁有更多知識的人都可以提供任何見解嗎?我已經提供了整個班級以供參考。先謝謝你。
#ifndef SINGLE_LAYER_PERCEPTRON_H
#define SINGLE_LAYER_PERCEPTRON_H
#include <cassert>
#include <functional>
#include <numeric>
#include <vector>
#include "functional.h"
#include "random.h"
namespace qp {
namespace rf {
namespace {
template <typename Feature>
double weight_update(const Feature& feature, const double error,
const double learning_rate, const double current_weight) {
return current_weight + (learning_rate * error * feature);
}
template <typename T>
using Matrix = std::vector<std::vector<T>>;
} // namespace
template <typename Feature, typename Label, typename ActivationFn>
class SingleLayerPerceptron {
public:
// For testing only.
SingleLayerPerceptron(const Matrix<double>& weights,
const std::vector<double>& biases, double learning_rate)
: weights_(weights),
biases_(biases),
n_inputs_(weights.front().size()),
n_outputs_(biases.size()),
learning_rate_(learning_rate) {}
// Initialize the layer with random weights and biases in [-1, 1].
SingleLayerPerceptron(std::size_t n_inputs, std::size_t n_outputs,
double learning_rate)
: n_inputs_(n_inputs),
n_outputs_(n_outputs),
learning_rate_(learning_rate) {
weights_.resize(n_outputs_);
std::for_each(
weights_.begin(), weights_.end(), [this](std::vector<double>& wv) {
generate_back_n(wv, n_inputs_,
std::bind(random_real_range<double>, -1, 1));
});
generate_back_n(biases_, n_outputs_,
std::bind(random_real_range<double>, -1, 1));
}
std::vector<double> predict(const std::vector<Feature>& features) const {
std::vector<double> output(n_outputs_);
for (auto i = 0ul; i < n_outputs_; ++i) {
output[i] =
activate_(std::inner_product(weights_[i].begin(), weights_[i].end(),
features.begin(), -1 * biases_[i]));
}
return output;
}
void learn(const std::vector<Feature>& features,
const std::vector<double>& true_output) {
const auto actual_output = predict(features);
for (auto i = 0ul; i < n_outputs_; ++i) {
const auto error = true_output[i] - actual_output[i];
for (auto weight = 0ul; weight < n_inputs_; ++weight) {
weights_[i][weight] = weight_update(
features[weight], error, learning_rate_, weights_[i][weight]);
}
// Bias can be treated as a weight with a constant feature value of 1.
biases_[i] = weight_update(1, error, learning_rate_, biases_[i]);
}
}
private:
Matrix<double> weights_; // n_outputs x n_inputs
std::vector<double> biases_; // 1 x n_outputs
std::size_t n_inputs_;
std::size_t n_outputs_;
ActivationFn activate_;
double learning_rate_;
};
struct StepActivation {
double operator()(const double x) const { return x > 0 ? 1 : -1; }
};
} // namespace rf
} // namespace qp
#endif /* SINGLE_LAYER_PERCEPTRON_H */