之前在https://blog.csdn.net/fengbingchun/article/details/124909910 介绍过深度学习中的优化算法Adadelta，这里介绍下深度学习的另一种优化算法Adam。论文名字为《ADAM: A METHOD FOR STOCHASTIC OPTIMIZATION》，论文地址：https://arxiv.org/pdf/1412.6980.pdf

    Adam(Adaptive Moment Estimation)：自适应矩估计是一种计算每个参数或权重的自适应学习率的方法，它除了像Adadelta和RMSProp一样存储exponentially decaying average of past squared gradients外，Adam还保持exponentially decaying average of past gradients，类似于动量(momentum)。如下图所示，截图来自：https://arxiv.org/pdf/1609.04747.pdf

    Adam是梯度下降优化算法的扩展，当处理涉及大量数据或大量参数时，该算法非常有效。直观地说，它是带动量的梯度下降算法和RMSProp算法的结合。

    Adam旨在加速优化过程，例如减少达到最优值所需的迭代次数，或提高优化算法的能力，例如获得更好的最终结果。

    以下是与Adadelta不同的代码片段：

    1.在原有枚举类Optimizaiton的基础上新增Adam：

enum class Optimization {
	BGD, // Batch Gradient Descent
	SGD, // Stochastic Gradient Descent
	MBGD, // Mini-batch Gradient Descent
	SGD_Momentum, // SGD with Momentum
	AdaGrad, // Adaptive Gradient
	RMSProp, // Root Mean Square Propagation
	Adadelta, // an adaptive learning rate method
	Adam // Adaptive Moment Estimation
};

    2.calculate_gradient_descent函数：

void LogisticRegression2::calculate_gradient_descent(int start, int end)
{
	switch (optim_) {
		case Optimization::Adam: {
			int len = end - start;
			std::vector<float> m(feature_length_, 0.), v(feature_length_, 0.), mhat(feature_length_, 0.), vhat(feature_length_, 0.);
			std::vector<float> z(len, 0.), dz(len, 0.);
			float beta1t = 1., beta2t = 1.;
			for (int i = start, x = 0; i < end; ++i, ++x) {
				z[x] = calculate_z(data_->samples[random_shuffle_[i]]);
				dz[x] = calculate_loss_function_derivative(calculate_activation_function(z[x]), data_->labels[random_shuffle_[i]]);

				beta1t *= beta1_;
				beta2t *= beta2_;

				for (int j = 0; j < feature_length_; ++j) {
					float dw = data_->samples[random_shuffle_[i]][j] * dz[x];
					m[j] = beta1_ * m[j] + (1. - beta1_) * dw; // formula 19
					v[j] = beta2_ * v[j] + (1. - beta2_) * (dw * dw); // formula 19

					mhat[j] = m[j] / (1. - beta1t); // formula 20
					vhat[j] = v[j] / (1. - beta2t); // formula 20

					w_[j] = w_[j] - alpha_ * mhat[j] / (std::sqrt(vhat[j]) + eps_); // formula 21
				}

				b_ -= (alpha_ * dz[x]);
			}
		}
			break;
		case Optimization::Adadelta: {
			int len = end - start;
			std::vector<float> g(feature_length_, 0.), p(feature_length_, 0.);
			std::vector<float> z(len, 0.), dz(len, 0.);
			for (int i = start, x = 0; i < end; ++i, ++x) {
				z[x] = calculate_z(data_->samples[random_shuffle_[i]]);
				dz[x] = calculate_loss_function_derivative(calculate_activation_function(z[x]), data_->labels[random_shuffle_[i]]);

				for (int j = 0; j < feature_length_; ++j) {
					float dw = data_->samples[random_shuffle_[i]][j] * dz[x];
					g[j] = mu_ * g[j] + (1. - mu_) * (dw * dw); // formula 10

					float alpha = (eps_ + std::sqrt(p[j])) / (eps_ + std::sqrt(g[j]));
					float change = alpha * dw;
					p[j] = mu_ * p[j] +  (1. - mu_) * (change * change); // formula 15

					w_[j] = w_[j] - change;
				}

				b_ -= (eps_ * dz[x]);
			}
		}
			break;
		case Optimization::RMSProp: {
			int len = end - start;
			std::vector<float> g(feature_length_, 0.);
			std::vector<float> z(len, 0), dz(len, 0);
			for (int i = start, x = 0; i < end; ++i, ++x) {
				z[x] = calculate_z(data_->samples[random_shuffle_[i]]);
				dz[x] = calculate_loss_function_derivative(calculate_activation_function(z[x]), data_->labels[random_shuffle_[i]]);

				for (int j = 0; j < feature_length_; ++j) {
					float dw = data_->samples[random_shuffle_[i]][j] * dz[x];
					g[j] = mu_ * g[j] + (1. - mu_) * (dw * dw); // formula 18
					w_[j] = w_[j] - alpha_ * dw / (std::sqrt(g[j]) + eps_);
				}

				b_ -= (alpha_ * dz[x]);
			}
		}
			break;
		case Optimization::AdaGrad: {
			int len = end - start;
			std::vector<float> g(feature_length_, 0.);
			std::vector<float> z(len, 0), dz(len, 0);
			for (int i = start, x = 0; i < end; ++i, ++x) {
				z[x] = calculate_z(data_->samples[random_shuffle_[i]]);
				dz[x] = calculate_loss_function_derivative(calculate_activation_function(z[x]), data_->labels[random_shuffle_[i]]);

				for (int j = 0; j < feature_length_; ++j) {
					float dw = data_->samples[random_shuffle_[i]][j] * dz[x];
					g[j] += dw * dw;
					w_[j] = w_[j] - alpha_ * dw / (std::sqrt(g[j]) + eps_);
				}

				b_ -= (alpha_ * dz[x]);
			}
		}
			break;
		case Optimization::SGD_Momentum: {
			int len = end - start;
			std::vector<float> change(feature_length_, 0.);
			std::vector<float> z(len, 0), dz(len, 0);
			for (int i = start, x = 0; i < end; ++i, ++x) {
				z[x] = calculate_z(data_->samples[random_shuffle_[i]]);
				dz[x] = calculate_loss_function_derivative(calculate_activation_function(z[x]), data_->labels[random_shuffle_[i]]);

				for (int j = 0; j < feature_length_; ++j) {
					float new_change = mu_ * change[j] - alpha_ * (data_->samples[random_shuffle_[i]][j] * dz[x]);
					w_[j] += new_change;
					change[j] = new_change;
				}

				b_ -= (alpha_ * dz[x]);
			}
		}
			break;
		case Optimization::SGD:
		case Optimization::MBGD: {
			int len = end - start;
			std::vector<float> z(len, 0), dz(len, 0);
			for (int i = start, x = 0; i < end; ++i, ++x) {
				z[x] = calculate_z(data_->samples[random_shuffle_[i]]);
				dz[x] = calculate_loss_function_derivative(calculate_activation_function(z[x]), data_->labels[random_shuffle_[i]]);

				for (int j = 0; j < feature_length_; ++j) {
					w_[j] = w_[j] - alpha_ * (data_->samples[random_shuffle_[i]][j] * dz[x]);
				}

				b_ -= (alpha_ * dz[x]);
			}
		}
			break;
		case Optimization::BGD:
		default: // BGD
			std::vector<float> z(m_, 0), dz(m_, 0);
			float db = 0.;
			std::vector<float> dw(feature_length_, 0.);
			for (int i = 0; i < m_; ++i) {
				z[i] = calculate_z(data_->samples[i]);
				o_[i] = calculate_activation_function(z[i]);
				dz[i] = calculate_loss_function_derivative(o_[i], data_->labels[i]);

				for (int j = 0; j < feature_length_; ++j) {
					dw[j] += data_->samples[i][j] * dz[i]; // dw(i)+=x(i)(j)*dz(i)
				}
				db += dz[i]; // db+=dz(i)
			}

			for (int j = 0; j < feature_length_; ++j) {
				dw[j] /= m_;
				w_[j] -= alpha_ * dw[j];
			}

			b_ -= alpha_*(db/m_);
	}
}

    执行结果如下图所示：测试函数为test_logistic_regression2_gradient_descent，多次执行每种配置，最终结果都相同。图像集使用MNIST，其中训练图像总共10000张，0和1各5000张，均来自于训练集；预测图像总共1800张，0和1各900张，均来自于测试集。在Adadelta中设置eps为1e-3，耗时为26秒；在Adam中设置eps为1e-8，学习率为0.001，beta1为0.8，beta2为0.888时，耗时为27秒；它们的识别率均为100%

    GitHub： https://github.com/fengbingchun/NN_Test