摘要: # Batch gradient descent(批量梯度下降) for i in range(nb_epochs): params_grad = evaluate_gradient(loss_function, data, params) params = params - learning_rate * params_grad # Stochastic gradien... 阅读全文
posted @ 2016-04-05 04:02 罗兵 阅读(966) 评论(0) 推荐(0) 编辑