2018年3月3日
CS231n笔记 Lecture 9, CNN Architectures
摘要： Review: LeNet-5 1998 by LeCun, one conv layer. Case Study: AlexNet [Krizhevsky et al. 2012] It uses a lot of mordern techniques where is still limited 阅读全文
posted @ 2018-03-03 21:28 ichneumon 阅读(530) 评论(0) 推荐(0) 编辑
CS231n笔记 Lecture 8, Deep Learning Software
摘要： CPU and GPU If you aren’t careful, training can bottleneck on reading data and transferring to GPU! Solutions: - Read all data into RAM - Use SSD inst 阅读全文
posted @ 2018-03-03 17:21 ichneumon 阅读(323) 评论(0) 推荐(0) 编辑
CS231n笔记 Lecture 7, Training Neural Networks, Part 2
摘要： Review Activation Functions. Sigmoid, tanh, ReLU(good default choice). Optimization Optimization algorithms SGD. Problems: jitering or stop at saddle 阅读全文
posted @ 2018-03-03 15:59 ichneumon 阅读(249) 评论(0) 推荐(0) 编辑