Lecture 7: Deep Learning 201

In this lecture, we talk about more advanced concepts of DL, like convolutional neural networks, pooling, transfer learning, learning rate scheduling, hyper parameter tuning, etc.

Reading :

Much of the same papers as DL101 - these are very useful ...

• A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decay, Leslie N. Smith
• Bag of Tricks for Image Classification with Convolutional Neural Networks, Tong He, Zhi Zhang, Hang Zhang, Zhongyue Zhang, Junyuan Xie, Mu Li
• The 1Cycle Policy, Sylvain Gugger
• Pytorch documentation
• Resnet paper
• Efficientnet paper