Friday, April 21, 2017

DL 101

1. A friendly intro to neural nets by Karpathy (Link)
2. Intro to image classification  - Nearest Neighbour classifier, Linear classifier
3. A concept-heavy deep dive into loss functions and gradient descent (Link)
4. A concept-heavy intro to Backprop and Activation functions (Link)
5. A concept-heavy intro to Neural network architecture (Link)
6. A concept-heavy intro to 'Convolutional' neural network architecture: Link1, Link2, Tranfer Learning
7. Practical advice on data-preprocessing, Regularization, Loss function intuition, batch normalization (Link)
8. Practical advice on parameter tuning, learning rates, model ensembling. (Link)
9. Implement your own neural network from scratch (Link)
10. Concept-heavy RNN by Karpathy (Link)


Path I intend to follow, before setting out to do anything: 1, 2, 3, 4, ... 10

After DL101:

DL102: Part 2 of the FastAI course
DL103: Generative Adversarial networks (Link)
DL104: + Karpathy post on RL + OpenAI Gym