Pytorch Training Material

Linear Regression
Deep Neural Networks
Convolutional Neural Networks
- Cifar10 example
Recurrent Neural Networks
- RNNs
- LSTMs
- Transformers & Bert
Reinforcement Learning; refer to https://github.com/xeliot/rl_gym
- Deep Q Learning
- Policy Gradient
- Advantage Actor Critic
- Deep deterministic policy gradients

by Dave Ho

Name		Name	Last commit message	Last commit date
Latest commit History 15 Commits
.ipynb_checkpoints		.ipynb_checkpoints
screenshots		screenshots
slide_deck		slide_deck
.gitignore		.gitignore
README.md		README.md
cifar10.ipynb		cifar10.ipynb
cifar10_SOLVED.ipynb		cifar10_SOLVED.ipynb
cnn.ipynb		cnn.ipynb
fizzbuzz.ipynb		fizzbuzz.ipynb
fizzbuzz_SOLVED.ipynb		fizzbuzz_SOLVED.ipynb
linear_regression.ipynb		linear_regression.ipynb
linear_regression_SOLVED.ipynb		linear_regression_SOLVED.ipynb
neural_networks.ipynb		neural_networks.ipynb
rnn.ipynb		rnn.ipynb
sin_time_series.ipynb		sin_time_series.ipynb
sin_time_series_SOLVED.ipynb		sin_time_series_SOLVED.ipynb
tensor_operations.ipynb		tensor_operations.ipynb

xeliot/pytorch_training