Course Materials

Book

A part of this course is based on “Deep Learning with Python” by Francois Chollet. Subsequent sources will be added to the following section.

Additional Course Materials

• Andrew Ng - deeplearning.ai and Coursera course
• Deep learning course at Udacity
• Deep Learning textbook - Ian Goodfellow, Yoshua Bengio and Aaron Courville
• A review of optimization techniques for DL
• A review of Transfer learning

Tutorials

1. Google Colab tutorial - An introduction to Google Colab, How to upload files? How to connect to Google Drive and resume training.
2. Fully connected networks for predicting house prices, sentiment analysis, text classification, and image classification
3. MNIST classification using ConvNets
4. ConvNet for image classification, data augmentation.
5. ConvNet pre-training
6. ConvNet visualization: activations, filters, and heatmaps
7. IMDB sentiment analysis using MLP with pre-trained embeddings, SimpleRNN, and LSTM
8. Temperature forecasting problem using GRUs
9. Text processing using 1D ConvNets
10. Keras functional API
11. Text generation with LSTMs
12. DeepDream
13. MNIST with VAE
14. GAN for frog generation
15. TensorFlow 2 Tutorial (Official Page) - A set of tutorials, prepared by IUST, on TensorFlow 2 (basically a mini-course): It covers most of the required materials to start coding in TensorFlow, such as defining the computation, designing the model, working the input pipeline, and many more.