Deep Learning I - NN, TF, PyTorch, Data Augmentation

Deep Learning I

Deep learning fundamentals — how neural networks are built and trained, from layers and activation functions through forward propagation and backpropagation. Covers the major architectures (MLP, CNN, RNN, LSTM, GAN, GNN), the PyTorch and TensorFlow landscape, data augmentation, and a hands-on PyTorch implementation.

→ Slide Deck: Deep Learning I

Notebook link

→ https://github.com/SnowArchitect60/deep-learning-i

Some useful links

→ https://pytorch.org/

→ https://tensorflow.org/

→ https://softwaremill.com/ml-engineer-comparison-of-pytorch-tensorflow-jax-and-flax/

→ https://arxiv.org/pdf/2508.04035

→ https://docs.pytorch.org/docs/2.14/nn.html

→ https://docs.pytorch.org/docs/2.14/nn.functional.html