Deep-Learning
Einops - Part 1
Introduction to einops - readable tensor operations with rearrange, reduce, and repeat replacing cryptic transposes.
Einops - Part 2: Deep Learning Architectures
Building ConvNets and Multi-Head Attention with einops - comparing traditional PyTorch vs einops implementations.
Environment & Distribution Shift
Notes on covariate shift, label shift, and concept shift - how to detect and correct distribution changes.
Loss Functions
Cross entropy loss explained with NumPy implementation for multiclass classification tasks.
Notes
Practical tips on LR schedulers, optimizers, and training tricks for deep learning models.
Tensorflow Tutorial
Hands-on TensorFlow v1.0 tutorial - variables, sessions, training algorithms, and building a neural network.
🧑🏻💻 DL Interviews
DL interview prep - maximum entropy, data augmentation, overfitting, and probability of success problems.