On the Variance of the Adaptive Learning Rate and Beyond
Educational deep learning library in plain Numpy.
CS F425 Deep Learning course at BITS Pilani (Goa Campus)
ADAS is short for Adaptive Step Size, it's an optimizer that unlike othe...
Google Street View House Number(SVHN) Dataset, and classifying them thro...
Reproducing the paper "PADAM: Closing The Generalization Gap of Adaptive...
PyTorch/Tensorflow solutions for Stanford's CS231n: "CNNs for Visual Rec...
Implemented Adam optimizer in python
Toy implementations of some popular ML optimizers using Python/JAX
This library provides a set of basic functions for different type of dee...
Lookahead optimizer ("Lookahead Optimizer: k steps forward, 1 step back"...