deepnet

MNIST classification using Convolutional NeuralNetwork. Various techniques such as data augmentation, dropout, batchnormalization, etc are implemented.

CS F425 Deep Learning course at BITS Pilani (Goa Campus)

[WACV 2022] "Sandwich Batch Normalization: A Drop-In Replacement for Feature Distribution Heterogeneity" by Xinyu Gong, Wuyang Chen, Tianlong Chen and Zhangyang Wang

Win probability predictions for League of Legends matches using neural networks

Toy implementations of some popular ML optimizers using Python/JAX

Interesting python codes to tackle simple machine/deep learning tasks

Unofficial Keras implementation of the paper Attentive Normalization.

A compressed adaptive optimizer for training large-scale deep learning models using PyTorch

Modified XGBoost implementation from scratch with Numpy using Adam and RSMProp optimizers.

The project aimed to implement Deep NN / RNN based solution in order to develop flexible methods that are able to adaptively fillin, backfill, and predict time-series using a large number of heterogeneous training datasets.