Neural Machine Translation (NMT) from Spanish to English. Architecture is Seq2Seq + Multiplicative Attention + Character-level conditional English (target) language model.

Semantic Visual Search: Given an image, retrieve semantically similar looking images.

Car Detection

Advance Machine Learning (CSL 712) Course Lab Assignments

Python codes for Cryptopals Crypto Challenges

Basic Capsule Network models.

My solutions for Assignments of CS231n: Convolutional Neural Networks for Visual Recognition

Implemented Vanilla RNN and LSTM networks, combined these with pretrained VGG-16 on ImageNet to build image captioning models on Microsoft COCO dataset. Explored use of image gradients for generati…

Implemented fully-connected DNN of arbitrary depth with Batch Norm and Dropout, three-layer ConvNet with Spatial Batch Norm in NumPy. The update rules used for training are SGD, SGD+Momentum, RMSPr…

Reinforcement Learning in Pacman

Python code for Gibbs Sampler.

Image Classification pipeline for CIFAR-10 dataset based on K-NN, Svm, Softmax and 2-layer Neural Net Classifiers

Implemented minimax and expectimax search and designed a evaluation function for Pacman State.

Experimented with different AI search techniques like BFS, DFS, A* search in a Pacman environment.

Support Vector Machines Implementation from scratch using simplified SMO algorithm.

SimpleRISC Debugger

SimpleRISC functional simulator