lk1422 Goto Github PK

chessengine

Using Minimax scored with a NN

comporg-project

Computer Organization Group Project | RPI CS | CSCI-2500 Spring '23

csci4967

Repository for CSCI4967 Homeworks (Projects in Machine Learning and AI)

distributedtraining

An implementation of model parallel training in order to increase the total model capacity which can be trained by me alongside a few others.

frnns

Fully Reccurent Neural Network Architecture,

hiddendigittransformer

A novel transformer architecture that utilizes hidden tokens to increase model capacity.

k-arm-bandit

K-arm-bandit implemented after completing first section of fundamentals of reinforcement learning

lennygrad

Deep Learning Library Written in C++

markov-decision-processes-tictactoe

Using Markov Decision Processes in order to find optimal moves in tic tac toe.

morality-classification

Using a Transformer to classify if a scenario is moral or not.

simpleautograd

A testing ground for things which i learn as i read the deep learning book.

ultimatetictactoe