Anirudh Rajiv Menon's Projects
An efficient NEAT implementation on a multi-agent Pong environment
Raven Distribution Framework's Deep Learning Library
The foundation for any Machine Learning or Deep Learning Framework. Simply put, it is more like a decentralized calculator, comparable to a decentralized version of the IBM machines the were used to launch the Apollo astronauts. Apart from building ML/DL frameworks, a lot more can be done on it, such as maximizing yield on your favorite defi protocols like Compound and more!
Raven Distribution Framework's Javascript Library
Op is the fundamental unit of RDF. RavOp is our library to work with ops. You can create ops, interact with ops, and create scalars and tensors. RavOp is a crucial building block of the framework. It can be used to write various algorithms, formulas, and mathematical calculations.
Python client for federated and distributed computing
The code is a Stacked Autoencoder made using Pytorch. It takes as input ratings of movies seen by a user and predicts ratings for movies not seen by them i.e. the the blank spaces in the input vector. The following code predicts the rating within an 0.95 of the actual rating when tested.
The agent learns how to navigate a maze (defined in Gridworld.py) via an RL based value iteration algorithm. The above is an example of a Markov Decision Process. One may edit the maze to their liking by changing the rewards and obstacle coordinates.
A tic tac toe that learns by exploring/exploiting based on the epsilon greedy policy
This DDPG agent hates rocks.
A Federated Learning based architecture for training a PPO agent that learns to play Gin Rummy.
Scheduler service
Conversational seq2seq chatbot trained on cornell movie dialog corpus with glove 50 embeddings
Socket codes for various purposes like text, image and video transmission
A few lines of code using which I can hack your computer. I mean it literally :P
The code is a MATLAB code that allows a 4x4 LED Matrix to respond to the pitch of sound signals and Light Up the appropriate number of Rows,
Repo with TF 2.0 implementation of a Wavenet based architecture as well as a transformer based model
Speech Emotion Recognition using MFCCs of .wav files using LSTMs
Sentiment analysis on the twitter comment data-set of kaggle.
Project on Vision for Blind made for Code2Create Hack
Text to Image GAN on Caltech-UCSD Birds Dataset. Utilizes a transformer architecture to extract features from the text captions
A few transformer-attention based stuff for NLP related tasks
A project that takes image of German text as input and outputs the English translation
Lightweight Transformer based model for VQA
A CNN model trained to classify items into either organic category or recyclable category