Ali Kuwajerwala's Projects
Ali's personal website repo
A beautiful, simple, clean, and responsive Jekyll theme for academics
just seeing what happens when you run a C program
Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch
Teaching robots to respond to open-vocab queries with CLIP and NeRF-like neural fields
Notes, programming assignments and quizzes from all courses within the Coursera Deep Learning specialization offered by deeplearning.ai: (i) Neural Networks and Deep Learning; (ii) Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization; (iii) Structuring Machine Learning Projects; (iv) Convolutional Neural Networks; (v) Sequence Models
Data Exploration with Python
my dotfiles
Library for Model Based RL
Ali's copy of dust3r
A notebook exploring how Neural Networks construct their understanding of images using DeepDream and Tensorflow.
gradslam without chamferdist, forked to be used as a requirement for ConceptGraphs
Self-driving car simulator for the Duckietown universe
My first Github Project
jiant is an nlp toolkit
A simulation of the Key Reinstallation Attack, allowing users to understand the exploit breaking WPA2 by forcing nonce reuse.
Lucid library adapted for PyTorch
My project for the Montreal AI Symposium 2024. I investigate 4 puzzling properties of NN loss landscapes by computing lots and lots of Hessian Eigenspectra of a small resnet on CIFAR10
Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow
The Mojo Programming Language
[CVPR'24] Gaussian Splatting SLAM
A puzzle game for Android based on graph theory problems, that includes a fully featured 'make mode' allowing users to create their own levels.
A collaboration friendly studio for NeRFs
just messing around
YAMT is a minimal Jekyll theme focused on simplicity and ease-of-use.