Henry Ndubuaku

maths-cs-ai-compendium. Become a cracked AI/ML researcher/engineer with this unconventional textbook covering maths, computing, and ML with intuition.

nanodl. JAX library for training sub-4B foundation models for edge

cuda-tutorials. Comprehensive CUDA tutorials for Maths & ML with examples

super-lazy-autograd. Hand-derived memory-efficient VJPs for tuning LLMs on laptops.

halo. A Library That Uses Quantized Diffusion Model With Clustered Weights For Efficiently Generating More Image Datasets On-Device.

tango. Decentralised ML engine to train on tiny edge devices.

pete. Parameter-efficient transformer embeddings replace learned embeddings with hardware-aware polynomial expansions of token IDs.

vector. Programming language for ML on XLA with JAX-level speed; compiles for CPU, TPUs/Nvidia GPUs, AMD GPUs, Apple GPUs, etc.

vision-architectures. Comparative Analysis of SOTA Vision Architectures; VGG, GoogleNet, ResNet & Vision Transformers.

fbnet. Modelling The Brain's Response To Natural Scenes In The Bottleneck Space.

federated-learning-on-phones. Distributed machine learning on mobile phones

HenryNdubuaku. CSS

closegan. Conditional Latent-Optimised Sequence Generative Adversarial Network For Creative Text Generation.

bayesian-cognitive-robot. A Bayesian Belief Network on ROS for robot facial expression.

autonomous-vehicle-fgpa. Progressive Language Enhancement Algorithm Using Masking Filling Transformers In A Markov Chain.

gaussian-moe. A Study of Gaussian Mixture Model In Three-Dimensional Phoneme Clustering.