neural-network

A group of notebooks and other files which can help you learn AI from scratch.

Concise and beautiful algorithms written in Julia

A primitive library for neural network

Owl - OCaml Scientific Computing @ https://ocaml.xyz

Arm NN ML Software.

Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)

[ECCV`24&ICLR`25] CityGaussian Series for High-quality Large-Scale Scene Reconstruction with Gaussians

Pocket-Sized Multimodal AI for content understanding and generation across multilingual texts, images, and 🔜 video, up to 5x faster than OpenAI CLIP and LLaVA 🖼️ & 🖋️

Keras implementation of "One pixel attack for fooling deep neural networks" using differential evolution on Cifar10 and ImageNet

Physics-Informed Neural Networks (PINN) Solvers of (Partial) Differential Equations for Scientific Machine Learning (SciML) accelerated simulation

Diagrams for visualizing neural network architecture

A project for processing neural networks and rendering to gain insights on the architecture and parameters of a model through a decluttered representation.

Research on Tabular Deep Learning: Papers & Packages

:computer: Learn to make machines learn so that you don't have to struggle to program them; The ultimate list

Audio processing by using pytorch 1D convolution network

Samples and Tools for Windows ML.

torchview: visualize pytorch models

Dataflow compiler for QNN inference on FPGAs

Upscale an image by a factor of 4, while generating photo-realistic details.

Pure PyTorch Implementation of NVIDIA paper on Instant Training of Neural Graphics primitives: https://nvlabs.github.io/instant-ngp/

Active learning for systematic reviews

Python机器学习算法技术博客，有原创干货！有code实践！ 【更多内容敬请关注公众号 "算法进阶"】

Machine Learning Open Source University

A-Paper-A-Week

A real-time method that estimates the 3D human pose directly in the popular Bio Vision Hierarchy (BVH) format, given estimations of the 2D body joints originating from monocular color images. Our contributions include: (a) A novel and compact 2D pose NSRM representation. (b) A human body orientation classifier and an ensemble of orientation-tuned

Pure Rust implementation of a minimal Generative Pretrained Transformer

SchNetPack - Deep Neural Networks for Atomistic Systems

BladeDISC is an end-to-end DynamIc Shape Compiler project for machine learning workloads.

Data compression in TensorFlow

The repository contains script and notebook related to Statistics, Machine learning, Neural network, Deep learning, NLP, Numerical methods, and Automation.