Implementation of Attention-based Contact Planning, by Junzhe He of ETH Zürich

3D vision and medical imaging in one Python package: 73 algorithms, 43 datasets in one line, Open3D / SimpleITK / PyVista, MCP server for AI agents

Local-first research agent harness for deep learning: literature → reading → ideas → GPU experiments → papers & publication figures. DeepSeek-powered, custom OpenAI-compatible LLMs, SSH GPU orchestration.

htop for Neural Networks: A terminal monitor for PyTorch layer activations and gradients

Symmetric INT8 per-tensor and per-channel quantization engine for LLM weights and activations, with SNR and MSE reconstruction telemetry.

Spectral Graph Convolutional Network (GCN) layer with self-loop renormalization and forward propagation

Spectral Graph Convolutional Network (GCN) layer with self-loop renormalization and forward propagation

🐍 Learn every core Python concept for Machine Learning & Deep Learning in 2–3 hours. Hands-on Jupyter notebook with ML examples, practice tasks & solutions.

Multi-layer perceptron (MLP) feedforward inference with Xavier/Glorot initialization and activations

Symmetric INT8 per-tensor and per-channel quantization engine for LLM weights and activations, with SNR and MSE reconstruction telemetry.

2D spatial convolution layer forward pass with stride, padding, and max-pooling

Transformer multi-head self-attention engine with causal triangular masking and softmax normalization

2D spatial convolution layer forward pass with stride, padding, and max-pooling

LayerNorm and Root Mean Square Normalization (RMSNorm) with affine transformation parameters

Multi-layer perceptron (MLP) feedforward inference with Xavier/Glorot initialization and activations

Reverse-mode automatic differentiation engine with DAG tape and chain rule backpropagation

Reverse-mode automatic differentiation engine with DAG tape and chain rule backpropagation

Free multiple-choice quiz on AI and machine learning, from the basics to research topics. Every option explains why it's right or wrong. English and Spanish.

LayerNorm and Root Mean Square Normalization (RMSNorm) with affine transformation parameters

Transformer multi-head self-attention engine with causal triangular masking and softmax normalization

Comprehensive 81-page Persian lecture notes & mathematical foundations for Stanford's Mining of Massive Datasets (MMDS), featuring MapReduce, LSH, PageRank, Stream Mining, and Large-Scale ML. Includes full & chapter-by-chapter PDFs and an interactive web portal.

AIE640 – Artificial Intelligence Applications | Hacettepe University, Institute of Informatics | Assoc. Prof. Dr. Hakan Emekci. Hands-on graduate course on Large Language Models (LLMs): transformers, prompt engineering, RAG, fine-tuning & multimodal AI.

AssetMind is a digital memory and lifecycle system for physical office assets — not just an inventory tracker. Every asset at the fictional software house Nexora Technologies (desktops, laptops, chairs, monitors, and more) gets a permanent digital identity that remembers everything that ever happens to it: assignment, maintenance.

研图 Figure Atlas：论文模型图图元库——786 个可直接放进模型结构图的元素：248 个等轴测原创图元、88 个计算机视觉图元（CC0），450 个开源 3D 物件与装饰（MIT / CC0）；另附 289 张论文原图与 2.8 万开源科研图标。 Drop-in elements for deep-learning figures.

Implementation of OTRetarget: Joint Robot and Object Motion Retargeting via Optimal Transport

Forma: a desktop app for 3D deep-learning microscopy analysis on Mac and Windows

Handwrite your way from Python loops to CUDA kernels — a from-scratch LLM roadmap. 50+ runnable scripts, numpy-only start, no datasets required.

Learning repo and future reference, following Build a Large Language Model (From Scratch) by Sebastian Raschka.

Provider-independent TypeScript text/image classification; experimental localization, segmentation and cutouts. Caller-owned models. MIT.

GPT-style transformer written from scratch in PyTorch