Open-source alternatives to Tensor Puzzles

This repository is a collection of machine learning theory notes and mathematical references. It serves as a structured study guide containing conceptual explanations and handwritten mathematical derivations of the foundations and core formulas used in the field. The content focuses on the mathematical derivation of algorithms, breaking down the step-by-step logic and proofs required to understand their inner workings. These academic records utilize typesetting for precise scientific notation and mathematical documentation. The materials are organized as a markdown-based study guide with a t

This project is a functional programming course and automated coding curriculum designed to teach the core principles of the paradigm through a structured sequence of exercises and modules. It serves as an interactive programming tutorial where learners solve incremental problems and validate their understanding through a programming exercise suite. The curriculum is language-agnostic, focusing on core logic and paradigms rather than a specific language. It employs an automated toolchain that transforms source code into executable binaries to verify solutions. Correctness is validated using

This project is an interactive machine learning textbook and educational resource designed to teach the mathematical foundations of artificial intelligence. It functions as a structured course and digital book that covers essential topics ranging from basic arithmetic to advanced calculus, linear algebra, and statistics. The resource utilizes a math visualization library and a collection of interactive code examples to demonstrate abstract principles through algorithmic output. It transforms theoretical study into a practical experience by combining programmable examples with visual guides.

This project is a PyTorch-based Chinese text classification framework. It provides a transformer-based pipeline designed to categorize Chinese language sequences into predefined labels using deep learning models. The implementation supports both BERT and ERNIE language models for processing and tagging complex Chinese text. These models are used to perform tasks such as sentiment analysis and general text categorization. The system utilizes transformer-based text encoding and attention-weighted sequence pooling to convert raw characters into document vectors. It employs pre-trained model fin

This project is a technical curriculum and learning path for machine learning, providing a structured sequence of mathematical foundations, core concepts, and professional workflows. It serves as a comprehensive guide and resource index that connects theoretical principles to the specific software libraries and tools used in real-world implementation. The repository functions as a project workflow blueprint, outlining the sequential steps required to solve machine learning problems from initial discovery through to final deployment. It maps theoretical mathematical principles to practical app

gpt-fast is a PyTorch transformer inference engine designed for low-latency text generation. It functions as a distributed GPU inference library, a quantized model runner, and a speculative decoding framework. The system utilizes a speculative decoding workflow where a small draft model predicts token sequences for verification by a larger model to accelerate generation. It supports quantized model execution to reduce memory footprint and implements tensor parallelism to split computations across multiple GPUs. The project includes a standardized evaluation harness to measure the accuracy an

This project is a PyTorch implementation of a research architecture designed for high-resolution representation learning. It serves as a computer vision framework focused on precise keypoint detection, human pose estimation, and semantic image segmentation. The implementation provides specialized tools for identifying anatomical landmarks on the human body and predicting facial keypoint coordinates to analyze orientation and alignment. It utilizes a system of multi-resolution parallel streams and repeated multi-scale fusion to maintain high-resolution representations throughout the network.

NYU-DLSP20 is a self-paced deep learning course repository that provides a complete educational curriculum covering supervised and unsupervised deep learning fundamentals. The course materials include lecture slides, Jupyter notebooks, and YouTube video recordings, all organized around PyTorch-based code exercises and neural network architecture tutorials. The course is structured as a sequential progression from fundamentals to advanced architectures, with each lecture building on previous material. Assignments are distributed as Jupyter notebooks that students complete and submit, ensuring

gpt-fast is a PyTorch transformer inference engine designed for text generation using a native tensor library implementation. It provides a runtime for executing large language models without the need for external C++ extensions. The project implements speculative decoding to accelerate generation by using a small draft model for token prediction and a larger model for verification. It further optimizes performance through a compiled prefill stage and a multi-GPU tensor parallelism library that shards linear layers across multiple graphics processing units. Memory efficiency is managed throu

This project is a PyTorch implementation of the EfficientDet architecture designed for real-time object detection. It provides a neural network and inference engine capable of identifying and locating multiple objects within images or video streams. The implementation includes pretrained computer vision models with optimized weights, enabling immediate inference and fine-tuning without the need for training from scratch. The project covers the full pipeline for computer vision model optimization, including custom object detection training and model weight optimization. It incorporates struct

This project is a linear algebra tutorial and educational resource focused on the mathematical foundations of machine learning. It serves as a technical guide and instructional material for understanding how matrix calculations and linear operations power predictive algorithms. The resource emphasizes the transition from basic arithmetic to the implementation of predictive models. It focuses on linear algebra visualization to demonstrate how matrix operations translate into the geometric transformations used in data science. The material covers the implementation of machine learning logic th

This project is a PyTorch implementation of the YOLOv3 object detection architecture. It functions as a real-time object detector and computer vision framework designed to identify and locate multiple objects within images using bounding boxes and class labels. The system allows for both the use of pretrained weights for immediate image analysis and the training of custom models using datasets with bounding box annotations. It provides a programmatic interface to integrate detection capabilities directly into other software applications. The framework includes tools for model evaluation to m

This project is an educational codebase and reference library that translates theoretical deep learning concepts into executable PyTorch code. It serves as a practical implementation of a deep learning textbook, providing a course-like structure of guided exercises and architectural examples for learning purposes. The repository includes a library of standard neural network architectures, including linear, convolutional, recurrent, and transformer models. It specifically implements a variety of deep learning patterns such as multilayer perceptrons, VGG networks, gated recurrent units, and lon

This project is a PyTorch-based framework and implementation suite for the supervised classification of Chinese text. It serves as a deep learning text classifier designed to automate the process of labeling and organizing Chinese language documents into predefined categories. The framework provides a collection of neural network architectures, including TextCNN, Transformer, and FastText. It allows for the selection and prototyping of different model topologies through a modular implementation, enabling the evaluation of various sequence models on specific datasets. The system covers a full

This project is an educational platform designed to teach JavaScript programming through a structured, test-driven curriculum. It provides a collection of interactive coding exercises that guide learners through language fundamentals and software development concepts. The platform distinguishes itself by requiring users to verify their understanding of language features by passing automated test suites in real time. By utilizing a server-side runtime environment, the tool executes student code against predefined assertion patterns to provide immediate feedback on correctness. The curriculum

This is a PyTorch object detection framework that implements the Single Shot MultiBox Detector for identifying and localizing multiple objects within images and video. The project provides a neural network architecture designed for single-shot object detection, which predicts bounding boxes and class labels in one pass. The implementation includes a real-time object detector capable of processing live video streams to track and label objects across sequential frames. It also features a complete computer vision training pipeline for preparing image datasets and training model weights. The fra

Kaolin is a PyTorch 3D deep learning library providing a comprehensive suite of tools for 3D geometry processing, physics simulation, data visualization, and gradient-based rendering for computer vision. The library includes a differentiable 3D renderer and a geometry processing toolkit for converting and transforming 3D representations such as meshes and point clouds. It also features a 3D physics simulation engine to calculate physical interactions and collisions between three-dimensional objects and scenes. The toolkit provides utilities for 3D data visualization, including the creation o

Neural renderer is a differentiable rendering library for PyTorch that projects three-dimensional meshes into two-dimensional images while maintaining continuous mathematical gradients for backpropagation. The framework enables gradient-based inverse rendering, allowing optimization of input parameters such as camera pose, vertex positions, and texture maps by propagating pixel-level reconstruction errors backward to the source geometry. The architecture incorporates approximate rasterisation gradients that substitute discontinuous edge derivatives with heuristic approximations to facilitate

This project is an educational implementation of a small-scale generative pre-trained transformer designed to teach the fundamentals of neural network architecture and training. It serves as a reference implementation and tutorial for constructing a text-generating neural network from scratch. The codebase demonstrates the mechanics of tokenization, self-attention, and the construction of a lightweight language model. It focuses on the step-by-step process of building a generative model to illustrate how large language models are constructed. The implementation covers transformer-based archi

This project is a PyTorch implementation of the Faster R-CNN architecture for object detection. It provides a framework for identifying multiple object classes and their corresponding bounding boxes within images using a deep learning system. The implementation includes a training pipeline for optimizing models on custom datasets and a utility for converting pretrained weights from external formats into a compatible structure for model initialization. The system covers a two-stage detection pipeline comprising a region proposal network and an ROI pooling layer. It incorporates multi-task los

This project is a machine learning study guide and technical knowledge base. It serves as a version-controlled repository of mathematical formulas and algorithmic explanations, providing instructional material and reference notes for the study of artificial intelligence. The content is structured as a markdown-based knowledge base that pairs theoretical mathematical explanations directly with code implementations. This approach demonstrates model mechanics in practice across several specialized domains, including deep learning research, probabilistic graphical modeling, and reinforcement lear

This project is a comprehensive JavaScript programming tutorial and frontend web development curriculum. It serves as a structured educational resource for learning the JavaScript language, ranging from basic syntax to advanced asynchronous patterns and modern programming techniques. The resource functions as a frontend engineering textbook and CSS layout guide, providing detailed instructional material on building responsive user interfaces. It covers the design of custom web components and the application of styles and positioning to create effective frontend interfaces. The curriculum enc

PlaidML is a deep learning compiler framework and cross-platform runtime designed to execute machine learning models on a wide variety of hardware targets. It functions as a hardware agnostic tensor engine that translates tensor models into executable code, allowing deep learning networks to run across different compute devices without requiring specific driver dependencies. The system enables the execution of models on custom or limited hardware by using JSON specifications to define device hardware. It employs a domain-specific language to describe tensor computations and provides a middle

This project is a static educational website and comprehensive curriculum focused on computer vision and deep learning. It serves as a public repository of instructional materials, lecture notes, and technical guides specifically detailing convolutional neural networks and visual recognition. The site is developed using static-site generation to host course documentation and student project directories. It provides structured academic resources that guide learners through image classification, generative modeling, and the implementation of various neural network architectures. The curriculum

Tinygrad is a deep learning framework and tensor computation engine designed for building and training neural networks. It functions as a hardware abstraction layer that manages device memory, command queues, and kernel dispatching across heterogeneous computing architectures. By utilizing a lazy-evaluation approach, the framework constructs computational graphs that defer execution until data is explicitly required, allowing it to process only the necessary operations for a given result. The project distinguishes itself through a just-in-time compilation layer that transforms abstract comput

One Small Step is an educational resource that explains core AI and large language model concepts through short, accessible articles designed to be read in under five minutes. It covers the structure and function of key LLM components like attention mechanisms and tokenization, as well as foundational machine learning mathematics such as matrix rank and overfitting. The project also serves as a guide to the GGUF file format, which packages all model parameters and metadata into a single compact binary file for cross-platform deployment without external dependencies. It explains how this forma

This project is a comprehensive study kit and resource archive for the Structure and Interpretation of Computer Programs (SICP) course. It serves as a curated learning path for studying functional programming and the fundamentals of program construction, providing a centralized directory of textbooks, tutorials, and instructional materials. A primary focus of the repository is multilingual accessibility, specifically providing Chinese translations of English lecture subtitles and transcripts. These translated resources are mirrored across multiple video hosting platforms and cloud storage pro