Category

Downloadable cheatsheets and refreshers that condense core CS229 concepts—supervised/unsupervised learning, deep learning, math refreshers, and training tips—available as PDFs in multiple languages and hosted alongside a companion website.

ML for Beginners is a free, open-source curriculum developed by Microsoft, spanning 12 weeks with 26 lessons and 52 quizzes, focusing on classic machine learning using primarily Scikit-learn, avoiding deep learning. It uses a project-based approach with global cultural themes to explore topics like regression, classification, clustering, NLP, and time series forecasting.

A free 21-lesson course by Microsoft Cloud Advocates teaching beginners the fundamentals of building Generative AI applications. It covers concepts like Generative AI and LLMs, prompt engineering, chat apps, image generation, security, and more, with Python and TypeScript code samples supporting Azure OpenAI, OpenAI API, and open-source models. Features multi-language support, video intros, extra resources, and a Discord community.

A living, open-source textbook and curriculum for ML systems engineering — includes the textbook source, TinyTorch reference framework, hands-on labs and hardware kits, plus instructor materials for teaching training, deployment, and system-level trade-offs.

tiny-gpu is a minimal GPU implementation in Verilog designed for learning how GPUs and general-purpose accelerators work at the hardware level. It provides a compact, documented architecture and ISA, working example kernels (matrix add/mul), and full simulation support with execution traces, focused on teaching architecture, parallelization, and memory behavior.

A GitHub repository of learning notes and code dedicated to ML + SYS (machine learning systems). It collects tutorials, code walkthroughs and engineering notes on RLHF, distributed training (FSDP, Megatron), inference and scheduling (SGLang, vllm), quantization, CUDA/GPU optimization, system design, and practical engineering.

Hands-on, phase-based curriculum for building end-to-end AI systems from first principles — implement algorithms, run tests, and ship reusable artifacts (prompts, skills, agents, MCP servers) across Python, TypeScript, Rust, and Julia under an MIT license.

This post explores why physical systems’ “complexity” rises, peaks, then falls over time, unlike entropy, which always increases. Using Kolmogorov complexity and the notion of “sophistication,” the author proposes a formal way to capture this pattern, introducing the idea of “complextropy” — a complexity measure that’s low in both highly ordered and fully random states but peaks during intermediate, evolving phases. He suggests using computational resource bounds to make the measure meaningful and proposes both theoretical and empirical (e.g., using file compression) approaches to test this idea, acknowledging it as an open problem.

Stanford’s 10-week CS231n dives from first principles to state-of-the-art vision research, starting with image-classification basics, loss functions and optimization, then building from fully-connected nets to modern CNNs, residual and vision-transformer architectures. Lectures span training tricks, regularization, visualization, transfer learning, detection, segmentation, video, 3-D and generative models. Three hands-on PyTorch assignments guide students from k-NN/SVM through deep CNNs and network visualization, and a capstone project lets teams train large-scale models on a vision task of their choice, graduating with the skills to design, debug and deploy real-world deep-learning pipelines.

This tutorial explores the surprising capabilities of Recurrent Neural Networks (RNNs), particularly in generating coherent text character by character. It delves into how RNNs, especially when implemented with Long Short-Term Memory (LSTM) units, can learn complex patterns and structures in data, enabling them to produce outputs that mimic the style and syntax of the training material. The discussion includes the architecture of RNNs, their ability to handle sequences of varying lengths, and the challenges associated with training them, such as the vanishing gradient problem. Through various examples, the tutorial illustrates the potential of RNNs in tasks like language modeling and sequence prediction.

This tutorial explains how Long Short-Term Memory (LSTM) networks address the limitations of traditional Recurrent Neural Networks (RNNs), particularly their difficulty in learning long-term dependencies due to issues like vanishing gradients. LSTMs introduce a cell state that acts as a conveyor belt, allowing information to flow unchanged, and utilize gates (input, forget, and output) to regulate the addition, removal, and output of information. This architecture enables LSTMs to effectively capture and maintain long-term dependencies in sequential data