Courses

Interactive courses published by the community.

Longformer: The Long-Document Transformer

A hands-on course for ML practitioners and NLP researchers covering Longformer (arXiv:2004.05150) end-to-end: why standard Transformers fail on long documents, how Longformer's three-part attention mechanism scales linearly, the LED variant for summarization, pretraining from RoBERTa, and empirical results on character-LM, QA, and summarization benchmarks.

Created Jul 10, 2026

Community

intermediate

#Uncategorized✦ Claude Sonnet 4.6

Graph Representation Learning

From lookup tables to message-passing neural networks: how graphs became differentiable, and why that changes everything for fraud detection, chemistry, and beyond.

Created Jun 5, 2026

Community

intermediate

#Computer Science✦ Claude Sonnet 4.6

Flash Attention: Fast & Memory-Efficient Transformers

A presentation-ready deep dive into Flash Attention — the IO-aware algorithm that makes Transformers fast on long sequences. Covers the exact mechanism, the math, tiling & recomputation tricks, and real NLP applications.

Updated Jul 13, 2026

Community

intermediate

#Computer Science✦ Claude Sonnet 4.6

Byte-Pair Encoding (BPE)

Master Byte-Pair Encoding (BPE) — the subword tokenization algorithm powering GPT, LLaMA, and most modern LLMs. Learn how it works step by step, why it beats word-level and character-level approaches, and how it handles rare and unknown words.

Updated Jul 15, 2026

Community

intermediate

#Engineering✦ Claude Sonnet 4.6

Residential Flexibility in the Energy Sector

Learn how homes can actively help balance the electricity grid — by shifting loads, storing energy, and joining virtual power plants — and why this matters for the clean-energy transition.

Created Aug 27, 2026

Community

intermediate

#Uncategorized✦ Claude Sonnet 4.6

Graph Representation Learning

From the limits of discrete logic to graph neural networks: learn how nodes become vectors, how message passing works, and why deeper isn't always better on graphs.

Created Jun 6, 2026

Community

intermediate

#Uncategorized✦ Claude Sonnet 4.6

Flash Attention: The IO-Aware Fix

Standard attention is fast on paper and slow in practice. Learn why modern GPUs are bandwidth-bound, how the online softmax trick enables exact tiled attention, and why recomputing beats storing.

Created Jun 10, 2026

Community

beginner

#Engineering#Faculty of Mechanical Engineering✦ GLM 5.2

How Air Conditioning Works

Understand the refrigeration cycle and the four core components that move heat out of indoor spaces. Covers heat transfer principles and how refrigerant state changes cool air.

Updated Jul 6, 2026

Community

intermediate

#Computer Science#Faculty of Computer Science✦ GLM 5.2

Learning from Tabular Data: The Tree Era

A deep dive into why tree-based models dominate tabular machine learning, from the inductive bias war between trees and neural networks through decision trees, random forests, gradient boosting, and XGBoost.

Created Jun 20, 2026

Community

intermediate

#Biology✦ GLM 5.2

Bee Breeding & Genetics Tutorial

Explore the genetics of honey bees, trait selection, and modern queen rearing techniques including instrumental insemination for systematic colony improvement.

Updated Jun 23, 2026

Community

intermediate

#Computer Science#Faculty of Computer Science✦ GLM 5.2

Information Theory for LLMs

Explore how entropy, cross-entropy loss, log-likelihood, and perplexity underpin the training and evaluation of Large Language Models. Learn the mathematical foundations that connect bits and nats to modern language model objectives.

Created Jun 24, 2026

Community

intermediate

#Computer Science✦ Claude Sonnet 4.6

Chapter 4: Software Architecture Design — Exam Ready

A 6-mark exam-focused course covering all 5 topics of Software Architecture Design: introduction, principles, architectural styles, modular design, and cohesion & coupling — structured for high-yield, time-pressed revision.

Created Aug 10, 2026