resources

RNN & LSTM:

• CS231n Recurrent Neural Networks notes
• Introduction to recurrent neural networks by Jeremy Jordan
• Understanding LSTM Networks by Christopher Olah
• Were RNNs All We Needed?

CNN:

• MIT: Machine Learning 6.036, Lecture 8: Convolutional neural networks (Fall 2020) by Tamara Brodrick

Diffusion Models:

• Understanding Diffusion Models: A Unified Perspective by Calvin Luo

Gradient Descent:

• Proof that the gradient points in the direction of steepest ascent

LoRA:

• What is Low-Rank Adaptation (LoRA) explained by the inventor
• LoRA: Low-Rank Adaptation of Large Language Models - Explained visually + PyTorch code from scratch by Umar Jamil

Reinforcement Learning:

• Introduction to Reinforcement Learning by David Silver
• A (Long) Peek into Reinforcement Learning by Lilian Weng
• why-do-temporal-difference-td-methods-have-lower-variance-than-monte-carlo-met

Misc:

• What Happens When CHI Reaches30,000 Submissions in 2030? by Johannes Schöning
• Throwback Thursday: We Are Over-Indexing on Paper Acceptance by Colin Raffel

Papers:

For me, a good paper is one that is easy to read and understand, while also imparting knowledge or answering a question.

• Evaluating CLIP: Towards Characterization of Broader Capabilities and Downstream Implications
• EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
• Deep Residual Learning for Image Recognition
• Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
• Can LLMs subtract numbers?