← Browse all tags

Machine learning

Blog

A neural network made with neural architecture search

Neural Architecture Search

Searching for the right neural network.

Notes

Generative modelling

Grounding

GRPO

PPO

Linear Attention

Foundation models

Mixture of Experts

Test-time compute

Reinforcement learning with verifiable rewards

Self-training

Synthetic training data

Geospatial AI

Text embeddings

In-context learning

Scaling laws

Self-supervised learning

Coding agent

LLM

Retrieval augmented generation

Notes on: Large Language Models as Optimizers by Yang, C., Wang, X., Lu, Y., Liu, H., Le, Q. V., Zhou, D., & Chen, X. (2023)

LLM Harness

Notes on: Meta-Harness: End-to-End Optimization of Model Harnesses by Lee, Y., Nair, R., Zhang, Q., Lee, K., Khattab, O., & Finn, C. (2026)

Neural network training

Algorithmic bias

Reinforcement learning

Continual learning

t-SNE

Adversarial examples

Pytorch

AI and climate change

Few-shot learning

Computer vision

Neural networks

Reservoir computing

Rademacher complexity

Bias-variance tradeoff

NLP

Notes on: One model for the learning of language by Yang, Y., & Piantadosi, S. T. (2022)

Supervised learning

Catastrophic forgetting

Learning in dynamical systems

Meta-learning

Distillation

Transfer learning

Alternative learning mechanisms

Generalization in Machine learning

The Bitter Lesson

Recurrent neural networks

Privacy-preserving machine learning

Unsupervised learning

Federated learning

Gaussian Processes

Talk: Differentiation of black-box combinatorial solvers

Data representation

Kernel Methods