Machine Learning
Machine Learning is the general study of teaching machines from examples. There are many Types of Learning, but the typical style studied in classical machine learning textbooks is Supervised Learning, with brief explorations into Semi-supervised Learning and Unsupervised Learning.
This note will act as a central note for basic concepts in machine learning, and will show all the notes linking back to this topic.
Links to this note:
- weng2021how: How to Train Really Large Models on Many GPUs? | Lil'Log
- Probability Theory
- Artificial Intelligence
- Large Language Models
- OpenAI
- GPT3
- Reproducibility in Science
- Neural Network
- Deep Learning
- Causality
- Interview Review Material
- LSTM
- Linear Regression
- Backpropagation Through Time
- chandar2019nonsaturating: Towards Non-saturating Recurrent Units for Modelling Long-term Dependencies
- Maximum Likelihood Estimation
- Support Vector Machines
- wu2016multiplicative: On Multiplicative Integration with Recurrent Neural Networks
- Types of Learning
- sutskever2011generating: Generating text with recurrent neural networks
- Sigmoid Function
- Principle Component Analysis
- mohamed2019monte: Monte Carlo Gradient Estimation in Machine Learning
- Kernel Function
- Gradient Descent
- goudreau1994firstorder: First-order versus second-order single-layer recurrent neural networks
- Empirical Risk Minimization
- Dimensionality Reduction
- Classification
- chung2014empirical: Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- byrd2019what: What is the Effect of Importance Weighting in Deep Learning?