I'm Chris Albon, Director of Machine Learning at the Wikimedia Foundation. I wrote the [Machine Learning with Python Cookbook](https://amzn.to/3XHrpLf) and created some [machine learning flashcards](https://machinelearningflashcards.com/). My website contains [[#Articles|articles]] and [[#Technical+Notes|technical notes]] on applied artificial intelligence. ## Articles These pieces reflect my thoughts, experiences, and insights gained from my work. * 2024-01-01 - [[How I Take Notes]] ## Technical Notes I read a lot. Here are 137 [[notes]] on 60 topics in applied artificial intelligence, based on ~37 sources. Use the button at the bottom of the page to study a random topic. * ### Machine Learning * [[Training, Test, And Validation Sets]] * [[Reinforcement Learning]] * [[Four Types Of AI]] * [[Dimensionality Reduction]] * [[Feature Scaling]] * [[Bias-Variance Tradeoff]] * [[Clustering]] * [[Regression]] * [[Classification]] * [[Overfitting And Underfitting]] * [[Capacity]] * #### Pre-processing data * [[Mutual Information]] * [[One-hot encoding]] * [[Target encoding]] * #### Neural Networks * [[Stochastic Gradient Descent]] * [[Deep Double Descent]] * [[Internal Covarate Shift]] * [[Learning Rate]] * [[FLOPS]] * [[Vanishing Gradient]] * [[Weight Decay Regularization]] * [[Gradient Descent]] * [[Positional Encoding]] * [[Bias]] * [[Motivation]] * [[Autoencoders]] * [[How Deep Neural Networks Learn]] * [[Batching]] * ##### Layers * [[Skip Connections]] * [[Batch Normalization Layer]] * [[Convolutional Layers]] * [[Embedding Layers]] * [[Max Pooling Layer]] * [[Fully Connected Layers]] * [[Dropout Layer]] * ##### Activation Functions * [[Gaussian Error Linear Unit (GELU)]] * [[Hyperbolic Tangent (Tanh)]] * [[Rectified Linear Unit (ReLU)]] * [[Leaky ReLU]] * [[What is an activation?]] * [[Motivation]] * ### Large Language Models * [[Fine-Tuning Vs. Pretraining]] * [[History]] * [[Hallucinations]] * [[Model Collapse]] * #### Prompts * [[Prompt Hierarchy]] * [[Prompt Attacks]] * ### Python * [[Type Hinting]] * #### Object Oriented Programming * [[Example Of @property]] * [[Abstract Base Classes And Methods]] * [[Difference Between Class And Instance Variables]] * ##### Three Tenets Of OOP * [[Polymorphism]] * [[Inheritance]] * [[Encapsulation]] * [[Abstraction]] * ### MLOps * [[Data Warehouse Vs. Data Lake]] * [[Declarative ML Systems]] * [[Data Model]] * ### Mathematics * #### Linear Algebra * [[Broadcasting]] * [[Vector Operations]] * [[Tensors]] * #### Probability * [[Sample Space]] * [[Central Limit Theorem]] * [[Random Variable]] * [[Law Of Large Numbers]] * ### Computer Science * [[Handling Numbers]] * ### Data * [[Extracting Training Data From Models]] * [[MNIST Dataset]] * ### Software Engineering * [[Clean Code]] * [[Concurrency]]