MachinaLearning

Updates

Jul 10, 2025

FlexOLMo: Privacy-Preserving LLM Collaboration

Home Blog Paper Gallery ConceptGraph Meta Concepts

Curriculum

Linear Algebra & Calculus Refresher Eigenvalues & Eigenvectors in ML Probability & Statisticscoming soon Information Theorycoming soon

The Perceptron Linear Regression Logistic Regression Loss Functions & Optimization

Machine Learning Overview

Supervised Learning

Support Vector Machines K-Nearest Neighbors Decision Treesalmost done Random Forestalmost done Naive Bayescoming soon

Unsupervised Learning

K-Means Clustering Hierarchical Clusteringcoming soon DBSCAN Clusteringcoming soon Principal Component Analysisalmost done Autoencoders Topic Modeling

Gradient Descent Variantsalmost done Learning Rate Schedulingcoming soon Weight Initializationcoming soon Batch Normalizationalmost done Genetic Algorithmscoming soon Evolutionary Strategiescoming soon Self-Learning Systemscoming soon

L1/L2 Regularization Dropout & Variants Data Augmentation Early Stopping Elastic Net Cross-Validationcoming soon

Multi-Layer Perceptrons Convolutional Neural Networks Recurrent Neural Networks LSTM & GRU ResNet & Skip Connections Mamba & State Space Modelscoming soon Vision Transformerscoming soon

Transformers & Attention Mechanisms BERT & Encoder Modelscoming soon GPT & Decoder Modelscoming soon Scaling Lawscoming soon Model Optimizationcoming soon Test Time Computecoming soon Inference Optimizationcoming soon Language Modeling Fundamentalscoming soon

Text Preprocessing & Tokenization Word Embeddings (Word2Vec, GloVe)Contextual Embeddings (ELMo, BERT)Sequence Models for NLPcoming soon Named Entity Recognitioncoming soon Sentiment Analysiscoming soon Machine Translationcoming soon Question Answering Systemscoming soon

Introduction to Generative Models Variational Autoencodersalmost done Generative Adversarial Networks Diffusion Modelscoming soon Flow-Based Modelscoming soon Autoregressive Models Prompting Techniques Chain-of-Thought Reasoning World Models

CLIP & Cross-Modal Alignmentcoming soon Stable Diffusioncoming soon Text-to-Image Generationcoming soon Image-to-Text Modelscoming soon Video Generationcoming soon Controllable Generationcoming soon

Markov Decision Processes Value Functions & Bellman Equations Q-Learning & SARSA Deep Q-Networks Policy Gradient Methods Actor-Critic & A3C Multi-Agent RLcoming soon Inverse RLcoming soon

Vector Embeddings Fundamentals Vector Databases & Search RAG Architecture Online LLM Search Knowledge Graph RAGcoming soon Advanced RAG Techniquescoming soon Hybrid Search Systemscoming soon

Agent Architectures Tool Calling & Function Callingcoming soon Multi-Agent Systemscoming soon Agent Memory & Statecoming soon Self-Improving Systemscoming soon Autonomous Learningcoming soon AI Safety & Alignmentcoming soon

Model Deploymentcoming soon Scaling Laws in Productioncoming soon Test Time Compute Optimizationcoming soon Model Monitoringcoming soon A/B Testing for MLcoming soon Edge AI & Mobile Deploymentcoming soon MLOps Best Practicescoming soon

Interactive

Interactive Learning

Resources

Benchmarks Datasets Notebooks

← Back to Notebooks

Transformer Attention Patterns

Understand self-attention mechanism with interactive visualizations