ConceptAI & ML
Probability distribution
A function that takes a random variable and gives the probability for each of the possible values in its domain.
Know first
Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.
Opens up
Concepts that name this one as a prerequisite.
Lecturers
2Each in their own terms, from the easiest level.
Pieter Abbeel
A probability distribution associates a probability with each value of a random variable.
Lectures that assume it
254The first 12 are shown.
- Introduction to Information Theory (University of Cambridge, Lecture 1)
- Large Deviations
- Building makemore Part 3: Activations, Gradients, Kaiming Init & BatchNorm
- The Wave Function, Born's Rule & Fourier Wave Packets
- Model-Free Control — ε-Greedy SARSA & Off-Policy Q-Learning
- Speculations on Test-Time Scaling for Large Language Models (o1)
- Mixed Strategies in Theory and Tennis
- Generative Modeling by Estimating Gradients of the Data Distribution
- Law of Large Numbers and Central Limit Theorem (Statistics 110, Lecture 29)
- Expectation II
- Mixed States and Density Matrices
- Perfect Bayesian Equilibrium
Connections
264The lectures that define it or assume it, and the concepts next to it.
Concepts7
Show 1 moreShow fewer
Lectures257
- Harvard CS50’s Artificial Intelligence with Python – Full University Course
- Probability
- Search with Other Agents: Expectimax, Utilities
- Introduction to Information Theory (University of Cambridge, Lecture 1)
- Large Deviations
- Building makemore Part 3: Activations, Gradients, Kaiming Init & BatchNorm
Show 251 moreShow fewer
- The Wave Function, Born's Rule & Fourier Wave Packets
- Model-Free Control — ε-Greedy SARSA & Off-Policy Q-Learning
- Speculations on Test-Time Scaling for Large Language Models (o1)
- Mixed Strategies in Theory and Tennis
- Generative Modeling by Estimating Gradients of the Data Distribution
- Law of Large Numbers and Central Limit Theorem (Statistics 110, Lecture 29)
- Expectation II
- Mixed States and Density Matrices
- Perfect Bayesian Equilibrium
- Building makemore Part 2: Multi-Layer Perceptron Language Models (Bengio et al. 2003)
- Markov Processes, Reward Processes & Bellman Equations
- Expectation I
- Data Compression and Shannon’s Noiseless Coding Theorem
- Random Restrictions and AC0 Circuit Lower Bounds
- Unitary Time Evolution, Stationary States & Infinite Square Well
- Is Learning Feasible?
- Gambler's Ruin and Random Variables
- Random Variables and Their Distributions
- Options III & Risk and Return I
- Statistical Estimation
- The Linear Model II
- Adversarial Examples and Adversarial Training
- Racial Disparities in Economic Opportunity
- Introduction to Individual Decision-Making
- Auctions
- Huffman Coding
- Convex Optimization II: Stochastic Programming and Cutting-Plane Methods
- Conditional Expectation Given a Random Variable (Statistics 110, Lecture 27)
- Markov Chains Continued Further (Statistics 110, Lecture 33)
- Pseudorandom Generators
- Spectral Graph Theory III: Eigenvalues of the Laplacian
- Introduction to Cryptography: Symmetric Key Encryption and the One-Time Pad
- Deep Reinforcement Learning
- Exploration of advanced topics in deep reinforcement learning
- RL Theory
- Variational Inference, Part 2
- Bond Energies, the Boltzmann Factor, and Entropy
- The Switching Lemma: PRST Version
- Poverty Traps: Graduation Programs
- Deep Dive into Large Language Models: Pretraining to RLHF
- Stochastic Processes I
- The Poisson Distribution
- Reinforcement Learning Part 1/2
- Bayes' Nets: Representation
- Bayes' Nets: Sampling
- Hidden Markov Models
- Me and My Markov Blanket
- Complexity and Computability with Closed Timelike Curves
- Markov Chains
- Expectation Values, Momentum Operator & Heisenberg Uncertainty
- Error and Noise
- Upward Mobility, Innovation, and Economic Growth
- Imitation Learning II: Covariate Shift & Dataset Aggregation (DAgger)
- Exploration and Exploitation
- Three Learning Principles
- Discrete vs. Continuous, the Uniform
- Decision Networks and Value of Perfect Information (VPI)
- Commodity Models
- Universal Aspects of Period Doubling
- Local Node Differential Privacy
- Probability Densities and BLR Linearity Testing
- Noise Stability and Arrow's Theorem
- Level-1 Inequality and the 2/π Theorem
- Dominance
- Surrogate Modeling and Bayesian Optimization (Part 2)
- Spectral Graph Theory: The Standard Random Walk
- Entropy
- Exploration of fundamental concepts in deep reinforcement learning
- Deep Reinforcement Learning
- Offline Reinforcement Learning II
- Inverse Reinforcement Learning, Part 2
- Sanders's Theorem (Analysis of Boolean Functions, CMU 15-859S, Lecture 22)
- Hardness Amplification
- Quantum Probability
- Spelled-Out Intro to Language Modeling: Building makemore (Bigram & Cross-Entropy)
- Convex Functions — First/Second-Order Conditions & Epigraphs
- Natural Language Processing with Deep Learning: Introduction & Word Vectors
- The unreasonable effectiveness of the convexity assumption in high dimensions
- Differential Privacy: Fundamentals to Forefront I
- Randomization: Skip Lists
- Conformal Symmetry & Anomalous Scaling in Two-Dimensional Turbulence
- From System 1 to System 2 Deep Learning
- The Generic Viewpoint Assumption; Object Recognition
- Cognitive Science Tools for Understanding LLM Behavior
- Controlling Stochastic Biophysical Processes, from Protein Folding to Evolution
- Mathematical Optimization & Why Convexity Is the Watershed
- Mechanism Design & Game-Theoretic Incentives for Collaborative Learning
- Risk and Financial Crises
- Training Versus Testing
- Quantum Entanglement II: Bell States, Density Matrices & Non-Locality
- Higher Education and Upward Mobility
- Intrinsic Value Closure and Pricing Beginnings
- Policy Gradient Foundations: Trajectory Distributions & High-Dimensional State Spaces
- Secure Computation and Low-Complexity Cryptography
- Generalized Eigenvectors, Diagonalization, and Jordan Canonical Form
- Generative Models
- Bayes' Nets: Inference (Variable Elimination)
- Random Variables
- Portfolio Theory
- Markov and Chebyshev Inequalities
- A de Sitter Effective Field Theory
- Privacy Amplification for Correlated-Noise Mechanisms via b-Min-Sep Subsampling
- Machine Text Detectors are Membership Inference Attacks
- What Humans Want: Models of Preference and Reward in Minds and Machines
- Neural Networks I: Feedforward Architectures & Backpropagation
- Frontiers of Deep Reinforcement Learning
- Generative Models: Representation Learning Meets Generative Modeling
- Generative Models: Conditional Models
- Bayesian Games
- Agreement and Alignment for Human-AI Collaborative Decision Making
- Chernoff Bounds
- Simulation-Driven Robot Learning for the Lazy Researcher
- Beta Distribution
- Spectral Graph Theory III: Mixing Time
- Information Complexity
- Learning With Errors (LWE) and Public Key Encryption
- Intuitions on Language Models and the History of Transformer Architectures
- Exploration of deep reinforcement learning, likely
- Deep Reinforcement Learning
- Offline Reinforcement Learning
- Variational Inference, Part 1 (CS 285, Lecture 18)
- Control as Inference, Part 3
- Inverse Reinforcement Learning, Part 4
- Reinforcement Learning from Human Feedback: Algorithms & Applications
- Challenges & Open Problems in Deep Reinforcement Learning
- Inference Methods for Deep Learning
- Hardness vs. Randomness I
- Hardness vs. Randomness II
- Quantum Information Theory
- Quantum "Supremacy"
- The Challenge of Valid Evaluations
- Work, Average Value, and Probability
- Loss Functions and Optimization
- The Mathematics of Causal Inference and the Logic of Science
- Objective-Driven AI: World Models that Learn, Remember, Reason, and Plan
- Sequential Decision-Making: Policy Gradients vs. Value-Based Architectures
- An Observation on Generalization and Unsupervised Compression
- Dispersion of the Gaussian and the Finite Well
- Course Conclusion and Limits of Quantum Physics
- Machine Learning: Naive Bayes
- Machine Learning: Perceptrons and Logistic Regression
- Itō Calculus
- Probably Approximately Precision and Recall Learning
- Differentially Private Table-Image Multimodal Data Generation
- Leveraging Per-Instance Privacy for Machine Unlearning
- Partial Measurements and Spooky Action at a Distance
- The Hidden Subgroup Problem
- Spectral Concentration and Learning
- LTFs and Noise Stability
- Generalization: Out-of-Distribution (OOD)
- LLM-Guided Reinforcement Learning for Mastery Learning: Large-Scale Field Evidence
- Mid-Level Vision (cont'd)
- The Shape of Knots: From DNA to Solar Flares
- Active Inference: Bridging Perception and Decision-Making
- Tyler Prize Laureate Lecture: Richard B. Alley
- Where in the World are SUSY & WIMPS?
- Technology and Invention in Finance
- Adaptive Evolution: Natural Selection
- Quantum Logic, Superposition & Classical vs. Quantum States
- Hermitian Operators, Eigenvalues & Quantum Measurement Postulates
- Probability Theory
- Imitation Learning I: Behavioral Cloning & Distributional Shift
- Identical Particles
- Risk and Return II & Portfolio Theory I
- Saddle Points Continued, Maxmin Principle
- Stochastic dynamics
- Stochastic Control
- Deep Reinforcement Learning
- Particle Filtering
- The Future of Artificial Intelligence
- Stochastic Processes II
- Actor-Critic Methods: Value Function Bootstrapping & Advantage Estimation
- Recovering Riemannian Metric Distance from Random Geometric Graphs
- Quantum Gravity and Statistical Physics
- Astrophysics and Cosmology with Black Hole Mergers
- Disturbance and Recovery Dynamics in Complex Ecological Systems
- Representation Learning: Reconstruction-Based
- Generative Models: Basics
- UG-Hardness Results from Dictator Tests
- Why Does Nature Like the Square Root of Negative One?
- Generative Control, Action Chunking, and Moravec’s Paradox
- Energy Harvesting from Anisotropic Fluctuations
- Nonequilibrium Thermodynamics of Uncertain Stochastic Processes
- Introduction to Large Deviation Theory
- Scaling, Criticality, and the Statistical Physics of Biological Networks - Class 1
- A Look Ahead
- Machine Learning: Neural Networks and Decision Trees
- Transformers in Diffusion Models for Image Generation and Beyond
- Towards a Statistical Foundation for Reinforcement Learning
- RL with Sequence Models & Language Models, Part 1 (CS 285, Lecture 21)
- Transfer Learning & Meta-Learning
- Beyond Worst-Case Analysis
- Questions for Theory in the New Age of Machine Learning
- Language Models: Prompting, Chain-of-Thought, and Instruction-Tuning
- Multiplying By A Global Phase Doesn't Make A Difference
- Quantum Walks and RG in de Sitter Space
- Statistical Physics of Generative Grammars
- Optimal Finite-Time Copying Protocols
- Work Fluctuations and Entropy Production of a Trapped Brownian Particle in an "Active-Like" Viscoelastic Bath
- Signatures of Irreversibility in Microscopic Models of Flocking
- Algorithmic Thermodynamics
- Public Finance (Part 2)
- Value At Risk (VAR) Models
- Volatility Modeling
- Imitation Learning III: Inverse RL & Generative Adversarial Imitation Learning (GAIL)
- MGFs Continued
- Output feedback
- The Economic Geography of American Slavery
- Fluctuation-Dissipation Relations, Langevin Dynamics & Fokker-Planck Equations
- Stable Estimators for Fast Private Statistics
- Scientific Machine Learning for Electromagnetic Field Computations
- Foundations, Privacy & Generalization Challenges in Modern Machine Learning
- Zero-Sum Games
- HSE Kolmogorov Complexity, Lecture 1: Computability and Solomonoff Induction
- Geometric Decomposition of Entropy Production Rate: Wisdom from Optimal Transport
- Advanced Quantum Mechanics: Lecture 1
- Thermodynamic Consistency of Driven Quantum Optical Master
- Nonequilibrium Thermodynamics of Quantum Coherence Beyond Linear Response
- Machining the Ghost: Ideating in the Age of AI
- Nutrition: The Hidden Traps
- Conceptual Abstraction and Analogy in Natural and Artificial Intelligence
- Epilogue: The Map of Machine Learning
- The Mathematics of Crime: Predictive Policing and Gang Activity
- Reasonable AI
- Deep Learning in Biology
- Introduction to Deep Learning
- Universal Thermodynamic Bounds on Symmetry Breaking in Living Systems
- Statistical Thermodynamics as a Paradigm for Data Science
- Introduction to Information Theory
- Analysis of Boolean Functions: Applications in Social Choice
- Exploration of deep reinforcement learning architectures and algorithms
- Exploration of deep reinforcement learning algorithms
- Exploration of advanced topics in deep reinforcement learning
- Exploration of advanced topics in deep reinforcement learning
- Exploration of advanced topics in deep reinforcement learning
- Exploration of advanced topics in deep reinforcement learning
- Frenetic Steering
- Imitation Learning, Foundation Models, and Course Wrap-up
- Bridging Rigorous Methods with Machine Learning in Robotics
- Sequential Optimization of Dynamically Augmented Conditional Value-at-Risk
- Minimal Architecture for Adaptation in Non-Equilibrium Chemical Signaling Networks
- What to Learn from Few Visible Transitions' Statistics?
- Emergent Behaviors in Foundational Models
- Randomized Matrix Multiplication
- An Occam's Razor Principle for Transformers?
- 1D Hydrodynamics
- Scaling Density Functional Theory with Gaussian Splatting (GS-DFT)
- Form Models II: Open-endedness and Prophecy
- Crowding and Selectivity Theory in Quantitative Finance
- Advanced Topics and Course Summary
- Day 4 (I) - Who to Include in Analyses _ Prof. L.Jeyaseelan