ConceptAI & ML
Generative model
Models that learn how to generate all of the data by modeling the joint probability distribution of features and labels.
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
6Each in their own terms, from the easiest level.
Phillip Isola
Models that can model a multimodal distribution and joint dependencies between multidimensional predictions.Fei-Fei Li, Justin Johnson & Serena Yeung
A class of unsupervised learning models that aim to generate new samples from the same distribution as the training data.Karl Friston
A probabilistic model that describes how observed data is generated from underlying hidden states.Stefano Ermon
A model that learns to generate complex objects like images, text, or audio by learning from data.Holger Lyre
Learn joint probability distribution p(e,h) to learn how data were generated in order to categorize.
Lectures that assume it
27The first 12 are shown.
- Adversarial Examples and Adversarial Training
- Deep Dive into Large Language Models: Pretraining to RLHF
- Me and My Markov Blanket
- Making is Decision Making
- Mechanism Design & Game-Theoretic Incentives for Collaborative Learning
- AI for Materials on Demand: Accelerating Discovery
- Inference Methods for Deep Learning
- Objective-Driven AI: World Models that Learn, Remember, Reason, and Plan
- Machine Learning: Naive Bayes
- Differentially Private Table-Image Multimodal Data Generation
- Unifying the Cognitive Sciences: The Free Energy Principle
- The Physics of Motivation: An Active Inference Perspective
Connections
45The lectures that define it or assume it, and the concepts next to it.
Concepts10
Lectures35
- Generative Modeling by Estimating Gradients of the Data Distribution
- Generative Models
- Generative Models: Conditional Models
- Understanding AI: Semantic Grounding in Large Language Models
- Machine Learning: Perceptrons and Logistic Regression
- Active Inference: Bridging Perception and Decision-Making
Show 29 moreShow fewer
- Generative Models: Basics
- The Physics of Communication
- Adversarial Examples and Adversarial Training
- Deep Dive into Large Language Models: Pretraining to RLHF
- Me and My Markov Blanket
- Making is Decision Making
- Mechanism Design & Game-Theoretic Incentives for Collaborative Learning
- AI for Materials on Demand: Accelerating Discovery
- Inference Methods for Deep Learning
- Objective-Driven AI: World Models that Learn, Remember, Reason, and Plan
- Machine Learning: Naive Bayes
- Differentially Private Table-Image Multimodal Data Generation
- Unifying the Cognitive Sciences: The Free Energy Principle
- The Physics of Motivation: An Active Inference Perspective
- Accelerating Scientific Discovery with Artificial Intelligence
- Theory of Modern AI: Learning Theoretic, Game Theoretic, and Algorithmic Perspectives
- Hacker's Guide to Deep Learning
- Generative Control, Action Chunking, and Moravec’s Paradox
- From Large Language Models to Cognitive Architectures
- Variational Inference, Part 4 (CS 285, Lecture 18)
- Visualizing and Understanding
- Transfer Learning: Data
- Deep Inference with Karl J. Friston
- From Large Language Models to General Artificial Intelligence?
- Super Turing Computing: Foundations for Aware and Ever-Adapting Systems
- Exploration of advanced topics in deep reinforcement learning
- Imitation Learning, Foundation Models, and Course Wrap-up
- An Occam's Razor Principle for Transformers?
- Systems Engineering in the Age of Autonomy and Complexity