ConceptAI & ML
Representation learning
The process of mapping raw data to structured abstract representations.
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.
Machine learning basics2Neural networks2Deep learning1Deep learning basics1Supervised learning1Vector embeddings1
Opens up
Concepts that name this one as a prerequisite.
Lecturers
3Each in their own terms, from the easiest level.
Phillip Isola
Sara Beery
Learning a representation of data that makes subsequent learning tasks easier and more efficient.Cheng Chen
Representation learning learns to represent objects with vector embeddings with a guarantee that semantically similar objects are closer to each other.
Lectures that assume it
10- Transfer Learning: Models
- Objective-Driven AI: World Models that Learn, Remember, Reason, and Plan
- Endpoint Replay: Compressing the Recency Buffer in Deep Reinforcement Learning
- Generalization: Out-of-Distribution (OOD)
- From Large Language Models to Cognitive Architectures
- Multimodal Vision-Language Learning
- Transfer Learning: Data
- Model Scale Versus Domain Knowledge in Long-Term Forecasting of Chaos
- Guest Lecture: Dorsa Sadigh (UC Berkeley CS 285)
- Inaugural Lectures: The Future of Software Engineering with AI, Making it Ping, and Digital Humanism
Connections
23The lectures that define it or assume it, and the concepts next to it.
Concepts8
Show 2 moreShow fewer
Lectures15
- Representation Learning: Similarity-Based
- Generative Models: Representation Learning Meets Generative Modeling
- Representation Learning: Reconstruction-Based
- Generative Models: Basics
- SingleStore Database Overview
- Transfer Learning: Models
Show 9 moreShow fewer
- Objective-Driven AI: World Models that Learn, Remember, Reason, and Plan
- Endpoint Replay: Compressing the Recency Buffer in Deep Reinforcement Learning
- Generalization: Out-of-Distribution (OOD)
- From Large Language Models to Cognitive Architectures
- Multimodal Vision-Language Learning
- Transfer Learning: Data
- Model Scale Versus Domain Knowledge in Long-Term Forecasting of Chaos
- Guest Lecture: Dorsa Sadigh (UC Berkeley CS 285)
- Inaugural Lectures: The Future of Software Engineering with AI, Making it Ping, and Digital Humanism