ConceptAI & ML
Supervised learning
Learning to predict an output y from an input x given a data set of input-output pairs.
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 learning4Labeled data3Training data3Target function2Artificial neural networks1Basic premise of learning1Basic probability1Data1
Opens up
Concepts that name this one as a prerequisite.
Lecturers
13Each in their own terms, from the easiest level.
Yaser Abu-Mostafa
A setting where we have a target function and a dataset containing both the input features and the corresponding target outputs.Fei-Fei Li, Justin Johnson & Serena Yeung
A type of problem where we have data X and labels Y, and the goal is to learn a function mapping X to Y.Brian Yu
A type of task where we give the computer access to a data set consisting of input-output pairs, and the AI learns a function to map inputs to outputs.Andrew Ng
A learning problem where the algorithm is provided with a data set of inputs and their corresponding right answers (outputs) to learn the association between them.Andrej Karpathy
A training process where models imitate human expert players.Emma Brunskill
A machine learning paradigm that involves learning from data with correct labels and performing generalization.Shrikant I. Bangdiwala
Training a model on labeled data, where the desired output is known.Barbara Kwiecinska
A learning method where data sets with a known output are presented to the neural network to calculate and minimize error.Yann LeCun
Training a machine by showing examples instead of programming it, where parameters are tweaked when the output is wrong.Ashish Vaswani, Lucas Beyer & William Fedus
Predicting on the same tasks that supervised deep learning or any supervised machine learning method is trying to predict well on.Chris Ré
A machine learning paradigm where a model is trained on a dataset of input-output pairs to learn a mapping from inputs to outputs.Ilya Sutskever
A paradigm in machine learning that gives precise mathematical conditions under which learning must succeed, requiring low training error and a training set larger than the degrees of freedom.
Lectures that assume it
44The first 12 are shown.
- Introduction to Reinforcement Learning
- State of GPT: Pretraining, SFT, Reward Modeling & RLHF Pipeline
- The Linear Model II
- Architectures: Memory
- Decision Transformer: Reinforcement Learning via Sequence Modeling
- Imitation Learning II: Covariate Shift & Dataset Aggregation (DAgger)
- Representation Learning: Similarity-Based
- Fundamental concepts in deep reinforcement learning
- The Alberta Plan for AI Research: Continual Reinforcement Learning
- Learning Representations: A Challenge for Learning Theory, COLT 2013
- Generative Models: Conditional Models
- Simulation-Driven Robot Learning for the Lazy Researcher
Connections
69The lectures that define it or assume it, and the concepts next to it.
Concepts9
- Machine learning
- Training data
- Target function
- Artificial neural networks
- Reinforcement learning
- Imitation learning
Show 3 moreShow fewer
Lectures60
- Harvard CS50’s Artificial Intelligence with Python – Full University Course
- The Learning Problem
- Is Learning Feasible?
- Machine Learning (CS 229): Lecture 1 - Course Introduction
- Deep Dive into Large Language Models: Pretraining to RLHF
- Self Attention and Non-parametric transformers (NPTs)
Show 54 moreShow fewer
- Introduction to Reinforcement Learning (CS234, 2024, Lecture 1)
- Generative Models
- Neural Networks I: Feedforward Architectures & Backpropagation
- Objective-Driven AI: World Models that Learn, Remember, Reason, and Plan
- An Observation on Generalization and Unsupervised Compression
- The Deep Learning Revolution: The Sequel (Turing Award Lecture)
- Deep Reinforcement Learning
- Foundations of Deep Reinforcement Learning: Problem Formulation & Neural Control
- Day 4 (IV) - AI, ML and Computer intensive methods in RCTs _ Prof. Shrikant I Bangdiwala
- Current & Future Application of AI in Epilepsy by Dr. Barbara Kwiecinska, PGY4 Neurology Resident
- Introduction to Reinforcement Learning
- State of GPT: Pretraining, SFT, Reward Modeling & RLHF Pipeline
- The Linear Model II
- Architectures: Memory
- Decision Transformer: Reinforcement Learning via Sequence Modeling
- Imitation Learning II: Covariate Shift & Dataset Aggregation (DAgger)
- Representation Learning: Similarity-Based
- Fundamental concepts in deep reinforcement learning
- The Alberta Plan for AI Research: Continual Reinforcement Learning
- Learning Representations: A Challenge for Learning Theory, COLT 2013
- Generative Models: Conditional Models
- Simulation-Driven Robot Learning for the Lazy Researcher
- Expanding What Robots Can Learn in the Real World
- Understanding AI: Semantic Grounding in Large Language Models
- Intuitions on Language Models and the History of Transformer Architectures
- Offline Reinforcement Learning
- Challenges & Open Problems in Deep Reinforcement Learning
- Inference Methods for Deep Learning
- Sequential Decision-Making: Policy Gradients vs. Value-Based Architectures
- Turing Lecture: Deep Learning for AI and System-2 Reasoning
- Leveraging Per-Instance Privacy for Machine Unlearning
- Generalization: Out-of-Distribution (OOD)
- Integrating Learning and Planning
- Imitation Learning I: Behavioral Cloning & Distributional Shift
- Efficient Algorithms for Reliable Machine Learning
- Generalization Theory
- Theory of Modern AI: Learning Theoretic, Game Theoretic, and Algorithmic Perspectives
- Representation Learning: Reconstruction-Based
- Generative Models: Basics
- Generative Control, Action Chunking, and Moravec’s Paradox
- Exploration of deep reinforcement learning architectures and algorithms
- Exploration of advanced topics in deep reinforcement learning
- Model-Based Reinforcement Learning with Policies
- Towards a Statistical Foundation for Reinforcement Learning
- Challenges and Open Problems in Deep Reinforcement Learning (CS 285, Lecture 23, Part 1)
- Questions for Theory in the New Age of Machine Learning
- Language Models: Prompting, Chain-of-Thought, and Instruction-Tuning
- Transformers in Vision: Tackling problems in Computer Vision
- Epilogue: The Map of Machine Learning
- Overview of Transformers (Stanford CS25: Transformers United V6)
- Guest Lecture: Aviral Kumar (UC Berkeley CS 285)
- Guest Lecture: Dorsa Sadigh (UC Berkeley CS 285)
- Imitation Learning, Foundation Models, and Course Wrap-up
- An Occam's Razor Principle for Transformers?