ConceptAI & ML
Inference
The process of using an already trained machine learning model to make predictions or classify new data inputs.
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
5Each in their own terms, from the easiest level.
Pieter Abbeel
The process of calculating the probability of a query variable given some observed evidence in a Bayes net.Andrej Karpathy
The process of generating new data from a trained model by sampling from the probability distributions produced by feeding token sequences into the network.Brian Yu
The process of deriving new sentences from old ones.Phillip Isola
In machine learning, inference is making predictions about new datapoints using a trained model.
Lectures that assume it
7- Speculations on Test-Time Scaling for Large Language Models (o1)
- Logic Programming, Part 2: MIT 6.001 Structure and Interpretation (1986)
- Evidence Law: Circumstantial and Character Evidence
- Demystifying Mixtral of Experts
- Active Inference: Bridging Perception and Decision-Making
- Generative Control, Action Chunking, and Moravec’s Paradox
- Who Am I? According to Mandukya Upanishad - Part 1
Connections
23The lectures that define it or assume it, and the concepts next to it.
Concepts10
- Bayesian network
- Conditional probability
- Joint probability
- Probability distribution
- Backtracking search
- Alakṣaṇam
Show 4 moreShow fewer
Lectures13
- Harvard CS50’s Artificial Intelligence with Python – Full University Course
- Digital Design & Computer Architecture: Introduction and Basics
- Deep Dive into Large Language Models: Pretraining to RLHF
- Bayes' Nets: Representation
- Inference Methods for Deep Learning
- Particle Filtering
Show 7 moreShow fewer
- Speculations on Test-Time Scaling for Large Language Models (o1)
- Logic Programming, Part 2: MIT 6.001 Structure and Interpretation (1986)
- Evidence Law: Circumstantial and Character Evidence
- Demystifying Mixtral of Experts
- Active Inference: Bridging Perception and Decision-Making
- Generative Control, Action Chunking, and Moravec’s Paradox
- Who Am I? According to Mandukya Upanishad - Part 1