Tractable Learning in Structured Probability Spaces
Offered By: Simons Institute via YouTube
Course Description
Overview
Syllabus
Intro
References
Running Example
Learning with Constraints
Example: Video
Example: Language
Example: Deep Learning
What are people doing now?
Structured Probability Spaces
Boolean Constraints
Combinatorial Objects: Rankings
Encoding Rankings in Logic
Structured Space for Paths
Logical Circuits
Property: Decomposability
Property: Determinism
Sentential Decision Diagram (SDD)
Tractable for Logical Inference
PSDD: Probabilistic SDD
Tractable for Probabilistic Inference
PSDDs are Arithmetic Circuits
Parameters are interpretable
Learning Algorithms
Learning Preference Distributions
What happens if you ignore constraints?
Structured Naïve Bayes Classifier
Structured Datasets
Learning from Incomplete Data
Structured Queries
Conclusions
Taught by
Simons Institute
Related Courses
Electrónica Digital Bit a Bit: Fundamentos, Verilog y FPGAPontificia Universidad Católica de Chile via Coursera Sistemas Digitales: De las puertas lógicas al procesador
Universitat Autònoma de Barcelona (Autonomous University of Barcelona) via Coursera Digital Circuits
Indian Institute of Technology, Kharagpur via Swayam Digital System Design
Indian Institute of Technology, Ropar via Swayam ITC Conference - Line Point Zero Knowledge and Its Applications
Paul G. Allen School via YouTube