Logic and Artificial Intelligence

Advanced Graduate course, Wed, Fri 11-12:15 pm, 0216 Siebel Center for Comp Sci, 2021

Head TA: Linyi Li Office hours: Wed 12:15-1:15 pm

Instructor Office hours: Fri 12:15-1:15 pm

Overview

Given the black-box nature of the state-of-the-art AI models and the lack of associated formal guarantees, there is a growing interest in using formal methods for AI-based systems to ensure their reliability and interpretability. This direction is a key component of the so-called “Third wave of AI”. Similarly, there is a growing interest in leveraging data-driven machine learning for knowledge discovery and boosting logical inference. This course will introduce recent developments in both directions and outline several promising future research directions. Overall, the students will be exposed to the following topics:

  • Verification of AI systems
  • Symbolic explanations of neural networks
  • Training and querying with logic
  • Robust training methods
  • Neural network repair
  • Probabilistic circuits
  • Neurosymbolic computing
  • Machine learning for verification

The course will be taught in person. For students preferring to attend remotely, the video recording of the lectures will be made available online.

Lectures

DateTitleSlides Reading material
Aug 25, 27Introduction
Sep 1, 3Verification of neural networks: Box + MILP

Box

MILP

Sep 8, 10Verification of neural networks: Zonotopes

Lecture notes

Sep 15, 17 Verification of neural networks: DeepPoly + Refinement

DeepPoly

Refinement

Sep 22Project presentation
Sep 24Verification of neural networks: k-ReLU

k-ReLU

Sep 29, Oct 01Symbolic explanation of neural networks

Polaris

Oct 06, 08Training and querying with Logic

DL2

Oct 13, 15Robust training of neural networks

IBP

DiffAI

Oct 20, 22Neural network repair

DDNN

Oct 27, 29Probabilistic circuits

PC

Nov 03, 05Neurosymbolic computing

ns-vqa

ns-cl

Nov 10, 12Machine Learning for verification

GNN branching

Lait

Nov 17, 19, Dec 01, 03, 08Student Presentations

Grading

The students will work in a group of 2 or individually on:

  • a course project,
  • conference-style paper presentation on one of the topics taught in the course towards the end of the semester (see dates above). The students are free to select any paper, but it must be approved by us.

Both project and presentation will make up 50 % of the grade each.

Key Dates

DeadlineTask
Sep 21Register your group for the project and presentation
Oct 26Selecting a paper to present
Nov 10Project submission