02:44:37

CSE574: Week 2: Atomic Transition Systems; Operator-based planning

02:39:08

CSE574 Week 1: Introduction & What is Planning --an expansive view

01:11:33

Human-Aware Planning Methods for Active Teaming (Sachin Grover's PhD Defense at ASU 7/18/2022)

01:21:12

Foundations of Human-Aware Explanations for Sequential Decision Making Problems (PhD Defense @ASU)

05:49

Rao talking on Good Morning Arizona about DALL-E/LaMDA/AI Sentience

58:11

Planning to Advise and Explain Reinforcement Learning (Invited talk at PRL Wkshp; ICAPS 2022)

01:15:14

Perceiving, Acting, Planning & Self-Explaining: A Cognitive Quartet.. (Yantian Zha's PhD Defense)

46:48

Incorporating Human Cognitive Limitations into Sequential Decision Making Problems and Algorithms

06:23

Chaitali talking about her dad Nirmal Chakrabarti

01:11:15

Analyzing Failure Modes in Inscrutable Machine Learning Models

32:30

Collaborative AI: A Planning Perspective

20:33

Symbols as a Lingua Franca for Bridging Human-AI Chasm for Explainable and Advisable AI Systems

01:25:11

Lecture 28: (Smoothness and Overparameterization); Learning BN; Naive Bayes;

01:28:08

Lecture 27: Bayesian Learning and its many approximations--leading to ML

01:26:22

Lecture 26: D-Sep condition in Bayes Nets; Causality in Bayes Nets; Bayesian Learning Basics

01:03:38

Deep Fakes Interview Part 3

01:11:05

Deep Fakes Interview Part 2

19:49

Deep Fakes Interview Part 1

01:27:19

Lecture 25: BNs as product of factors; BN inference; BN conditional independences

01:24:15

Lecture 24: Bayesian vs. Frequentist statistics; Making Bayes Networks compact (Naive Bayes/EM)

01:24:53

Lecture 23: Bayes Networks: Syntax, Semantics, Specification

01:15:06

Lecture 22: From propositional logic to probabilistic logic (via Non-mon, fuzzy, CFs)

01:23:05

Lecture 21: Planning with lifted representations of goals, actions and states; Predicate Logic

32:13

Taming Broad/Shallow AI with Explicit Knowledge & Bridging Human-AI Chasm w/ Symbolic Lingua Franca

01:07:44

Rise of AI & Challenges of Human-Aware AI Systems (Talk at IIT Madras Foundation)

01:02:36

Yochan Human-Robot Halloween

01:25:29

Lecture 20: Resolution theorem proving; search in theorem proving; Horn Clauses; SAT/CSP Solving

01:24:25

Lecture 19: Logics/Propositional logic--model vs. proof theory, resolution theorem proving

01:19:40

Human-Aware AI Methods for Active Teaming

40:35

Perceiving, Acting, Planning & (Self-)Explaining: A Cognitive Quartet with Four Neural Networks

47:20

Lecture 18 (Extension): LLMs, Word Vectors, Auto-encoders, GANS done slower

01:25:48

Lecture 18: CNNs, Data Augmentation, Tfr Learning, LLMs as 1-D CNN

01:24:34

Lecture 17: Foundations of Generalization in Learning (in the backdrop of batchnorm/dropout)

01:27:32

Lecture 16: Back propagation; GPU connection; weight initializaiton and batch norm

01:30:32

Lecture 15: Cross-entropy and other error functions; Perceptron expressiveness; Kernel m/c to MNN

01:28:37

Lecture 14: Inductive Learning: Regression, Classification, Perceptron Learning

01:30:00

Lecture 13: Generalization in RL --Online Learning/regression-gradient descent

01:29:41

Lecture 12: Model-free RL: Temporal Difference Learning & Q-Learning drill-down

19:31

Explainable Plans and Decisions (Talk at CRA Workshop on AI & OR)

01:24:31

Lecture 11: Why VI converges; Policy Iteration; Improvements to PI/VI; discussion of RL

01:27:11

Lecture 10: Drilling down into Bellman Equations and infinite horizon value/policy iteration

01:24:54

Lecture 9: MDPs--intuitions on value/discount/policy+digression to RL+ Value Iteration

01:26:36

Lecture 8: Markov Decision Processes--and connections galore (to A*, incentives, life..)

00:09

ECP and AIPS become ICAPS (Sep 12, 2001; Toledo)

01:25:46

Lecture 7: Online Search: Depth-limited Minmax; RTA*; Monte Carlo Tree Search

01:31:39

Lecture 6: (Some odds/ends of A*); Game tree search--including alpha-betra pruning

01:22:05

Lecture 5: Everything A* Search (also path vs. node search)

01:20:12

Lecture 4: A* search and heuristics intro; environments, blind search, iterative deepening search

01:09:40

Lecture 3: Agent Architectures; hybrid vs. end-to-end and their interpretability tradeoffs

01:26:45

Lecture 2: GPT3 & LLM demo/discussion; 4 defns of AI; agent architectures

01:09:09

Lecture 1: Course info; Definitions of AI; Agent Architectures Intro to AI

19:09

Integrating Planning, Execution and Monitoring in the presence of Open World Novelties

16:14

Trust-Aware Planning: Modeling Trust Evolution in Longitudinal Human-Robot Interaction

16:14

Providing personalized explanations for sequential decision making problems

14:11

Leveraging PDDL to Make Inscrutable Agents Interpretable

14:06

Synthesizing Policies That Account For Human Execution Errors

15:02

Planning for Proactive Assistance in Environments with Partial Observability (

09:58

GPT3 To Plan: Extracting plans from text using GPT3

01:13:21

Foundations of Human-Aware Explanations for Sequential Decision-Making Problems

01:05:27

AI & Ethics