Text Description automatically generated with medium confidence

 

Spring 2023 MW 4:30pm – 5:50pm, April 3rd – June 5th

Location: Gates B12

 

Edward Chang (echang@cs.stanford.edu)

Adjunct Professor, Computer Science, Stanford University

 

CA: Henrik Marklund

 

Office Hours: MW after class to 6:15pm at Gates B12 or 104.

 

 

Announcements

 

 

About

 

The 2023 edition of the course will focus on topics related to Generative AI, including GPT-3/4, ChatGPT, BioGPT, and consciousness modeling.

 

Artificial intelligence, specifically deep learning, attention mechanisms, and foundation models, has emerged as some of the most transformative technologies of the past decade. AI can already outperform humans in various computer vision and natural language processing tasks. However, we still face some limitations and obstacles reminiscent of those that contributed to the decline of the first AI boom five decades ago. This research-oriented course will initially examine the limitations (e.g., iid assumption on training and testing data, extensive training data requirements, and lack of interpretability) of widely used AI algorithms, including convolutional neural networks (CNNs), transformers, reinforcement learning, generative AI, LLMs, and AI safety. To address these limitations, we will explore topics such as transfer learning to alleviate data scarcity, knowledge-guided multimodal learning to enhance data diversity, out-of-distribution generalization, subspace learning for interpretability, privacy-preserving data management, emotion/behavior/ethics modeling, and more.

The course will be taught through a combination of lectures and project sessions. Guest speakers from academia and industry will present lectures on specialized AI applications (e.g., cancer/depression diagnosis and treatment). Students will be assigned to work on a term project relevant to their fields of study (e.g., CS, Medicine, and Data Science). Projects may involve conducting literature surveys, formulating ideas, and implementing these ideas. Students are encouraged to develop a project that integrates their own graduate research.

 

Note: The following prerequisite for taking this course have been waved because of the ease-of-use of ChatGPT. 

Level: Senior/graduate of EE/CS, Medicine, Medical Informatics, Engineering; proficient in basic programming

Perquisite: Introductory course in AI, Statistics, or Machine Learning

 

Assignments

 

·   No exams.

·   Three light-weight assignments, using ChatGPT to complete.

·   Term project: A group project of two to three involving prompt template design. 

 

References (optional)

 

Probabilistic Machine Learning, Kevin P. Murphy, March 2022

Projections: A Story of Human Emotion, Karl Deisseroth, 2021

 

Grading

 

·   Assignments 30%

·   Class participation 10%

·   Literature survey and project proposal 20%

·   Project implementation and demo 40%

 

  Syllabus (last updated 4/03/2023)

 

Date

Description

Course Materials

Notes

Week #1

4/3/2023

 

Course Aims and Syllabus

ChatGPT Intro

[slides]

Intro to AI, GAI and why you should or should not take this course.

E. Chang

4/5/2023

LLMs (Large Language Models) Part 1 of 4

Foundation Models and ChatGPT

[slides]

Intro to GPT-3, GPT-4, ChatGPT, BioGPT and Prompt engineering.

[1]  J. Wei, X. Wang, et al, Chain of thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems, 2022. [link]

[2]  J. Jung, L. Qin, S. Welleck, F. Brahman, C. Bhagavatula, R. L. Bras, and Y. Choi. Maieutic prompting: Logically consistent reasoning with recursive explanations. In Conference on Empirical Methods in Natural Language Processing, 2022. [link]

[3] Prompting Large Language Models with the Socratic Method, E. Y. Chang, IEEE CCWC, March 2023. [link]

[4] Sparks of Artificial General Intelligence: Early experiments with GPT-4,

Sébastien Bubeck, Varun Chandrasekaran, et al, March 2003. [link]

 

E. Chang

 

Assignment #1: Design [your] chatbot functions, using ChatGPT

 

Henrik’s [PPT]

 

Week #2

4/10/2023

P4 Medicine, Part 1 of 3:

History of AI in Diagnosis [link]

 

[1] Schwartz, W. B., R. S. Patil, and P. Szolovits. "AI in Medicine: where do we stand." New England Journal of Medicine 316 (1987): 685-688. [link].

[2] Wu, T. D. "Efficient Diagnosis of Multiple Disorders Based on a Symptom Clustering Approach." Proceedings of AAAI, 1990, pp. 357-364.

[3] Universal Equivariant Multilayer Perceptrons, Siamak Ravanbakhsh, ICML, 2020.

[4] Tricorder (medical IoTs), E. Y. Chang, et al., "Artificial Intelligence in XPRIZE DeepQ Tricorder. " ACM MM Workshop for Personal Health and Health Care, 2017.

[5] Szolovits, P., and S. G. Pauker. "Categorical and Probabilistic Reasoning in Medical Diagnosis.” Artificial Intelligence 11(1-2), 1978: 115-144.

[6] Patil, R. S., P. Szolovits, and W. B. Schwartz. "Causal Understanding of Patient Illness in Medical Diagnosis." In Proceedings of the Seventh International Joint Conference on Artificial Intelligence.

 

E. Chang

4/12/2023

LLM, Part 2 of 4:

Prompt template design principles [link]

+ Noora introduction

 

 

[1] Prompting Large Language Models with the Socratic Method, E. Y. Chang, IEEE CCWC, March 2023. [link]

[2] CRIT: Critical Reading Inquisitive Template, E. Y. Chang. [link]

[3] Noora.cs.stanford.edu

 

E. Chang

 

Assignment #1 due

Assignment #2: Design and test prompting templates

Week #3

4/17/2023

LLM, Part 2 of 4 （finish the lecture）

Prompt template design principles

+ project discussion

 

[1] Prompting Large Language Models with the Socratic Method, E. Y. Chang, IEEE CCWC, March 2023. [link]

[2] CRIT: Critical Reading Inquisitive Template, E. Y. Chang. [link]

[3] Noora.cs.stanford.edu

 

E. Chang

4/19/2023

LLM, Part 3 of 4:

History of NLP in one lecture.

From one-hot vector, word2vec to attention, transformers, BERT, and GPT [slides][video]

 

[1] Attention is all you need, Ashish Vaswani, et al., [link].

[2] BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding [link].

[3] Reformer: The Efficient Transformer [link].

[4] Perceiver: General Perception with Iterative Attention [link].

           

E. Chang

 

Assignment #2 due

Assignment #3: Design chatbot states

Week #4

4/24/2023

Intro to Psychiatric Disorders, symptoms, and treatments [slides][video]

 

NA

 

 

Dr. Vikas Duvvuri,

MD/PhD Stanford

4/26/2023

ChatGPT for Better Communication?  Envisioning the Future of Speech Language Therapy via Generative AI

[slides][video]

[1] Lee, S. A. S. (2019). Virtual speech-language therapy for individuals with communication disorders: Current evidence, limitations, and benefits. Current Developmental Disorders Reports, 6, 119-125.

[2] Du, Y., Grace, T. D., Jagannath, K., & Salen-Tekinbas, K. (2021). Connected play in virtual worlds: communication and control mechanisms in virtual worlds for children and adolescents. Multimodal Technologies and Interaction, 5(5), 27.

[3] Edwards-Gaither, L., Harris, O., & Perry, V. (2023). Viewpoint Telepractice 2025: Exploring Telepractice Service Delivery During COVID-19 and beyond. Perspectives of the ASHA Special Interest Groups, 1-6.

 

Assignment #3 due

 

Prof. Yao Do, Medical School, USC

 

Week #5

5/1/2023

P4 Medicine, Part 2 of 3:

Healthcare with Small Data

[slides]

 

Part#2 Training Your Own ChatGPT [slides]

[1] Daphne Koller:  Biomedicine and Machine Learning, AI Podcast #93 with Lex Fridman, May 2020 [link]

[2] Edward Y. Chang et al., "Context-Aware Symptom Checking for Disease Diagnosis Using Hierarchical Reinforcement Learning." AAAI (2018).

[3] Edward Y. Chang et al., "REFUEL: Exploring Sparse Features in Deep Reinforcement Learning for Fast Disease Diagnosis." NIPS (2018).

 

E. Chang

 

5/3/2023

Project proposal and related work presentation

 

 

Henrik Marklund

E. Chang

Week #6

5/8/2023

P4 Medicine, Part 3 of 3:

Frontier Research [slides]

(Healthcare is already in the 3rd AI winter due to data and regulations.)

[1] On Bottleneck of Graph Neural Networks and its Practical Implications, Uri Alon, Eran Yahav, ICRL 2021.

[2] Panel: VR/AR for Surgery and Medical Education, April 2018 [link].

[3] Stanford SNI Talk: Advancing Healthcare w/ AI and VR, Edward Y. Chang [link] (Stanford ID required).

[4] The problem of Protein Folding, Wikipedia.

 

 

E. Chang

5/10/2023

LLM Part 4 of 4:

Virtual Assistant and Augmented LM. [slides]

[1] Genie: A Generator of Natural Language Semantic Parsers for Virtual Assistant Commands
G. Campagna, S. Xu, M. Moradshahi, R. Socher, and Monica S. Lam
In Proceedings of the 40th ACM SIGPLAN Conference on Programming Language Design and Implementation, Phoenix, AZ, June 2019 [link].

[2] Augmented Language Model, a survey, Meta, 2023 [link].

 

E. Chang

 

Week #7

5/15/2023

Consciousness & Mind, Part 1 of 3: What is Consciousness?

Rule of Nature in Philosophy and Physics (lecture #14) [slides]

 

[1] What is Life, Erwin Schrodinger, online book [link].

[2] COCOMO: Computational Consciousness Modeling, E.Y. Chang, 2023 [link].

 

E. Chang

 

5/17/2023

Consciousness & Mind, Part 2 of 3: Computational Consciousness, COCOMO (lecture #15) [slides].

[1] Projections, by Karl Deisseroth, Random House, 2021.

[2] Discovery of a Perceptual Distance Function for Measuring Image Similarity, Beitao Li, Edward Chang, and Yi Wu, Multim. Syst., 2003 [link].

[3] COCOMO: Computational Consciousness Modeling, E.Y. Chang, 2023 [link].

 

 

E. Chang

 

Week #8

5/22/2023

Cancer, Part 1 od 2: Cancer Causes and Diagnosis (lecture #12)

[video][Slides]

[1] Principles and methods of integrative genomic analyses in cancer, Vessela N. Kristensen, Ole Christian Lingjærde, Hege G. Russnes, Hans Kristian M. Vollan, et al., Nature Reviews, 2014.

[2] Biomarker development in the precision medicine era: lung cancer as a case study, Ashley J. Vargas, and Curtis C. Harris, Natural Reviews, 2016.

[optional] Artificial intelligence in radiology, Ahmed Hosny, Chintan Parmar, John Quackenbush, Lawrence H. Schwartz,and Hugo J. W. L. Aerts, Nature Reviews, 2018.

 

Dr. Melissa Ko,

PhD, Cancer Biology,

Stanford

 

E. Chang

5/24/2023

Cancer, Part 2 of 2: Cancer Treatment and How AI May Help (lecture #13) [video][Slides]

[1] Mass cytometry: blessed with the curse of dimensionality, Evan W Newell & Yang Cheng, Nature Immunology, June 2016.

[2] Next-Generation Machine Learning for Biological Networks, Diogo M. Camacho, Katherine M. Collins, Rani K. Powers, James C. Costello, and James J. Collins, Leading Edge Review, June 2018.

[optional] Personalized Cancer Models for Target, Discovery and Precision Medicine, Carla Grandori1 and Christopher J. Kemp, Trends in Cancer, CellPress Reviews, September 2018.

 

Dr. Melissa Ko,

PhD, Cancer Biology,

Stanford

 

Henrik Marklund

Week #9

5/29/2023

 

Memorial Holiday

 

 

5/31/2023

Consciousness & Mind, Part 3 of 3: GAI Alignment, Free Will, Ethics, and Mind; Course Summary (lecture #16)

 

[1] COCOMO: Computational Consciousness Modeling, E.Y. Chang, 2023.

 

E. Chang

 

5/31/2023

Project Presentation I

Please sign up (sending us email)

E. Chang

Henrik Marklund

Week #10

6/5 (last day of class)

 

Project Presentations II

Presentation time is flexible to arrange between 5/31 and 6/5.   If later than 6/5, then online presentation can be arranged.

E. Chang

Henrik Marklund