Spring 2022 MW 9:45am – 11:15am, from March
28th to June 1st
Location:
Thornt 211 (Charles B. Thornton Center for
Engineering and Management)
Edward Chang (echang@cs.stanford.edu)
Adjunct Professor, Computer Science, Stanford
University
Visiting Professor,
EECS, UC Berkeley (2017-2021)
President, HTC DeepQ Healthcare (2012-2021)
Director of
Research, Google (2006-2012)
Professor, ECE, UC
Santa Barbara (1999-2006)
CA: Ruishan
Liu (ruishan@stanford.edu)
Announcements (last update 5/12)
§
(5/12) Lectures #13, and #14 are both online.
§
(5/7) We kicked off the final segment of the course today and began our
6-lecture series on Consciousness.
§
(4/27) Lecture #12 slides online, Saahil Jain’s short talk on Search
Engine on Canvas.
§
(4/21) Lectures #8 and #10 recorded in 2021 are online.
§
(4/18) Lecture #7 guest speaker Alexey Bochkovskiy’s slides and video
are posted.
§
(4/11) Lecture #6 slides is on Canvas together with last year’s recorded lecture.
§
(4/06) Lecture #5 slides is online.
Please formulate your project proposal by 4/13.
§
(4/03) Lecture #4 slides is online.
The recorded lecture in 2021 is posted on Canvas. Assignment #1 due on 4/11.
§
(4/02) Lecture #3 slides on protein folding and DNA sequencing will be
posted on Canvas later this quarter.
§
(3/30) Lecture #2 slides is online.
The link to the recorded lecture in 2021 is announced on Canvas.
§
(3/28) Lecture #1 slides and audio recording is online.
§
(3/26) The University requires in-person attendance in Spring. The first lecture is essential to attend to
decide enroll/drop. I will record only
the first two lectures for course shoppers.
§
(2/22) Received top review in 2021.
§
(2/1) First
syllabus draft posted.
About
Artificial intelligence, specifically
deep learning, stands out as one of the most transformative technologies of the
past decade. AI can already outperform humans in several computer vision and
natural language processing tasks. However, we
still face some of the same limitations and obstacles that
led to the demise of the first AI boom phase five decades ago. This
research-oriented course will first review and reveal
the limitations (e.g., iid assumption on training and
testing data, voluminous training data requirement, and lacking interpretability)
of some widely used AI algorithms, including
convolutional neural networks (CNNs), transformers, reinforcement learning, and
generative adversarial networks (GANs). To address
these limitations, we will then explore
topics including transfer learning for remedying data scarcity,
knowledge-guided multimodal learning for improving data diversity, out of
distribution generalization, subspace learning for enabling interpretability,
privacy-preserving data management, and other topics. (The 2022
edition plans to cover consciousness modeling.)
The course will be taught through a
combination of lecture and project sessions. Lectures on specialized AI applications
(e.g., cancer/depression diagnosis and treatment) will feature guest speakers
from academia and industry. Students
will be assigned to work on a term project that is 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 welcome to formulate a project
that leverages their own graduate research.
Level: Senior/graduate of EE/CS, Medicine, Medical Informatics, Engineering;
proficient in programming
Perquisite: Introductory course in AI, Statistics, or Machine Learning
Assignments
· No exams.
· Three written assignments in the first half of the
quarter.
· Reading: A list of papers/articles/podcasts grouped by topics. Each student selects one topic of interest to
conduct in-depth surveys and presentation.
· Term project: A group project of two to three involving algorithm
design and coding. Some past example
projects are:
§ COVID-19 demographic analysis
§ COVID-19 outbreak tracking and prediction
§ Thoracic disease diagnosis with limited X-ray images
§ News article summarization (extractive and abstractive)
§ Methods for fusing knowledge and perception (text and image)
§ Symptom checker
Textbook
Probabilistic
Machine Learning, Kevin P. Murphy, March 2022
Projections: A Story of Human
Emotion, Karl Deisseroth, 2021
Grading
· Assignments 20%
· Class participation 20%
· Literature survey and project proposal 20%
· Project implementation and demo 40%
Syllabus
|
Date |
Description |
Course Materials |
Notes |
|
Week #1 3/28/2022 |
Course Aims and
Syllabus |
Overview the current surgence of AI since
2012, including some promises, constraints, and future directions. Go over course logistics. |
Prof. Edward Chang |
|
3/30/2022 |
P4 Medicine, Part
1 of 4: Healthcare Paradigm Shift [slides][video-2021
Canvas] |
[1] Edward Y. Chang, et al., "Artificial Intelligence in XPRIZE DeepQ Tricorder. " ACM MM Workshop for Personal
Health and Health Care, 2017. [2] FC Chang, JJ Chang, CN Chou, EY Chang, “Toward Fusing Domain
Knowledge with Generative Adversarial Networks to Improve Supervised
Learning for Medical Diagnoses”, FC Chang, JJ Chang, CN Chou, EY Chang, IEEE
MIPR Conference, 2019. [3] Edward Y. Chang, et al., "Context-Aware Symptom Checking for
Disease Diagnosis Using Hierarchical Reinforcement Learning." AAAI,
2018. [4] Transfer representation learning for medical image analysis, Chuen-Kai Shie, Chung-Hisang Chuang, Chun-Nan Chou, Meng-Hsi
Wu, Edward Y Chang, IEEE EMBC, 2015. |
Prof. Edward Chang |
|
4/1/2022 |
P4 Medicine, Part
2 of 4 Protein Folding
& DNA Sequencing (& project
discussion) [full slides
on Canvas] [video] |
[1] Highly accurate protein structure prediction with AlphaFold,
DeepMind, Nature, May 2021. [2] The sequence of the sequencers, The history of sequencing DNA, J. M.
Heather and B. Chain, Genomics 107(1), pp. 1-8, January 2016. [link] |
Prof. Edward Chang
|
|
Week #2 4/4/2022 |
P4 Medicine, Part
3 of 4: ML with Data and
Inductive Biases [slides]
[video-2021 Canvas] |
[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]. [3] Universal Equivariant Multilayer Perceptrons,
Siamak Ravanbakhsh,
ICML, 2020. [4] The problem of Protein Folding, Wikipedia. [5] On Bottleneck of Graph Neural Networks and its Practical
Implications, Uri Alon, Eran Yahav, ICRL
2021. [6] SIGN: Scalable Inception Graph Neural Networks, Fabrizio Frasca, Emanuele Rossi, Davide Eynard, Ben Chamberlain, Michael
Bronstein, Federico Monti, GraphSaint, 2020. [7] Panel: VR/AR for Surgery and Medical Education, April 2018 [link]. [8] Stanford SNI Talk: Advancing Healthcare w/ AI and VR, Edward Y.
Chang [link] (Stanford ID
required). [9] Daphne Koller: Biomedicine
and Machine Learning, AI Podcast #93 with Lex Fridman,
May 2020 [link] |
Prof. Edward Chang Assignment #1: Deadline 4/11 |
|
4/6 |
Finish last
lecture; Start NLP, Part 1
of 3: Hand-engineering,
Similarity, Collaborative Filtering, Latent Dirichlet Allocation [slides]
[video-2021 Canvas] Brainstorming on
term projects, datasets, and resources |
[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]. |
Prof. Edward Chang |
|
Week #3 4/11/2022 |
NLP, Part 2 of 3: Attention,
Transformers, BERT, and GPT [slides Canvas] [ video-2021 Canvas] |
[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]. |
Prof. Edward Chang |
|
4/13 |
CA led project
discussion |
Four to five candidate projects will be presented in class for
selection. [1] Nodule detection from DeepQ Health, [2] Document summarization from You.com, [3] News recommendation from Ailly.ai, and [3] Two healthcare projects from Stanford Medical School. |
Prof. Edward Chang CA: Ruishan Project Proposal Deadline 4/20 |
|
Week #4 4/18/2022 |
Object Detection,
YOLOv4/YOLOR guest lecture [sildes][video] |
YOLOv4: Optimal Speed and Accuracy of Object Detection, A. Bochkovskiy,
C-Y Wang, H-Y M. Liao [link],
2020. Other links are provided on the last page of the slides by Dr.
Bochkovskiy. |
Dr. Alexey Bochkovskiy |
|
4/20 |
NLP Part 3 of 3: CLI: Conversational
Language Interface, Dialogue & Virtual Assistant (Alexa, Google Home, & Oval),
and Conversational Language Interface [slides][video] Project signed up,
project group formed, and project abstract due |
[1] GPT3 and multimodal pre-trained models [2] OVAL [3] Chirpy Cardinal [4] Genie [5] Tricorder revisit, Edward Y. Chang, et al., "Artificial Intelligence
in XPRIZE DeepQ Tricorder. " ACM MM Workshop
for Personal Health and Health Care, 2017. |
Prof. Edward Chang Project Proposal due @ 11:59pm |
|
Week #5 4/25/2022 |
Cancer, Part 1 od
2: Cancer Causes and Diagnosis (recorded in 2021) [video] |
[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 |
|
4/27 |
P4 Medicine, Part
4 of 4: History of AI in
Diagnosis, Principles of Precision
Diagnosis, Precision Surgery, and Optogenetics. |
[1] Edward Y. Chang et al., "Context-Aware Symptom Checking for
Disease Diagnosis Using Hierarchical Reinforcement Learning." AAAI
(2018). [2] Edward Y. Chang et al., "REFUEL: Exploring Sparse Features in
Deep Reinforcement Learning for Fast Disease Diagnosis." NIPS (2018). [3] Szolovits, P., and S. G. Pauker. "Categorical and Probabilistic Reasoning in
Medical Diagnosis.” Artificial Intelligence 11(1-2), 1978: 115-144. [4] Wu, T. D. "Efficient Diagnosis of Multiple Disorders Based on a
Symptom Clustering Approach." Proceedings of AAAI, 1990, pp. 357-364. [5] 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. |
Prof. Edward Chang |
|
4/27 (bonus) |
Title: An
Intro to Search: Past, Present, & Future [video][slides] |
Abstract: In this talk, we
will cover a range of topics related to the past, present, and future of
search. Topics will introduce the following concepts: search, relevance,
search system considerations, search architectures, classical information
retrieval, neural information retrieval, reranking, search system evaluation,
benchmarks, and future research directions.
|
Saahil Jain, You.com |
|
Week #6 5/2/2022 |
Cancer, Part 2 of
2: Cancer Treatment and How AI May Help (recorded in 2021) [video] |
[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 |
|
5/4 |
Project Check-in:
methods, datasets, experiments, and preliminary results |
|
CA: Ruishan Liu |
|
Consciousness Modeling, the Next Frontier of
Artificial Intelligence |
|||
|
Week #7 5/9 |
Consciousness
& Mind, Part 1 of 6, AI for Psychiatry:
Beyond Brainless and Mindless? [slides][video] |
[1] Students Face Mental Health Challenges --- barriers to care (during
COVID-19)”, Stanford Daily (4/30/2020) [link]. [2] Meditation Music: Sangchhen
Dorji Lhuendrup Nunnery,
Bhutan, Himalayas, Edward Y. Chang [link]. |
Dr. Vikas Duvvuri, MD/PhD
Stanford |
|
5/11 |
Consciousness
& Mind, Part 2 of 6: What is Consciousness? Rule of Nature in
Physics and Biology [slides][video] |
[1] What is Life, Schrodinger, Cambridge University Press, 1992 [2] Discovery of Discovery of a Perceptual Distance Function for
Measuring Image Similarity Beitao Li, Edward
Chang, and Yi Wu, Multim.
Syst. [link]. [3] What is Life, Erwin Schrodinger [link]. |
Prof. Edward Chang |
|
Week #8 5/16/2022 |
Consciousness
& Mind, Part 3 of 6: Where is Consciousness, Optogenetics for
Neuron/Brain Visualization, Joy and Pain, Memory, and Evolution |
[1] Projections, by Karl Deisseroth, Random House, 2021. [2] Tutorials to Brain Structures [link][link]. [3] Podcast links on Evolution (distributed on Slack) |
Prof. Edward Chang |
|
5/18 |
Consciousness
& Mind, Part
4 of 6: An Uncertain Future, Coping with COVID-19 anxiety with facts and
right perspectives |
This pandemic is not going away soon. It has impact health,
economy, and living tremendously, perhaps the most drastic one in our
lifetime this far. How should we deal with it
mentally? Dr. Duvvuri lectures on
COVID-19 and AI. |
Dr. Vikas Duvvuri,
MD/PhD Stanford |
|
Week #9 5/23 |
Consciousness
& Mind, Part 5 of 6: Mind, Love, and Ethics |
[1] The Emperor’s New Mind, Roger Penrose, 2016 edition [2] Divine Comedy, Dante Alighieri, 1320 [3] Podcast links |
Prof. Edward Chang |
|
5/25 |
Consciousness
& Mind, Part 6 of 6: Putting All Together |
|
Prof. Edward Chang |
|
Week #10 5/30 |
Memorial Holiday |
|
|
|
6/1: 9:45am – 11:20am |
Project: final
presentations Session #1 |
|
Final report due
on 6/8 |
|
6/3: 9:45am – 11:20pm |
Project: final
presentations Session #2 |
Final report due
on 6/8 |
|
|
|
|||