Spring 2024 Computer Science 458. 4/10/2024


[Home]

Canvas Quiz of the Day (need daily password)

Most days, there will be a simple canvas quiz related to the lecture. You need a password to activate the quiz, which I will provide in class. These quizzes will count toward your class participation grade. The quiz is available only during class.

Click for today's quiz.

Administrivia

  • I have office hours Mondays and Wednesdays from 2-3 pm, on zoom, id 459 434 2854.

  • Complete the online student information sheet. Note: the previous form was not working. Please submit again. Thanks.

    Talk: Lori Goler, Meta. Thursday April 11th, 3pm, Tsai City

    Lori Goler '91 will discuss her current position as chief human resources officer at Meta and the key experiences along the way that enabled this role. She will reflect on how students can prepare themselves for the workforce, including technical skills that are most desirable. Lastly, Lori will discuss how she coordinates with the various units inside the large ecosystem of Meta.

    Risk and AI Certificate Program

    Rich Apolostik last week mentioned a new GARP certificate program in AI. He has asked me to join the advisory committee. I would welcome your thoughts on issues related to AI and risk. I have added a canvas discussion question. Feel free to dive in.

    Guest Lecture Wednesday April 17th (via zoom) Alborz Geramifard, Meta

    Bio: Alborz Geramifard is a research science director at Meta working on reinforcement learning (RL). Previously he led the Conversational AI at Meta where the team brought the end-to-end approach for dialog management using LLMs into product (https://ai.facebook.com/blog/project-cairaoke/). Prior to joining Facebook, he led the conversational AI team at Amazon Alexa and created more than a dozen of NLU models shipped into production. He obtained his PhD from MIT and MSc from University of Alberta, both in RL. Alborz was the recipient of the NSERC scholarships 2010-2012. He has contributed to the community in various roles including the guest editor for Machine Learning Journal and AI Magazine and Area Chair for EMNLP, NAACL and ACL.

    Abstract: Meta's mission is to empower people to build community and bring the world closer together through artificial intelligence. As part of this mission, Meta believes that augmented reality and metaverse will be the future platform for connectivity for which conversation and interactional AI systems are going to be a critical component. Even today, millions of people use natural-language interfaces via in-home devices, phones, or messaging channels such as Messenger to connect with each other. We strive to create new interactional technologies that have a deep understanding of the context and deliver a personalized experience to the user that is both task-oriented and empathic. Moreover, users are in charge of driving the interaction rather than following a predefined interaction flow. The next generation of interactional AI systems will be multi-modal and pro-active, integrating cues across several modalities to provide creative and on-spot response to the users through augmented reality enabled devices.

    Assignments

    Assignments. The project and hw3 are also available. Note: do not use machine learning for hw3.

    Group Projects

    Below is a list of group projects that have been submitted and approved. If your group project does not appear, let me know. I might have missed it.

    Each of these projects will give a presentation the week of April 22nd, either Monday the 22nd or Wednesday the 24th. If you have a preference, let me know.

    Also, if you have a solo project, but would like to give a presentation, let me know.

    I do not expect the project to be completed at that time. The presentation, which should be 10 minutes or so, should explain the idea and your approach. If you have results, you may certainly share them.

    1. Rohan Acharya and Sonny Nguyen. Enhanced Option Pricing with an Advanced Binomial Tree ModeL.
    2. Tetsu Kurumisawa and Mina Bengi Aral. Risk Management System for Equity Portfolio.
    3. Aileen Siele, Daniel Metaferia, and Vimbisai Basvi. Housing Recommendation System with Explanatory Feedback.
    4. Jiayi Chen and Harper Qi. Music Recommendation System.
    5. Samuel Chen, Fiza Shakeel, and Rick Gao. Counterfactual Regret Minimization-based Indian Poker Optimization.
    6. Ron Cheng and Michelle Zheng. MiniTherapist: A customizable, rule based expert system as a therapy aid that responds in and takes input with natural language.
    7. Francisco Almeida, Max Velasco, and João Bernardo Pachêco. Portfolio Risk Assessment: Creating A Python Tool for Value at Risk Calculation and Visualization.
    8. Sherrie Feng, Sean Lim, and Noah Dee. An itinerary planning application.
    9. Reese Johnson and Milan Mardia. Image Detection System: Is the image real or AI generated?
    10. Sushant Kunwar, Jorge Torres, and Eric Lin. Emotion-Based Music Recommendation System.
    11. Ariel Melendez and Caroline Reiner. A case-based medical diagnosis assistant system.
    12. Hengguang Zhou, Haolan Zuo, and Yining Wang. Interpretable Graph-Based Stock Trading Decision System.
    13. Nawal Naz Tareque and Denny Zhang. Rule Based Entertainment Recommendation System.

    Goals

  • Goals.html See english. New!

    Truth or Consequences

    We observe that Senators and Supreme Court justices often give explanations or opinions that hide or obscure their real reasons. That is, they lie. Should a computer lie? or more realistically, When should a computer lie? We call your attention to HAL from 2001: A Space Odyssey.

    There is a new discussion topic: when should a computer lie?

    Are These 10 Lies Justified? from The New York Times, December 14, 2015. See comments as well.

    Using polleverywhere, list which of the ten lies from the NYT article you believe are justified. https://pollev.com/slade

    The Singularity

    Goal-based Systems

    See GBDMgoals.html Chapter 3: Goal Dimensions.

    See GBDMResources.html Chapter 4: Resources.

    The Realm of Decisions

    For the next class and the coming weeks: Give an example of an explanation you thought interesting because it was especially good or bad. It can be personal or from the news. Use the Discussions section of canvas (not Ed Discussion). You earn a quiz point by posting to Discussions.
  • What is a correct decision? See A Realistic Model of Rationality. This short paper provides a high-level introduction to the topics we will discuss in this course: goals, plans, resources, relationships, goal adoption, explanations, subjective decisions, emotions, advice, and persuasion. We contrast it with the standard economic decision theory. We want to develop a theory that can be implemented in a computer program.


    [Home]