Spring 2024 Computer Science 458. 4/17/2024


[Home]

Canvas Quiz of the Day (need daily password)

NOTE: today, instead of a quiz, you are asked to post a response to the following prompt on canvas Discussions.
What did you learn from today's speaker, Alborz Geramifard from Meta? What was the best question from the audience? Did you ask it?

Unlike the other Discussions, you will not be able to read the responses until you have posted. You get a point for posting. The posting window will be open at 4 pm.

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.

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

    Over zoom: https://yale.zoom.us/j/91280742192 Not recorded.

    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.

    Reminder: submit the project on the zoo using the submit process. We are NOT using gradescope for the project. You should copy your files to the zoo and then execute the following command:

    /c/cs458/submit 6 filename[s]
      
    That is, use assignment 6 for the final project.

    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, as specified.

    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.

      Monday April 22nd.
    1. Ann Zhang. Decision-making system based on TV tropes.
    2. Rohan Acharya and Sonny Nguyen. Enhanced Option Pricing with an Advanced Binomial Tree ModeL.
    3. Tetsu Kurumisawa and Mina Bengi Aral. Risk Management System for Equity Portfolio.
    4. Aileen Siele, Daniel Metaferia, and Vimbisai Basvi. Housing Recommendation System with Explanatory Feedback.
    5. Jiayi Chen and Harper Qi. Music Recommendation System.
    6. Samuel Chen, Fiza Shakeel, and Rick Gao. Counterfactual Regret Minimization-based Indian Poker Optimization.
    7. 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.
    8. Ananya Rajagopalan. An explainable machine-learning model that predicts gene expression levels from genomic variants .

      Wednesday April 24th.

    9. Sydney Scheller. 7 Wonders Game Move Recommendations .
    10. Francisco Almeida, Max Velasco, and João Bernardo Pachêco. Portfolio Risk Assessment: Creating A Python Tool for Value at Risk Calculation and Visualization.
    11. Sherrie Feng, Sean Lim, and Noah Dee. An itinerary planning application.
    12. Reese Johnson and Milan Mardia. Image Detection System: Is the image real or AI generated?
    13. Sushant Kunwar, Jorge Torres, and Eric Lin. Emotion-Based Music Recommendation System.
    14. Ariel Melendez and Caroline Reiner. A case-based medical diagnosis assistant system.
    15. Hengguang Zhou, Haolan Zuo, and Yining Wang. Interpretable Graph-Based Stock Trading Decision System.
    16. Nawal Naz Tareque and Denny Zhang. Rule Based Entertainment Recommendation System.
    17. Rudy Cordero. Automated Personal Counselor for Community College Students Exploring Further Education and Vocational Opportunities .

    Scruffy Redux

    The Kris Hammond Ted Talk video reminded me of Minsky's Society of Mind.
    What magical trick makes us intelligent? The trick is that there is no trick. The power of intelligence stems from our vast diversity, not from any single, perfect principle. —Marvin Minsky, The Society of Mind, p. 308

    [Home]