16-264: Humanoids
Spring 2022
Instructors: Chris Atkeson, cga@cmu.edu
and Mrinal Verghese, mverghes@andrew.cmu.edu>
Time: MW 3:05-4:20PM
Place: NSH 3002
Zoom: https://cmu.zoom.us/j/91983131204?pwd=dmNEcjRSdUdweHdqdyt0a2wwNjcvZz09
Meeting ID: 91983131204, Passcode: 079892
Units: 12
Piazza for student-student interaction
The TA office hours will be Thursdays 2-3pm on in NSH 1502C and simultaneously on Zoom at https://cmu.zoom.us/j/2417921809

Events

Thursday, February 24, 2022 4:00pm
https://pitt.zoom.us/j/93475585120
“Compositional generalization in minds and machines”
Brenden M. Lake, NYU

Abstract: People learn in fast and flexible ways that elude the best artificial neural networks. Once a person learns how to “dax,” they can effortlessly understand how to “dax twice” or “dax vigorously” thanks to their compositional skills. In this talk, we examine how people and machines generalize compositionally in language-like instruction learning tasks. Artificial neural networks have long been criticized for lacking systematic compositionality (Fodor & Pylyshyn, 1988; Marcus, 1998), but new architectures have been tackling increasingly ambitious language tasks. In light of these developments, we reevaluate these classic criticisms and find that artificial neural nets still struggle when systematic compositionality is required. We then show how people succeed in similar few-shot learning tasks and find they utilize three inductive biases that can be incorporated into models. Finally, we show how neural nets can acquire compositional skills and human-like inductive biases through meta learning.

Video of the day

Of Interest

2022: Course Format.

Assignments

Examples

The TA says: The extended deadline for homework 1 is Wednesday, February 2nd. Please have slides about your work, a demo, or something else you can show over zoom prepared. I'll also ask you to submit a version of whatever you show just for my reference. This will be submitted over Gradescope (information to come). In the meantime, if you have any questions, please submit them here. I encourage you to make them public if you are comfortable with that, as someone else may have the same question!

This is meant to be a fun assignment, so try not to stress out over it too much!

  • Assignment 2: Due Feb 23. Get a computer to learn something. Do something cool and fun. Examples of software and demos on the web:

    I googled "demo face recognition" and selected a few. Many more ...
    skybiometry.com
    Face tracker
    LearnOpenCV
    OpenCV
    OpenCV
    OpenVino: Face detection
    OpenVino: Face recognition
    Google AIY Vision
    Luxand SDK
    Amazon Rekognition
    List

    ACLU: concerns
    Defeat face recognition

    Speech recognition:
    Maybe only Dragon learns

    Neural net learning demos
    XOR demo
    Tensorflow
    A list
    2017 list
    Another list
    A list of possible projects

    Software available to you for free, that I highly recommend.
    Matlab and its neural networks toolbox
    OpenCV
    LearnOpenCV
    TensorFlow
    Pytorch

    The TA provides a way to do Assignment2 in python This is a good option if you are less familiar with machine learning, or are looking for a more structured assignment. The assignment covers learning the kinematics of a two-link arm and we have provided code to get you started. As always, you are free to work on an original project too! Send me an email or come by my office hours if you have any questions!

    Schedule

    Possible Topics

    Project

    See course format (above) and the deadlines in the schedule (above). We will work out the project topics together. You can work in groups or alone. The "deliverables" include a web page along the lines of an instructables web page explaining how others could do your project and improve on your results. You will also present your project, and ideally the presentation should be made public as part of your web page. There will be intermediate deliverables including draft web pages and practice presentations.