July 19, 1994 - July 19, 2027

  • Date:11ThursdayJuly 2024

    Vision and AI

    More information
    Time
    12:15 - 13:15
    Title
    Deep Learning on a Budget
    Location
    Jacob Ziskind Building
    Room 1
    Lecturer
    Daphna Weinshall
    HUJI
    Organizer
    Department of Computer Science and Applied Mathematics
    Seminar
    Contact
    AbstractShow full text abstract about Currently, the most effective deep learning methods heavily ...»
    Currently, the most effective deep learning methods heavily rely on the availability of a large corpus of annotated data. However, such resources are not always accessible. In this seminar, I will discuss alternative paradigms that aim to make better use of both labelled and unlabelled data, drawing inspiration from certain properties of human learning. I will begin by describing our recent work on active learning, continual learning, and learning with label noise. If time permits, I will also discuss some new insights about local overfitting, which can occur even when overfitting (as traditionally defined)is not observed.

     
    Lecture