News

February 2023: We are thankful to all the participants for their thoughtful questions and remarks. As a remark, you can find various implementations in PyTorch, Keras, TensorFlow and JAX in this site shared during the tutorial.

December 2022: The site of the previous version of the tutorial (along with the respective material) can be found in this link.

Overview

Polynomial networks enable a new network design that treats a network as a high-degree polynomial expansion of the input. Recently, polynomial networks have demonstrated state-of-the-art performance in a range of tasks. Despite the fact that polynomial networks have appeared for several decades in machine learning and complex systems, they are not widely acknowledged for their role in modern deep learning.

In this tutorial we intend to bridge the gap and draw parallelisms between modern deep learning approaches and polynomial networks. To this end, we will share recent developments on the topic, as well as explain the required tools.

Schedule Detail

Tentative schedule.

  • 8.30 AM

    Introduction

  • 9.10 AM

    High-degree polynomial expansions

  • 10.30 AM

    Break

  • 10.50 AM

    Recognition and generation with polynomial nets

  • 11.50 AM

    Coding exampls with Jupyter notebooks

VENUE

AAAI 2023, Washington, DC, USA

Walter E. Washington Convention Center, Mount Vernon Place Northwest

FAQ

Following the guidelines of AAAI, this tutorial will take place on 7th February. You should register for the AAAI conference.
Please reach out at grigorios.chrysos [at] epfl [dot] ch.

Organizers

organizer img

Markos Georgopoulos

Imperial College London

organizer img

Razvan Pascanu

Deepmind