NeurIPS 2020 Schedule

( events) Timezone:

Workshop

Sat Dec 12 06:00 AM -- 04:30 PM (PST)

Beyond BackPropagation: Novel Ideas for Training Neural Architectures

Mateusz Malinowski · Grzegorz Swirszcz · Viorica Patraucean · Marco Gori · Yanping Huang · Sindy Löwe · Anna Choromanska

Workshop Home Page

Is backpropagation the ultimate tool on the path to achieving synthetic intelligence as its success and widespread adoption would suggest?

Many have questioned the biological plausibility of backpropagation as a learning mechanism since its discovery. The weight transport and timing problems are the most disputable. The same properties of backpropagation training also have practical consequences. For instance, backpropagation training is a global and coupled procedure that limits the amount of possible parallelism and yields high latency.

These limitations have motivated us to discuss possible alternative directions. In this workshop, we want to promote such discussions by bringing together researchers from various but related disciplines, and to discuss possible solutions from engineering, machine learning and neuroscientific perspectives.


	Live Intro (Talk)


	Introduction: Bastiaan Veeling (Introduction)


	Invited Talk Bastiaan Veeling (Talk)


	Introduction: Olivier Teytaud (Introduction)


	Invited Talk Olivier Teytaud (Talk)


	Poster Session: Morning (Parallel poster session)


	Introduction: Karl Friston (Introduction)


	Invited Talk Karl Friston (Talk)


	Panel discussion 1 (Discussion)


	Long Break (Break)


	Introduction: Yoshua Bengio (Introduction)


	Invited Talk Yoshua Bengio (Talk)


	Introduction: Danielle Bassett (Introduction)


	Invited Talk Danielle Bassett (Talk)


	Introduction: Oral 1.1 and Oral 1.2 (Introduction)


	Orals 1.1: Randomized Automatic Differentiation (Contributed Talks)


	Orals 1.2: ZORB: A Derivative-Free Backpropagation Algorithm for Neural Networks (Contributed Talks)


	Oral 1.1 and 1.2 Q&A (Q&A)


	Short Break 2 (Break)


	Introduction: Oral 2.1 and Oral 2.2 (Introduction)


	Orals 2.1: Policy Manifold Search for Improving Diversity-based Neuroevolution (Contributed Talks)


	Orals 2.2: Hardware Beyond Backpropagation: a Photonic Co-Processor for Direct Feedback Alignmen (Contributed Talks)


	Oral 2.1 and Oral 2.2 Q&A (Q&A)


	Introduction: David Duvenaud (Introduction)


	Invited Talk David Duvenaud (Talk)


	Introduction: Cristina Savin (Introduction)


	Invited Talk Cristina Savin (Talk)


	Panel discussion 2 (Discussion)


	Poster Session: Evening (Posters)