The quest for how the brain learns


Tuesday, March 21, 2023
11:00 am – 12:00 pm PT
Herklotz Conference Center*
Pierre Baldi, Ph.D.
Distinguished Professor
Donald Bren School of Information and Computer Science
Register for Colloquium


Event Description

We will first showcase two cutting-edge applications of modern Artificial Intelligence (AI) in biomedical imaging and in reasoning. These applications, as well as most modern AI applications (e.g., ChatGPT, AlphaFold, AlphaGO, Google Translate, Self-Driving Cars) are based on deep learning, a modern rebranding of neural networks, or connectionist methods, dating back to the 1980s, or even the 1950s. We will then briefly review the neuroscience-inspired, tortuous, historical path that has led to deep learning, and the key discoveries made along the way, highlighting the synergies and discrepancies between neuroscience and deep learning. One key conclusion is that approximate gradient descent is essential for learning. However, the standard gradient descent algorithm of deep learning called backpropagation is not biologically-plausible for multiple reasons. We will examine these reasons one-by-one and identify biologically-plausible solutions for each one of them. In particular, we will introduce and demonstrate a general class of neural architectures and learning algorithms capable of learning from data in a largely unsupervised and asynchronous manner, without the need for symmetric connectivity.


About the CNLM Colloquium Series

The CNLM Colloquium Series showcases the latest in learning and memory research. This year, the series will feature the CNLM Faculty Fellows at UCI. Each talk will be held in person at the Herklotz Conference Facility in the CNLM and broadcast widely via Zoom to reach our colleagues around the world. Zoom link will be emailed the morning of the event.

Find out more about the series by visiting:



Share With Your Lab and Colleagues

Registration for the CNLM Colloquium Series is open to researchers from the broader learning and memory scientific community.

If you received this email as a forward and would like to stay up-to-date on upcoming CNLM events, please sign up below.


For questions or meeting requests, please contact
Diana Lofflin at*The Dale Melbourne Herklotz Conference Center is located at the Center for the Neurobiology of Learning and Memory (building 506 on the campus map). This event will be broadcast widely via Zoom to reach our colleagues around the world.