Upcoming Events

December 7, 2022
3:00 p.m., Meliora 366 and Zoom (Check CVS Slack for login details)

Advancing Artificial Intelligence and Machine Perception by Studying Cognitive Science

Deep learning has been tremendously successful, but artificial intelligence (AI) still has a long way to go toward achieving the versatility of humans. My lab works toward overcoming the limitations of today’s AI systems by taking inspiration from cognitive science. I’ll briefly review some of the work from my lab on developing brain-inspired models of object recognition, before diving into the topic of lifelong learning in deep networks. After training on large amounts of data, conventional deep networks are frozen in time. Unlike humans, they cannot easily continue to learn more information. If this is attempted, they suffer from catastrophic forgetting, resulting in the loss of previously acquired skills. Taking inspiration from theories of memory consolidation in the brain, we have developed state-of-the-art AI systems for large-scale computer vision and multi-modal perception tasks that overcome catastrophic forgetting. Specifically, our work combines hippocampal indexing theory and replay mechanisms that occur during non-rapid eye movement (NREM) sleep into deep networks. I wrap up the talk by discussing future brain-inspired research directions in my lab.

Biography: Christopher Kanan is an Associate Professor of Computer Science at the University of Rochester. His research focuses on deep learning, especially lifelong machine learning, where he takes inspiration from cognitive science to make artificial neural networks capable of learning over time for large-scale vision and multi-modal perception tasks. Other recent projects cover self-supervised learning, open-world learning, and creating bias robust neural network architectures. He also works on medical applications of machine learning, especially computational pathology. Previously, he led AI R&D at the start-up Paige, leading to the first FDA approved computer vision system for helping pathologists diagnose cancer in whole slide histopathology images. Kanan received a PhD in computer science from the University of California at San Diego, where he developed machine learning algorithms to analyze eye tracking data and neural network models of active vision. Prior to joining the University of Rochester, he worked as a researcher at NASA’s Jet Propulsion Laboratory and then as a professor of Imaging Science at the Rochester Institute of Technology. He is an NSF CAREER award winner.

---

December 14, 2022
3:00 p.m., URMC 2-6408, K207 Auditorium

Tuning landscapes of the primate ventral stream

If you plan to attend via Zoom, advance webinar registration is required. Registration is free.

---

January 18, 2023
3:00 p.m., URMC 2-6408, K207 Auditorium

Retinal Connectomics and Pathoconnectomics

---

January 26, 2023
4:00 p.m., URMC 1-9576 Ryan Case Method Room

---

March 2, 2023
4:00 p.m., URMC 3-7619 Upper Auditorium

---

April 20, 2023
4:00 p.m., URMC 3-7619 Upper Auditorium

---

May 3, 2023
3:00 p.m., URMC 2-6408, K207 Auditorium

Neural dynamics of the primate attention network

---

May 17, 2023
3:00 p.m., URMC 2-6408, K207 Auditorium

Neurophysiological windows onto decision formation in the human brain

---