CTN: Sebastian Seung

Zuckerman Institute - L5-084 3227 Broadway, New York, NY, United States

Title:  Insights into vision from interpreting a neuronal wiring diagram Host: Marcus Triplett Abstract:  In 2023, the FlyWire Consortium released the neuronal wiring diagram of an adult fly brain. This contains as a…

CTN: Stephanie Palmer

Zuckerman Institute - L5-084 3227 Broadway, New York, NY, United States

Title: How behavioral and evolutionary constraints sculpt early visual processing Abstract: Biological systems must selectively encode partial information about the environment, as dictated by the capacity constraints at work in all living…

Continual Learning Working Group: Kick Off

CEPSR 620 Schapiro 530 W. 120th St

Speaker: Mengye Ren Title: Lifelong and Human-like Learning in Foundation Models Abstract: Real-world agents, including humans, learn from online, lifelong experiences. However, today’s foundation models primarily acquire knowledge through offline, iid learning, while…

ARNI NSF Site Visit

Innovation Hub Tang Family Hall - 2276 12TH AVENUE – FLOOR 02

NSF Site Visit - The NSF team will evaluate the progress and achievements of ARNI’s projects to date and provide recommendations to steer future directions and funding for the project.…

CTN: Eva Dyer 

Zuckerman Institute - L5-084 3227 Broadway, New York, NY, United States

Title: Large-scale pretraining on neural data allows for transfer across individuals, tasks and species Abstract: As neuroscience datasets grow in size and complexity, integrating diverse data sources to achieve a comprehensive understanding…

Continual Learning Working Group: Haozhe Shan

CEPSR 620 Schapiro 530 W. 120th St

Speaker: Haozhe Shan Title: A theory of continual learning in deep neural networks: task relations, network architecture and learning procedure Abstract: Imagine listening to this talk and afterwards forgetting everything else…

CTN: Brenden Lake

Zuckerman Institute - L3-079 3227 Broadway, New York, NY, United States

Title: Meta-learning for more powerful behavioral modeling Abstract: Two modeling paradigms have historically been in tension: Bayesian models provide an elegant way to incorporate prior knowledge, but they make simplifying and constraining…

Continual Learning Working Group: Lindsay Smith

CEPSR 620 Schapiro 530 W. 120th St

Title: A Practitioner’s Guide to Continual Multimodal Pretraining Reading: https://arxiv.org/pdf/2408.1447 Zoom: https://columbiauniversity.zoom.us/j/97176853843?pwd=VLZdh6yqHBcOQhdf816lkN5ByIpIsF.1

CTN: Benjamin Grewe

Zuckerman Institute - L5-084 3227 Broadway, New York, NY, United States

Title: Target Learning rather than Backpropagation Explains Learning in the Mammalian Neocortex Abstract: Modern computational neuroscience presents two competing hypotheses for hierarchical learning in the neocortex: (1) deep learning-inspired approximations of the…