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 backpropagation algorithm, where neurons adjust synapses to minimize error, and (2) target learning algorithms, where neurons reduce the feedback required to achieve a desired activity.…

Title: Meta Continual Learning Revisited: Implicitly Enhancing Online Hessian Approximation via Variance Reduction Reading: https://openreview.net/pdf?id=TpD2aG1h0D Zoom: https://columbiauniversity.zoom.us/j/97176853843?pwd=VLZdh6yqHBcOQhdf816lkN5ByIpIsF.1

General Agenda October 21st, Day 1 from 8:45am to 5pm Breakfast and Lunch Provided Opening 3 Keynote Speakers from ARNI Faculty Research Brainstorming and Discussions Project/Student Poster Session Education and Broader Impact Discussions October 22nd, Day 2 from 9am to 1pm Breakfast and Lunch Provided 1 Keynote Speaker Brainstorming and Discussion on Collaborations & Knowledge…

Title: Unifying neural population dynamics, manifold geometry, and circuit structure. Abstract: Single neurons show complex, heterogeneous responses during cognitive tasks, often forming low-dimensional manifolds in the population state space. Consequently, it is widely accepted that neural computations arise from low-dimensional population dynamics while attributing functional properties to individual neurons is impossible. I will present recent work from…

Title: Mice wiggle a wheel to boost the salience of low visual contrast stimuli Abstract: From the Welsh tidy mouse to the New York City pizza rat, movement belies rodent intelligence. We show that head-fixed mice develop an active sensing strategy while performing a visual perceptual decision-making task (The International Brain Laboratory, 2021). Akin to humans shaking a computer mouse…

Title: Building mechanistic models of neural computations with simulation-based machine learning Abstract: Experimental techniques now make it possible to measure the structure and function of neural circuits at an unprecedented scale and resolution. How can we leverage this wealth of data to understand how neural circuits perform computations underlying behaviour? A mechanistic understanding will require models that…

Title: Do contemporary, machine-executable models (aka digital twins) of the primate ventral visual system unlock the ability to non-invasively, beneficially modulate high level brain states? Abstract: In this talk, I will first briefly review the story of how neuroscience, cognitive science and computer science (“AI”) converged to create specific, image-computable, deep neural network models intended…

Zoom Link:  https://columbiauniversity.zoom.us/j/97176853843?pwd=VLZdh6yqHBcOQhdf816lkN5ByIpIsF.1

Seminar Time: 11:30am Date: 11/8/2024 Location: JLG, L5-084  Host: Krishan Kumar   Title: Building mechanistic models of neural computations with simulation-based machine learnin

Title: Wandering Within a World A discussion on Wandering Within a World: Online Contextualized Few-Shot Learning, this 2021 paper by our very own Rich Zemel leverages contextual information in a continually changing environment to improve model performance in realistic settings. Zoom Link: https://columbiauniversity.zoom.us/j/97176853843?pwd=VLZdh6yqHBcOQhdf816lkN5ByIpIsF.1

Title: TBD Abstract: TBD

Title: Statistical mechanics of transfer learning in the proportional limit Abstract: Transfer learning (TL) is a well-established machine learning technique to boost the generalization performance on a specific (target) task using information gained from a related (source) task, and it crucially depends on the ability of a network to learn useful features. I will present…