Calendar of Events
M Mon
T Tue
W Wed
T Thu
F Fri
S Sat
S Sun
1 event,
CTN: Monday Lab Kim Stachenfeld
CTN: Monday Lab Kim Stachenfeld
Title: Discovering Symbolic Cognitive Models from Human and Animal Behavior with CogFunSearch Abstract: A key goal of cognitive science is to discover mathematical models that describe how the brain implements cognitive processes. These models often take the form of short computer programs, and constructing them typically requires a great deal of human effort and ingenuity. In this…
0 events,
1 event,
ARNI Biological Learning Working Group
ARNI Biological Learning Working Group
Title: Brain-like learning with exponentiated gradients and Learning to live with Dale’s principle: ANNs with separate excitatory and inhibitory units Meeting Summary: Our focus will be on answering the following question, which may be a focus for the next few meetings: To what degree are different learning algorithms entangled with a particular neural architecture? Can…
0 events,
0 events,
0 events,
0 events,
0 events,
0 events,
1 event,
0 events,
1 event,
0 events,
0 events,
1 event,
0 events,
0 events,
0 events,
0 events,
0 events,
0 events,
0 events,
1 event,
ARNI Continual Learning Working Group Spring Opening Meeting
ARNI Continual Learning Working Group Spring Opening Meeting
From: Tom Zollo In Y2, the aim is to use this working group as a launchpad for a larger ARNI continual learning project (which we hope to spawn multiple subprojects and papers). We hope for this group to tackle issues that are relevant to both modern practitioners and the ARNI mission of connecting artificial and natural intelligence.…
0 events,
0 events,
0 events,
0 events,
0 events,
0 events,
1 event,
ARNI WG Multi-resource-cost optimization of neural network models: Paul Schrater
ARNI WG Multi-resource-cost optimization of neural network models: Paul Schrater
Title: Control when confidence is costly Abstract: We develop a version of stochastic control that accounts for computational costs of inference. Past studies identified efficient coding without control, or efficient control that neglects the cost of synthesizing information. Here we combine these concepts into a framework where agents rationally approximate inference for efficient control. Specifically,…
1 event,
ARNI Biological Learning Working Group
ARNI Biological Learning Working Group
Ken Miller will be talking about E/I networks & balanced networks and some computational/functional implications, there’s two papers I’d suggest reading:on balanced amplification: https://www.sciencedirect.com/science/article/pii/S0896627309001287 review of loosely and tightly balanced networks: https://www.sciencedirect.com/science/article/pii/S0896627321005754. Meeting Link: meet.google.com/nnq-csiy-yah
2 events,
ARNI Continual Learning Project
ARNI Continual Learning Project
Followup to discussion in Meeting 1 Zoom Link: https://columbiauniversity.zoom.us/j/97176853843?pwd=VLZdh6yqHBcOQhdf816lkN5ByIpIsF.1
ARNI Frontier Models for Neuroscience and Behavior Working Group (Priorly: Animal Behavior)
ARNI Frontier Models for Neuroscience and Behavior Working Group (Priorly: Animal Behavior)
Description: Advances in neurotechnology and behavioral tracking have enabled the collection of large-scale neural and behavioral datasets, offering new opportunities to study brain function in complex settings. However, researchers face significant challenges in integrating and analyzing data across different brain regions, individuals, and behavioral contexts. Inspired by recent successes in large-scale “foundation” models in natural language…
1 event,
ARNI Distinguished Seminar Series: Marlene Behrmann
ARNI Distinguished Seminar Series: Marlene Behrmann
About Dr. Marlene Behrmann: Marlene Behrmann joined the Department of Ophthalmology at the University of Pittsburgh School of Medicine, where she holds the John and Clelia Sheppard Chair, in 2022. She also holds the position of Emeritus Professor at Carnegie Mellon University. Dr. Behrmann’s research is concerned with the psychological and neural bases of visual…