CNS'2020 Workshop: Machine learning and mechanistic modeling for understanding brain in health and disease

Crowdcast: https://www.crowdcast.io/e/cns2020-w9/register?session=1

(requires advance registration for CNS*2020 meeting at https://www.cnsorg.org/cns-2020)

Details: https://sites.google.com/view/cns-ml-msm-workshop-2020/

Speakers: Thomas Serre, Haroon Anwar, William W. Lytton, Sam Neymotin, Kenji Doya, Daniel
Durstewitz, Gunnar Cedersund, Danilo Bzdok, Idan Segev, Terrence Sejnowski

Schedule: JULY 22 • WEDNESDAY (all times US Eastern)

10:30am – 10:45am  W W9 S1 - Machine learning and mechanistic modeling for understanding brain in health and disease
Speakers: William W. Lytton, Sam Neymotin

10:45am – 11:15am  W W9 S2 - Using reinforcement learning to train biophysically detailed models of visual-motor cortex to play Atari games
Speakers: Haroon Anwar, Sam Neymotin

11:15am – 11:45am  W W9 S3 - Multi-level modelling of the brain: from intracellular signaling and neurovascular coupling to whole-body cross-talk and clinical implementations
Speakers: Gunnar Cedersund

11:45am – 12:15pm  W W9 S4 -Algorithmic Analytics Towards Precision Psychiatry
Speakers: Danilo Bzdok

12:15pm – 12:45pm  W W9 S5 - Inferring nonlinear dynamical systems from multi-modal psychiatric data by statistical deep learning
Speakers: Daniel Durstewitz

LUNCH

2:45pm – 3:15pm  W W9 S7 - From models of neural circuits to deep learning: A multi-scale approach to understanding the function of the visual tilt illusion
Speakers: Thomas Serre

3:15pm – 3:45pm  W W9 S8 - Strong inhibition and stable temporal dynamics in spiking networks sustain working memory
Speakers: Terrence Sejnowski

3:45pm – 4:15pm  W W9 S9 - Toward multi-scale brain data assimilation
Speakers: Kenji Doya
Authors: Carlos Gutierrez, Ken Nakae, Hiromichi Tsukada

4:15pm – 5:15pm W W9 S10 - Workshop Discussion

Brief Description:

Breakthrough technology developments in semi-automated, high-throughput data collection have enabled experimental neuroscientists to acquire more multiscale neural data than ever before. However, the neural origin of the patterns observed in the multiscale, multimodal datasets are often difficult to decipher. There is therefore a critical need for time- and cost-efficient approaches to analyze and interpret the massive datasets to advance understanding of cellular and circuit-level origins of the observed neural dynamics in both health and disease, and to use the insights gained to develop new therapeutics. While machine learning is a powerful technique to integrate multimodal data, classical machine learning techniques often ignore the fundamental laws of physics and may therefore result in non-physical solutions. Multiscale modeling is a successful strategy to integrate multiscale, multiphysics data and unravel mechanisms that explain the emergence of function. However, multiscale modeling alone often fails to efficiently combine large data sets from different sources and different levels of resolution. This workshop aims to highlight research that bridges the disciplines of machine learning and multiscale modeling. Speakers are invited to address open questions, and discuss potential challenges and limitations in several topical areas: differential equations, data-driven approaches, and theory-driven approaches. This multidisciplinary perspective suggests that integrating machine learning and multiscale modeling can provide new insight into disease mechanisms, help identify new targets or treatment strategies, and inform decision making in the benefit of human health.

Meeting Date
Meeting Location
Online
Table sorting checkbox
Off