Format results
-
Lecture 4: Different Approaches to the Infinite-Width Limit
Yonatan Kahn - University of Toronto
-
Teaching Statements and Strategies
Ghazal Geshnizjani - Perimeter Institute for Theoretical Physics , Dave Fish - Perimeter Institute for Theoretical Physics , Ashley McCarl Palmer - Perimeter Institute for Theoretical Physics
-
Lecture 3: Gradient Descent Dynamics and the Neural Tangent Kernel
Yonatan Kahn - University of Toronto
-
Lecture 2: Universality Classes of Nonlinear Networks
Yonatan Kahn - University of Toronto
-
Lecture 1: Introduction: Criticality in Linear Networks
Yonatan Kahn - University of Toronto
-
-
-
The Quadratic Formula Revisited
Bernd Strumfels - Max Planck Institute for Mathematics in the Sciences
-
Neural network enhanced cross entropy benchmark for monitored circuits
Yangrui Hu - University of Waterloo
-
Recurrent neural networks for Rydberg atom arrays
Mohamed Hibat Allah - University of Waterloo
-
-
-
-
Teaching Statements and Strategies
Ghazal Geshnizjani - Perimeter Institute for Theoretical Physics , Dave Fish - Perimeter Institute for Theoretical Physics , Ashley McCarl Palmer - Perimeter Institute for Theoretical Physics
In this session, members of Perimeter’s Training and Educational Outreach teams will share resources for developing a teaching statement and introduce evidence-based strategies for effective teaching. Participants will be guided to reflect on their own teaching philosophy and will receive practical… -
Lecture 3: Gradient Descent Dynamics and the Neural Tangent Kernel
Yonatan Kahn - University of Toronto
-
-
-
The lay of the land in AI
Luis Serrano - Serrano Academy
Bio for Luis Serrano: Luis Serrano did his undergraduate and masters in math at the University of Waterloo, his PhD in algebraic combinatorics at the University of Michigan, and a postdoctoral fellowship at the University of Quebec at Montreal. He then went to industry, working in AI at Google… -
Theoretical physics at ELI ERIC
Sergey Bulanov
As part of a visit to Perimeter of a delegation from the ELI Beamlines laser facility in the Czech Republic, Dr. Bulanov will speak about potential topics for collaboration between Perimeter Institute and ELI theorists on topics related to high energy laser physics. To highlight the interplay… -
The Quadratic Formula Revisited
Bernd Strumfels - Max Planck Institute for Mathematics in the Sciences
High school students learn how to express the solution of a quadratic equation in one unknown in terms of its three coefficients. Why does this formula matter? We offer an answer in terms of discriminants and data. This lecture invites the audience to a journey towards non-linear algebra. -
Neural network enhanced cross entropy benchmark for monitored circuits
Yangrui Hu - University of Waterloo
We explore the interplay of quantum computing and machine learning to advance experimental protocols for observing measurement-induced phase transitions (MIPT) in quantum devices. In particular, we focus on trapped ion monitored circuits and apply the cross entropy benchmark recently introduced by… -
Recurrent neural networks for Rydberg atom arrays
Mohamed Hibat Allah - University of Waterloo
Rydberg atom arrays have emerged as powerful quantum simulators, capable of preparing strongly correlated phases of matter that are potentially challenging to access with classical computational methods. A major focus has been on realizing these arrays on frustrated geometries, aiming to stabilize… -
Does provable absence of barren plateaus imply classical simulability?
Zoë Holmes
A large amount of effort has recently been put into understanding the barren plateau phenomenon. In this perspective talk, we face the increasingly loud elephant in the room and ask a question that has been hinted at by many but not explicitly addressed: Can the structure that allows one to avoid… -
Doob's Lagrangian: A Sample-Efficient Variational Approach to Transition Path Sampling
Kirill Neklyudov
The 3rd talk of a monthly webinar series jointly hosted by Perimeter, IVADO, and Institut Courtois. Rare event sampling in dynamical systems is a fundamental problem arising in the natural sciences, which poses significant computational challenges due to an exponentially large space of trajectories…