1 citations · 1 across the 2 of their papers we have counts for
4 papers
Unifying Physical Backpropagation
Cyrill Bösch, Yigithan Gediz, Hakan Türeci
Physical computing systems exploit device dynamics for computation, but their gradient-based optimization is challenging: backpropagation through a digital twin suffers from model-…
Local Learning Rules for Out-of-Equilibrium Physical Generative Models
Cyrill Bösch, Geoffrey Roeder, Marc Serra-Garcia +1
We show that the out-of-equilibrium driving protocol of score-based generative models (SGMs) can be learned via local learning rules. The gradient with respect to the parameters of…
Nonlinear Computation with Linear Optics via Source-Position Encoding
N. Richardson, C. Bosch, R. P. Adams
Optical computing systems provide an alternate hardware model which appears to be aligned with the demands of neural network workloads. However, the challenge of implementing energ…
Adjoint computation of Berry phase gradients
Cyrill Bösch, Marc Serra-Garcia, Christian Böhm +1
Berry phases offer a geometric perspective on wave propagation and are key to designing materials with topological wave transport. However, controlling Berry phases is challenging…