4 citations · 4 across the 4 of their papers we have counts for
14 papers
Transferable Learning on Analog Hardware
Sri Krishna Vadlamani, Dirk Englund, Ryan Hamerly
While analog neural network (NN) accelerators promise massive energy and time savings, an important challenge is to make them robust to static fabrication error. Present-day traini…
A Self-Similar Sine-Cosine Fractal Architecture for Multiport Interferometers
Jasvith Raj Basani, Sri Krishna Vadlamani, Saumil Bandyopadhyay +2
Multiport interferometers based on integrated beamsplitter meshes have recently captured interest as a platform for many emerging technologies. In this paper, we present a novel ar…
Hardware error correction for programmable photonics
Saumil Bandyopadhyay, Ryan Hamerly, Dirk Englund
Programmable photonic circuits of reconfigurable interferometers can be used to implement arbitrary operations on optical modes, facilitating a flexible platform for accelerating t…
Scaling advantage of nonrelaxational dynamics for high-performance combinatorial optimization
Timothee Leleu, Farad Khoyratee, Timothee Levi +3
The development of physical simulators, called Ising machines, that sample from low energy states of the Ising Hamiltonian has the potential to drastically transform our ability to…
Freely scalable and reconfigurable optical hardware for deep learning
Liane Bernstein, Alexander Sludds, Ryan Hamerly +3
As deep neural network (DNN) models grow ever-larger, they can achieve higher accuracy and solve more complex problems. This trend has been enabled by an increase in available comp…
Fundamental thermal noise limits for optical microcavities
Christopher Panuski, Dirk Englund, Ryan Hamerly
We present a joint theoretical and experimental characterization of thermo-refractive noise in high quality factor (), small mode volume () optical microcavities. Analogous t…