Architectural Implications of Neural Network Inference for High Data-Rate, Low-Latency Scientific Applications

no code implementations • 13 Mar 2024 • Olivia Weng, Alexander Redding, Nhan Tran, Javier Mauricio Duarte, Ryan Kastner

With more scientific fields relying on neural networks (NNs) to process data incoming at extreme throughputs and latencies, it is crucial to develop NNs with all their parameters stored on-chip.

Tailor: Altering Skip Connections for Resource-Efficient Inference

no code implementations • 18 Jan 2023 • Olivia Weng, Gabriel Marcano, Vladimir Loncar, Alireza Khodamoradi, Nojan Sheybani, Andres Meza, Farinaz Koushanfar, Kristof Denolf, Javier Mauricio Duarte, Ryan Kastner

We argue that while a network's skip connections are needed for the network to learn, they can later be removed or shortened to provide a more hardware efficient implementation with minimal to no accuracy loss.