Design and Optimisation of CNN Streaming Architectures

Add to your list(s) Download to your calendar using vCal

• Alexander Montgomerie-Corcoran (Imperial College)
• Monday 24 January 2022, 16:00-17:00
• Teams (in the "CAS Seminars" team).

If you have a question about this talk, please contact George A Constantinides.

Toolflows that map Convolutional Neural Network (CNN) models to Field Programmable Gate Arrays (FPGAs) have been an important tool in accelerating a range of applications across different deployment settings. In this group, we have been developing a tool for this specific purpose, which generates high throughput CNN accelerator designs by exploring a large design space. This design space is explored through various optimisation methods. This talk will give an update on the fpgaConvNet project and discuss the design challenges associated with creating custom architectures for individual CNN models, and the different optimisation methods explored for generating the designs.

Best, Alex

This talk is part of the CAS Talks series.

This talk is included in these lists:

• Andrea Picciau's list
• CAS Talks
• Circuits and Systems Group: Internal Seminars
• Teams (in the "CAS Seminars" team)

Note that ex-directory lists are not shown.