Training Convolutional Neural Networks using Xilinx AI Engines

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

• Erwei Wang (Imperial College)
• Monday 27 April 2020, 16:00-17:00
• Level 9 Seminar Room, EEE Dept..

If you have a question about this talk, please contact James Davis.

In this week’s seminar, I will talk about my internship project at Xilinx. Xilinx’s new hardware platform, ACAP , features 7-nm AI Engine providing high performance, multi-precision and runtime programmable hardware solution, making it a good platform for CNN inference and training deployment. This work presents our first attempt in implementing embedded CNN training on ACAP AI Engine, showing that ACAP is indeed feasible to implement CNN training with performance comparable to state-of-the-art custom hardware.

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
• Level 9 Seminar Room, EEE Dept.

Note that ex-directory lists are not shown.