Video Not Available
Presentations
Hardware-Efficient Softmax Approximation for Self-Attention Networks
Presented Date:Jul 08, 05:24am UTCID: 1139
A 40nm 2TOPS/W Depth-Completion Neural Network Accelerator SoC with Efficient Depth Engine for Realtime LiDAR Systems
Presented Date:Jul 08, 05:24am UTCID: 1094
Unified Accelerator for Attention and Convolution in Inference Based on FPGA
Presented Date:Jul 08, 05:24am UTCID: 1224
Edge FPGA-Based Onsite Neural Network Training
Presented Date:Jul 08, 05:24am UTCID: 1311
Energy-Efficient Stochastic Computing for Convolutional Neural Networks by Using Kernel-Wise Parallelism
Presented Date:Jul 08, 05:24am UTCID: 1466
Chairs
Chair(s)
Display Name
Naveen Kumar Macha
- Affiliation
-
AffiliationNVIDIA
- Country
Display Name
Youngjoo Lee
- Affiliation
-
AffiliationPohang University of Science and Technology
- Country