1k citations · 1.2k across the 9 of their papers we have counts for
3 papers · 1 filter
NITI: Training Integer Neural Networks Using Integer-only Arithmetic
Maolin Wang, Seyedramin Rasoulinezhad, Philip H. W. Leong +1
While integer arithmetic has been widely adopted for improved performance in deep quantized neural network inference, training remains a task primarily executed using floating poin…
LUXOR: An FPGA Logic Cell Architecture for Efficient Compressor Tree Implementations
SeyedRamin Rasoulinezhad, Siddhartha, Hao Zhou +3
We propose two tiers of modifications to FPGA logic cell architecture to deliver a variety of performance and utilization benefits with only minor area overheads. In the irst tier,…
MajorityNets: BNNs Utilising Approximate Popcount for Improved Efficiency
Seyedramin Rasoulinezhad, Sean Fox, Hao Zhou +3
Binarized neural networks (BNNs) have shown exciting potential for utilising neural networks in embedded implementations where area, energy and latency constraints are paramount. W…