Search Results - "Erdeljan, Andrea"
-
1
CoNNa–Hardware accelerator for compressed convolutional neural networks
Published in Microprocessors and microsystems (01-03-2020)“…In this paper, we propose a novel Convolutional Neural Network hardware accelerator called CoNNA, capable of accelerating pruned, quantized CNNs. In contrast…”
Get full text
Journal Article -
2
IP core for efficient zero-run length compression of CNN feature maps
Published in Telfor Journal (2018)“…Convolutional Neural Networks (CNNs) are becoming a fundamental tool for machine learning. High performance and energy efficiency are of great importance for…”
Get full text
Journal Article -
3
CoNNA - Compressed CNN Hardware Accelerator
Published in 2018 21st Euromicro Conference on Digital System Design (DSD) (01-08-2018)“…In this paper we propose a novel Convolutional Neural Network hardware accelerator, called CoNNA, capable of accelerating pruned, quantized, CNNs. In contrast…”
Get full text
Conference Proceeding -
4
IP core for efficient zero-run length compression of CNN feature maps
Published in 2017 25th Telecommunication Forum (TELFOR) (01-11-2017)“…Convolutional Neural Networks (CNNs) are becoming a fundamental tool for machine learning. High performance and energy efficiency are of great importance for…”
Get full text
Conference Proceeding -
5
Reducing off-chip memory traffic in deep CNNs using stick buffer cache
Published in 2017 25th Telecommunication Forum (TELFOR) (01-11-2017)“…Recent studies show that traffic between the Convolutional Neural Network (CNN) accelerators and off-chip memory becomes critical with respect to the energy…”
Get full text
Conference Proceeding