Proceedings of the 52nd Annual Design Automation Conference 2015
DOI: 10.1145/2744769.2744795
|View full text |Cite
|
Sign up to set email alerts
|

An EDA framework for large scale hybrid neuromorphic computing systems

Abstract: In implementations of neuromorphic computing systems (NCS), memristor and its crossbar topology have been widely used to realize fully connected neural networks. However, many neural networks utilized in real applications often have a sparse connectivity, which is hard to be efficiently mapped to a crossbar structure. Moreover, the scale of the neural networks is normally much larger than that can be offered by the latest integration technology of memristor crossbars. In this work, we propose AutoNCS -an EDA f… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
18
0

Year Published

2016
2016
2020
2020

Publication Types

Select...
5
5

Relationship

2
8

Authors

Journals

citations
Cited by 37 publications
(18 citation statements)
references
References 18 publications
0
18
0
Order By: Relevance
“…Network 1 is a MLP network with a size of 784 × 500 × 300 × 10, which can't be directly implemented in NCS. Previously, we presented the hardware implementation of mapping a large network to small crossbar arrays [13]. Here, 784 corresponds to the 28×28 MNIST image input pattern; 500 and 300 are the neuron numbers of the first and second hidden layers, respectively; and 10 is the final classification outputs.…”
Section: B Function Validation Of Mlp On Mnistmentioning
confidence: 99%
“…Network 1 is a MLP network with a size of 784 × 500 × 300 × 10, which can't be directly implemented in NCS. Previously, we presented the hardware implementation of mapping a large network to small crossbar arrays [13]. Here, 784 corresponds to the 28×28 MNIST image input pattern; 500 and 300 are the neuron numbers of the first and second hidden layers, respectively; and 10 is the final classification outputs.…”
Section: B Function Validation Of Mlp On Mnistmentioning
confidence: 99%
“…High speed serial interfaces have been presented in the work by Jablonski et al [133] for bit-serial SATA AER inter-FPGA communication. A neuromorphic system for Electronic Design Automation (EDA) called the AutoNCS has been presented by Wen et al [134]. A mixed-signal design for a neuromorphic analog-to-digital converter has been presented by Xu et al [135].…”
Section: Other Applicationsmentioning
confidence: 99%
“…Many recent works demonstrate mapping of SNNs to a single crossbar [10]- [15]. In Section V we show how these techniques can be inefficient when applied to a multi-crossbar neuromorphic platform such as the DynapSE.…”
Section: Introductionmentioning
confidence: 99%