skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: SNNOpt: An Application-Specific Design Framework for Spiking Neural Networks
We propose a systematic application-specific hardware design methodology for designing Spiking Neural Network (SNN), SNNOpt, which consists of three novel phases: 1) an Olliver-Ricci-Curvature (ORC)-based architecture-aware network partitioning, 2) a reinforcement learning mapping strategy, and 3) a Bayesian optimization algorithm for NoC design space exploration. Experimental results show that SNNOpt achieves a 47.45% less runtime and 58.64% energy savings over state-of-the-art approaches.  more » « less
Award ID(s):
1932620
PAR ID:
10481611
Author(s) / Creator(s):
; ; ; ; ; ; ; ;
Publisher / Repository:
IEEE
Date Published:
Journal Name:
2023 IEEE 5th International Conference on Artificial Intelligence Circuits and Systems (AICAS)
ISBN:
979-8-3503-3267-4
Page Range / eLocation ID:
1 to 5
Format(s):
Medium: X
Location:
Hangzhou, China
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; (, Journal of Computing and Information Science in Engineering)
    Abstract Manufacturing supply networks (MSNs) involve group decisions to achieve group goals and network decisions to achieve network goals. These decisions are made across multiple levels of a decision hierarchy. Resilience—the ability to maintain the satisfactory network functionality despite disruptions, is a vital network goal. When designing MSNs for resilience, the resilience and group goals often conflict, requiring simultaneous consideration of network and group decisions. Limited information in the early stages of MSN design necessitates focusing on design exploration. Hence, facilitating “co-design exploration”—a simultaneous exploration of network and group solution spaces, is crucial. Current approaches for designing MSNs for resilience do not support simultaneous consideration of network and group decisions. To bridge this gap, we present the co-design exploration of MSNs for resilience (CoDE-MR) framework to facilitate co-design exploration of the network and the groups. The CoDE-MR framework allows designers to model multilevel network and group decisions and their interactions, manage disruptions, and visualize and simultaneously explore the multilevel network and group solution spaces. In the framework, we integrate a combination of Preemptive and Archimedean formulations of the coupled-compromise decision support problem construct with resilience index metric and interpretable self-organizing map (iSOM)-based visualization to facilitate co-design exploration of MSNs for resilience. The framework's efficacy is demonstrated using a steel MSN problem, considering network and group decisions across two levels. The decision-centric framework is generic and well suited for the co-design exploration of multilevel systems to ensure resilience. 
    more » « less
  2. ; ; (, American Society of Mechanical Engineers)
    Abstract Manufacturing Supply Networks (MSNs) involve group decisions to achieve group goals and network decisions to achieve network goals. These decisions are made across multiple levels of a decision hierarchy. Given the frequent disruptions in MSNs, ‘resilience’ — the ability to maintain satisfactory network functionality despite disruptions, is a vital network goal. When designing MSNs for resilience, the resilience and group goals often conflict, requiring simultaneous consideration of network and group decisions. Limited information in the early stages of MSN design necessitates focusing on design exploration. Hence, facilitating ‘co-design exploration’ — a simultaneous exploration of network and group solution spaces is crucial. Current approaches for designing MSNs for resilience do not support simultaneous consideration of network and group decisions. To bridge this gap, we present the Co-Design Exploration of MSNs for Resilience (CoDE-MR) framework to facilitate co-design exploration of the network and the groups. CoDE-MR framework allows designers to model multilevel network and group decisions and their interactions, manage disruptions, and visualize and simultaneously explore the multilevel network and group solution spaces. In the framework, we integrate a combination of Preemptive and Archimedean formulations of the coupled-compromise Decision Support Problem construct with Resilience Index metric and interpretable Self-Organizing Map (iSOM)-based visualization to facilitate co-design exploration of MSNs for resilience. The framework’s efficacy is demonstrated using a steel MSN test problem, considering network and group decisions across two levels. The use of information flow and generic constructs makes the framework generic and well-suited for co-design exploration of multilevel systems to ensure resilience. 
    more » « less
  3. ; ; ; (, Schloss Dagstuhl – Leibniz-Zentrum für Informatik)
    Chan, Timothy; Fischer, Johannes; Iacono, John; Herman, Grzegorz (Ed.)
    We consider hypergraph network design problems where the goal is to construct a hypergraph that satisfies certain connectivity requirements. For graph network design problems where the goal is to construct a graph that satisfies certain connectivity requirements, the number of edges in every feasible solution is at most quadratic in the number of vertices. In contrast, for hypergraph network design problems, we might have feasible solutions in which the number of hyperedges is exponential in the number of vertices. This presents an additional technical challenge in hypergraph network design problems compared to graph network design problems: in order to solve the problem in polynomial time, we first need to show that there exists a feasible solution in which the number of hyperedges is polynomial in the input size. The central theme of this work is to overcome this additional technical challenge for certain hypergraph network design problems. We show that these hypergraph network design problems admit solutions in which the number of hyperedges is polynomial in the number of vertices and moreover, can be solved in strongly polynomial time. Our work improves on the previous fastest pseudo-polynomial run-time for these problems. As applications of our results, we derive the first strongly polynomial time algorithms for (i) degree-specified hypergraph connectivity augmentation using hyperedges and (ii) degree-specified hypergraph node-to-area connectivity augmentation using hyperedges. 
    more » « less
  4. ; (, Schloss Dagstuhl – Leibniz-Zentrum für Informatik)
    Chan, Timothy; Fischer, Johannes; Iacono, John; Herman, Grzegorz (Ed.)
    We consider two-cost network design models in which edges of the input graph have an associated cost and length. We build upon recent advances in hop-constrained oblivious routing to obtain two sets of results. We address multicommodity buy-at-bulk network design in the nonuniform setting. Existing poly-logarithmic approximations are based on the junction tree approach [Chekuri et al., 2010; Guy Kortsarz and Zeev Nutov, 2011]. We obtain a new polylogarithmic approximation via a natural LP relaxation. This establishes an upper bound on its integrality gap and affirmatively answers an open question raised in [Chekuri et al., 2010]. The rounding is based on recent results in hop-constrained oblivious routing [Ghaffari et al., 2021], and this technique yields a polylogarithmic approximation in more general settings such as set connectivity. Our algorithm for buy-at-bulk network design is based on an LP-based reduction to h-hop constrained network design for which we obtain LP-based bicriteria approximation algorithms. We also consider a fault-tolerant version of h-hop constrained network design where one wants to design a low-cost network to guarantee short paths between a given set of source-sink pairs even when k-1 edges can fail. This model has been considered in network design [Luis Gouveia and Markus Leitner, 2017; Gouveia et al., 2018; Arslan et al., 2020] but no approximation algorithms were known. We obtain polylogarithmic bicriteria approximation algorithms for the single-source setting for any fixed k. We build upon the single-source algorithm and the junction-tree approach to obtain an approximation algorithm for the multicommodity setting when at most one edge can fail. 
    more » « less
  5. (, Communications in computer and information science)
    Wasson, B. (Ed.)
    Visualization plays an important role in Epistemic Network Analysis (ENA), not only in graphical representation but also to facilitate interpretation and communicate research findings. However, there is no published description of the design features behind ENA network graphs. This paper provides this description from a graphic design perspective, focusing on the design principles that make ENA network graphs aesthetically pleasing and intuitive to understand. By reviewing graphic design principles and examining other extant network visualizations, we show how the current ENA network graphs highlight the most important network characteristics and facilitate sense-making. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email