Computing with Time: From Neural Networks to Sensor Networks

This article advocates a new computing paradigm, called computing with time, that is capable of efficiently performing a certain class of computation, namely, searching in parallel for the closest value to the given parameter. It shares some features with the idea of computing with action potentials proposed by Hopfield, which originated in the field of artificial neuron networks. The basic idea of computing with time is captured in a novel distributed algorithm based on broadcast communication called the lecture hall algorithm, which can compute the minimum among n positive numbers, each residing on a separate processor, using only O(1) broadcasts. When applied to sensor networks, the lecture hall algorithm leads to an interesting routing protocol having several desirable properties.

[1]  Pramod K. Varshney,et al.  A state-free data delivery protocol for multihop wireless sensor networks , 2005, IEEE Wireless Communications and Networking Conference, 2005.

[2]  Wulfram Gerstner,et al.  Spiking Neuron Models , 2002 .

[3]  S. Thorpe,et al.  Speed of processing in the human visual system , 1996, Nature.

[4]  J J Hopfield,et al.  Transforming neural computations and representing time. , 1996, Proceedings of the National Academy of Sciences of the United States of America.

[5]  Roman Bek,et al.  Discourse on one way in which a quantum-mechanics language on the classical logical base can be built up , 1978, Kybernetika.

[6]  Jianliang Xu,et al.  PSGR: priority-based stateless geo-routing in wireless sensor networks , 2005, IEEE International Conference on Mobile Adhoc and Sensor Systems Conference, 2005..

[7]  Boleslaw K. Szymanski,et al.  Self-healing routing: a study in efficiency and resiliency of data delivery in wireless sensor networks , 2007, SPIE Defense + Commercial Sensing.

[8]  Michele Zorzi,et al.  Geographic Random Forwarding (GeRaF) for Ad Hoc and Sensor Networks: Multihop Performance , 2003, IEEE Trans. Mob. Comput..

[9]  Charles E. Perkins,et al.  Highly dynamic Destination-Sequenced Distance-Vector routing (DSDV) for mobile computers , 1994, SIGCOMM.

[10]  Torsten Braun,et al.  BLR: beacon-less routing algorithm for mobile ad hoc networks , 2004, Comput. Commun..

[11]  Erol Gelenbe,et al.  Power-aware ad hoc cognitive packet networks , 2004, Ad Hoc Networks.

[12]  David A. Maltz,et al.  DSR: the dynamic source routing protocol for multihop wireless ad hoc networks , 2001 .

[13]  Deborah Estrin,et al.  Directed diffusion: a scalable and robust communication paradigm for sensor networks , 2000, MobiCom '00.

[14]  Boleslaw K. Szymanski,et al.  A Self-selection Technique for Flooding and Routing in Wireless Ad-hoc Networks , 2006, Journal of Network and Systems Management.

[15]  K. P. Unnikrishnan,et al.  Speaker-Independent Digit Recognition Using a Neural Network with Time-Delayed Connections , 1992, Neural Computation.

[16]  J. J. Hopfield,et al.  Pattern recognition computation using action potential timing for stimulus representation , 1995, Nature.

[17]  Carlos D. Brody,et al.  Computing with Action Potentials , 1997, NIPS.

[18]  Sang Hyuk Son,et al.  IGF: A robust state-free communication protocol for sensor networks , 2003 .

[19]  Boleslaw K. Szymanski,et al.  Local leader election, signal strength aware flooding, and routeless routing , 2005, 19th IEEE International Parallel and Distributed Processing Symposium.

[20]  Theodore S. Rappaport,et al.  Wireless communications - principles and practice , 1996 .

[21]  Christopher J. Bishop,et al.  Pulsed Neural Networks , 1998 .

[22]  S. Thorpe,et al.  The Time Course of Visual Processing: From Early Perception to Decision-Making , 2001, Journal of Cognitive Neuroscience.

[23]  C. Malsburg.  Self-organization of orientation sensitive cells in the striate cortex , 2004, Kybernetik.

[24]  S. Grossberg,et al.  Adaptive pattern classification and universal recoding: I. Parallel development and coding of neural feature detectors , 1976, Biological Cybernetics.

[25]  Songwu Lu,et al.  GRAdient Broadcast: A Robust Data Delivery Protocol for Large Scale Sensor Networks , 2005, Wirel. Networks.

[26]  David E. Culler,et al.  Taming the underlying challenges of reliable multihop routing in sensor networks , 2003, SenSys '03.

[27]  David Zipser,et al.  Feature Discovery by Competive Learning , 1986, Cogn. Sci..

[28]  Charles E. Perkins,et al.  Ad-hoc on-demand distance vector routing , 1999, Proceedings WMCSA'99. Second IEEE Workshop on Mobile Computing Systems and Applications.

[29]  R VanRullen,et al.  Is it a Bird? Is it a Plane? Ultra-Rapid Visual Categorisation of Natural and Artifactual Objects , 2001, Perception.

[30]  William Bialek,et al.  Reading a Neural Code , 1991, NIPS.