Filters








149 Hits in 8.4 sec

Energy-efficient stochastic computing with superparamagnetic tunnel junctions [article]

Matthew W. Daniels, Advait Madhavan, Philippe Talatchian, Alice Mizrahi, Mark D. Stiles
2019 arXiv   pre-print
One of their applications is to generate random bitstreams suitable for use in stochastic computing implementations.  ...  Superparamagnetic tunnel junctions have emerged as a competitive, realistic nanotechnology to support novel forms of stochastic computation in CMOS-compatible platforms.  ...  The correct metric for the success of our generator is that it can be used to carry out stochastic computing calculations; we show that it can in a complex neural network architecture in Sec. IV.  ... 
arXiv:1911.11204v1 fatcat:puv7zy5cqvgcxddqpyzikadg3q

Energy-efficient stochastic computing with superparamagnetic tunnel junctions

Matthew W Daniels, Advait Madhavan, Philippe Talatchian, Alice Mizrahi, Mark D Stiles
2020 Physical Review Applied  
One of their applications is to generate random bitstreams suitable for use in stochastic computing implementations.  ...  Superparamagnetic tunnel junctions (SMTJs) have emerged as a competitive, realistic nanotechnology to support novel forms of stochastic computation in CMOS-compatible platforms.  ...  Stochastic computing is concerned with encoding real-valued numbers as the expectation values of random bitstreams; for example, a bitstream such as 01001101000 has four ones and six zeros, thereby encoding  ... 
pmid:33043097 pmcid:PMC7542576 fatcat:zr2np66mjnaxlmhjruroy5mvae

A Survey of Linear Network Coding and Network Error Correction Code Constructions and Algorithms

Michele Sanna, Ebroul Izquierdo
2011 International Journal of Digital Multimedia Broadcasting  
In this paper, we review the recent breakthroughs in linear network coding for acyclic networks with a survey of code constructions literature.  ...  Linear network coding is a practical implementation of this new paradigm covered by several research works that include rate characterization, error-protection coding, and construction of codes.  ...  in delay-free networks, messages of m bits are considered as symbols in a finite field F q of size q, for example, a Galois field of size q = 2 m or a ring of polynomials of maximum degree log 2 (q)  ... 
doi:10.1155/2011/857847 fatcat:jnafbky65vfqfarj4f6yugev4u

Joint Source-Channel Decoding of Variable-Length Codes with Soft Information: A Survey

Christine Guillemot, Pierre Siohan
2005 EURASIP Journal on Advances in Signal Processing  
Efficient quality-of-service (QoS) provisioning for multimedia on these channels may in particular require a loosening and a rethinking of the layer separation principle.  ...  The problem has been largely addressed in the research community, by considering both fixed-length codes (FLC) and variable-length source codes (VLC) widely used in compression standards.  ...  Siohan was in a sabbatical leave at INRIA Rennes. The authors would like to thank Dr. Thomas Guionnet, Dr. Claudio Weidmann, and Dr.  ... 
doi:10.1155/asp.2005.906 fatcat:ssketaxbrva2dp33sba2inkoqm

Skyrmion Gas Manipulation for Probabilistic Computing

D. Pinna, F. Abreu Araujo, J.-V. Kim, V. Cros, D. Querlioz, P. Bessiere, J. Droulez, J. Grollier
2018 Physical Review Applied  
Whereas its immediate application to stochastic computing circuit designs will be made apparent, we argue that its basic functionality, reminiscent of an integrate-and-fire neuron, qualifies it as a novel  ...  This is demonstrated by modelling the ensemble dynamics in a collective coordinate approach where skyrmion-skyrmion and skyrmion-boundary interactions are accounted for phenomenologically.  ...  where computations defined over stochastic signals require correlations to be absent for proper functioning.  ... 
doi:10.1103/physrevapplied.9.064018 fatcat:cwucpswopnhypkn4syagfu4wee

CeMux: Maximizing the Accuracy of Stochastic Mux Adders and an Application to Filter Design [article]

Timothy J. Baker, John P. Hayes
2021 arXiv   pre-print
Stochastic computing (SC) is a low-cost computational paradigm that has promising applications in digital filter design, image processing and neural networks.  ...  Implementing these techniques in hardware leads to the design of CeMux (Correlation-enhanced Multiplexer), a stochastic mux adder that is significantly more accurate and uses much less area than traditional  ...  Stochastic Cross Correlation Stochastic computing elements are usually designed to operate on statistically independent or uncorrelated SNs, although some designs require correlated inputs.  ... 
arXiv:2108.12326v2 fatcat:wdragtmlojcnnb4ez6vj5ppumi

Hybrid Boolean Networks as Physically Unclonable Functions

Noeloikeau Charlot, Daniel Canaday, Andrew Pomerance, Daniel J. Gauthier
2021 IEEE Access  
The joint entropy H joint does not assume independence, but does assume that all correlations are pairwise and that no other higher-order correlations exist.  ...  For the odd-input XOR functions used in this work, the all-zero and all-one challenge strings are fixed points; this can be seen since the output of the 3-XOR is zero or one if all its inputs are zero  ... 
doi:10.1109/access.2021.3066948 fatcat:xybuhdd4ivhlnphi7diapxm3mi

Format-Compliant JPEG2000 Encryption in JPSEC: Security, Applicability, and the Impact of Compression Parameters

Dominik Engel, Thomas Stütz, Andreas Uhl
2007 EURASIP Journal on Information Security  
A proof for the reversibility of JPSEC format-compliant packet body encryption is given.  ...  In this work, a thorough analysis of this topic is presented with a focus on format-compliant packet body encryption as sketched in the FCD 15444-8 (JPSEC).  ...  quality metrics used in our assessments.  ... 
doi:10.1155/2007/94565 fatcat:pvupqtadunfxdogb27sp5yolwu

Format-Compliant JPEG2000 Encryption in JPSEC: Security, Applicability, and the Impact of Compression Parameters

Dominik Engel, Thomas Stütz, Andreas Uhl
2007 EURASIP Journal on Information Security  
A proof for the reversibility of JPSEC format-compliant packet body encryption is given.  ...  In this work, a thorough analysis of this topic is presented with a focus on format-compliant packet body encryption as sketched in the FCD 15444-8 (JPSEC).  ...  quality metrics used in our assessments.  ... 
doi:10.1186/1687-417x-2007-094565 fatcat:duvkbpyegrb2pep5o6gyxk2y2u

CMOS Impulse Radar

Hakon A. Hjortland, Dag T. Wisland, Tor Sverre Lande, Claus Limbodal, Kjetil Meisal
2006 2006 NORCHIP  
So-called Suprathreshold Stochastic Resonance (SSR) systems are studied in detail. These systems take a noisy signal as input and then 1-bit quantize it.  ...  As it turns out, the combination of noise, coarse quantization, and also integration, results in systems that, perhaps a bit unexpectedly, have quite good performance.  ...  ACKNOWLEDGMENT The authors would like to thank the startup company, Novelda AS [14], for their generous support in putting together a working impulse radar system used in our measurements.  ... 
doi:10.1109/norchp.2006.329248 fatcat:o2qc4htubfb5xp553m6avzl7uq

SC-DCNN: Highly-Scalable Deep Convolutional Neural Network using Stochastic Computing [article]

Ao Ren, Ji Li, Zhe Li, Caiwen Ding, Xuehai Qian, Qinru Qiu, Bo Yuan, Yanzhi Wang
2017 arXiv   pre-print
Stochastic Computing (SC), which uses bit-stream to represent a number within [-1, 1] by counting the number of ones in the bit-stream, has a high potential for implementing DCNNs with high scalability  ...  The tremendous savings in power (energy) and hardware resources bring about immense design space for enhancing scalability and robustness for hardware DCNNs.  ...  Acknowledgement We thank anonymous reviewers for their valuable feedback. This work is funded in part by the seedling fund of DARPA SAGA program under FA8750-17-2-0021.  ... 
arXiv:1611.05939v2 fatcat:u2fbyc4mqrcaxby7hldgpqoy6m

On the Information Rates of the Plenoptic Function

Arthur L. da Cunha, Minh N. Do, Martin Vetterli
2010 IEEE Transactions on Information Theory  
The sources of information are combined, generating a stochastic process that we study in detail. We first propose a model for ensembles of realities that do not change over time.  ...  In this paper, we propose a stochastic model to study the compression limits of a simplified version of the plenoptic function.  ...  For example, for the MSE metric we have .  ... 
doi:10.1109/tit.2009.2039168 fatcat:i66twsydengirbl37l3k6i465e

Layered video transmission over wireless multirate DS-CDMA links

L.P. Kondi, D. Srinivasan, D.A. Pados, S.N. Batalama
2005 IEEE transactions on circuits and systems for video technology (Print)  
For a given fixed energy value per chip and chip rate, the selection of a spreading code length affects the transmitted energy per bit and bit rate for each scalable layer.  ...  For the latter case, spreading codes of different lengths are allowed for each CDMA channel (multirate CDMA).  ...  The distortion due to channel errors is stochastic. Thus, the total distortion is also stochastic and we use its expected value.  ... 
doi:10.1109/tcsvt.2005.856922 fatcat:pco4axrhh5fxdj3jn72swq5xni

Predicting multiple target tracking performance for applications on video sequences

Juan E. Tapiero, Henry Medeiros, Robert H. Bishop
2017 Machine Vision and Applications  
We also introduce the concepts that present the base for estimation in general and for applications in computer vision. ii ACKNOWLEDGEMENTS Without the guidance, patience, and encouragement of countless  ...  In order to use this approach for tracker performance prediction in video sequences, a framework that combines video quality assessment concepts and the marginalized transform is introduced.  ...  bitstream-based metrics.  ... 
doi:10.1007/s00138-017-0840-8 fatcat:e3xxdfmqkrgdzngxgpelwemfzm

Monte-Carlo Simulation-Based Financial Computing on the Maxwell FPGA Parallel Machine [chapter]

Xiang Tian, Khaled Benkrid
2013 High-Performance Computing Using FPGAs  
As the Monte-Carlo method relies on the average result of thousands of independent stochastic paths, massive parallelism can be harnessed to accelerate the computation.  ...  Efficient computational solutions for scientific and engineering problems are a priority for many governments around the world, as they can offer major economic comparative advantages.  ...  For computational efficiency, most of the a s in Eq. (2) should be zero.  ... 
doi:10.1007/978-1-4614-1791-0_2 fatcat:tz34xzedmvdulkbwnwxy7numme
« Previous Showing results 1 — 15 out of 149 results