Filters








70 Hits in 6.3 sec

Towards accurate and high-speed spiking neuromorphic systems with data quantization-aware deep networks

Fuqiang Liu, Chenchen Liu
2018 Proceedings of the 55th Annual Design Automation Conference on - DAC '18  
Spiking neuromorphic computing (SNC) has been widely investigated in deep networks implementation own to their high efficiency in computation and communication.  ...  %However, the system accuracy is limited by quantizing data directly in deep networks deployment. Previous works mainly focus on weights discretize while inter-layer signals are mainly neglected.  ...  The results indicate that the design can achieve 98.14% and 90.33% accuracy on MNIST and CIFAR10 with 4-bit data representation, which is only 0.02% and 2.72% lower than the ideal DNNs.  ... 
doi:10.1145/3195970.3196131 dblp:conf/dac/LiuL18 fatcat:q2mksrswzve2jlf3iacw3rkcty

Neuromorphic Deep Learning Machines [article]

Emre Neftci, Charles Augustine, Somnath Paul, Georgios Detorakis
2017 arXiv   pre-print
However, the workhorse of deep learning, the gradient descent Back Propagation (BP) rule, often relies on the immediate availability of network-wide information stored with high-precision memory, and precise  ...  to neural and synaptic state quantizations during learning.  ...  We thank Jun-Haeng Lee and Peter O'Connor for review and comments; and Gert Cauwenberghs, João Sacramento, Walter Senn for discussion.  ... 
arXiv:1612.05596v2 fatcat:mumivyfpxbfurg6xjsmq563pxa

Deep Learning With Spiking Neurons: Opportunities and Challenges

Michael Pfeiffer, Thomas Pfeil
2018 Frontiers in Neuroscience  
Neuromorphic hardware platforms have great potential to enable deep spiking networks in real-world applications.  ...  In this review, we address the opportunities that deep spiking networks offer and investigate in detail the challenges associated with training SNNs in a way that makes them competitive with conventional  ...  AUTHOR CONTRIBUTIONS All authors listed have made a substantial, direct and intellectual contribution to the work, and approved it for publication.  ... 
doi:10.3389/fnins.2018.00774 pmid:30410432 pmcid:PMC6209684 fatcat:flcvj3c4tvfibhn2du3y6t3jvq

Event-driven random backpropagation: Enabling neuromorphic deep learning machines

Emre Neftci, Charles Augustine, Somnath Paul, Georgios Detorakis
2017 2017 IEEE International Symposium on Circuits and Systems (ISCAS)  
However, the workhorse of deep learning, the gradient descent Back Propagation (BP) rule, often relies on the immediate availability of network-wide information stored with high-precision memory, and precise  ...  to neural and synaptic state quantizations during learning.  ...  We thank Jun-Haeng Lee and Peter O'Connor for review and comments; and Gert Cauwenberghs, João Sacramento, Walter Senn for discussion.  ... 
doi:10.1109/iscas.2017.8050529 dblp:conf/iscas/NeftciAPD17 fatcat:fqqfajaskrbhpgah7ogm2glvxi

Towards Energy-Efficient and Secure Edge AI: A Cross-Layer Framework [article]

Muhammad Shafique, Alberto Marchisio, Rachmad Vidya Wicaksana Putra, Muhammad Abdullah Hanif
2021 arXiv   pre-print
Deploying advanced Neural Networks (NN), such as deep neural networks (DNNs) and spiking neural networks (SNNs), that offer state-of-the-art results on resource-constrained edge devices is challenging  ...  The security and privacy concerns along with the amount of data that is required to be processed on regular basis has pushed processing to the edge of the computing systems.  ...  ACKNOWLEDGMENTS This work was partly supported by Intel Corporation through Gift funding for the project "Cost-Effective Dependability for Deep Neural Networks and Spiking Neural Networks".  ... 
arXiv:2109.09829v1 fatcat:rfbshpbaevgxdi4mnjskis5lty

Adaptive Extreme Edge Computing for Wearable Devices

Erika Covi, Elisa Donati, Xiangpeng Liang, David Kappel, Hadi Heidari, Melika Payvand, Wei Wang
2021 Frontiers in Neuroscience  
Due to the widespread of sensors in pervasive and distributed networks, power consumption, processing speed, and system adaptation are vital in future smart wearable devices.  ...  Wearable devices are a fast-growing technology with impact on personal healthcare for both society and economy.  ...  Thomas Mikolajick and Dr. Stefan Slesazeck for useful discussion on ferroelectric and memristive devices.  ... 
doi:10.3389/fnins.2021.611300 pmid:34045939 pmcid:PMC8144334 fatcat:5by77im5crcslgt7zj3wulzd5e

Bayesian Multi-objective Hyperparameter Optimization for Accurate, Fast, and Efficient Neural Network Accelerator Design

Maryam Parsa, John P. Mitchell, Catherine D. Schuman, Robert M. Patton, Thomas E. Potok, Kaushik Roy
2020 Frontiers in Neuroscience  
In resource-constrained environments, such as low-power edge devices and smart sensors, deploying a fast, compact, and accurate intelligent system with minimum energy is indispensable.  ...  In addition, we demonstrate resiliency of different input/output encoding, training neural network, or the underlying accelerator modules in a neuromorphic system to the changes of the hyperparameters.  ...  and spiking neuromorphic systems.  ... 
doi:10.3389/fnins.2020.00667 pmid:32848531 pmcid:PMC7396641 fatcat:jud4jgv3ejawjjtfcxeqtzza5a

2022 Roadmap on Neuromorphic Computing and Engineering [article]

Dennis V. Christensen, Regina Dittmann, Bernabé Linares-Barranco, Abu Sebastian, Manuel Le Gallo, Andrea Redaelli, Stefan Slesazeck, Thomas Mikolajick, Sabina Spiga, Stephan Menzel, Ilia Valov, Gianluca Milano (+47 others)
2022 arXiv   pre-print
built-in capabilities to learn or deal with complex data as our brain does.  ...  These needs can be addressed by neuromorphic computing systems which are inspired by the biological concepts of the human brain.  ...  This new class of extremely low-power and lowlatency artificial intelligence systems could, In a world where power-hungry deep learning techniques are becoming a commodity, and at the same time, environmental  ... 
arXiv:2105.05956v3 fatcat:pqir5infojfpvdzdwgmwdhsdi4

A Scalable Approach to Modeling on Accelerated Neuromorphic Hardware [article]

Eric Müller, Elias Arnold, Oliver Breitwieser, Milena Czierlinski, Arne Emmel, Jakob Kaiser, Christian Mauch, Sebastian Schmitt, Philipp Spilger, Raphael Stock, Yannik Stradmann, Johannes Weis (+11 others)
2022 arXiv   pre-print
Neuromorphic systems open up opportunities to enlarge the explorative space for computational research. However, it is often challenging to unite efficiency and usability.  ...  The focus lies on novel system and software features such as multi-compartmental neurons, fast re-configuration for hardware-in-the-loop training, applications for the embedded processors, the non-spiking  ...  Acknowledgments The authors wish to thank all present and former members of the Electronic Vision(s) research group contributing to the BrainScaleS-2 neuromorphic platform.  ... 
arXiv:2203.11102v1 fatcat:u5e7cdpga5hetmkap6t3tlgicm

Table of contents

2017 2017 IEEE International Symposium on Circuits and Systems (ISCAS)  
-Highly Linear Integrate-and-Fire Modulators with Soft Reset for Low-Power High-Speed ImagersO-21 -Color Temporal Contrast Sensitivity in Dynamic Vision SensorsO-22 -Real-Time Trajectory Calculation and  ...  O-5 -Live Demonstration: Multiplexing AER Asynchronous Channels Over LVDS Links with Flow-Control and Clock-Correction for Scalable Neuromorphic Systems O-6 -Live Demonstration: Dynamic Voltage and Frequency  ... 
doi:10.1109/iscas.2017.8049750 fatcat:csazlovzq5g4bmzlf7uss65sy4

Applications and Techniques for Fast Machine Learning in Science [article]

Allison McCarn Deiana, Joshua Agar, Michaela Blott, Giuseppe Di Guglielmo, Javier Duarte, Philip Harris, Scott Hauck, Mia Liu, Mark S. Neubauer, Jennifer Ngadiuba, Seda Ogrenci-Memik, Maurizio Pierini (+74 others)
2021 arXiv   pre-print
This is followed by a high-level overview and organization of technical advances, including an abundance of pointers to source material, which can enable these breakthroughs.  ...  In this community review report, we discuss applications and techniques for fast machine learning (ML) in science -- the concept of integrating power ML methods into the real-time experimental data processing  ...  Integration with the Google QKeras library [41] allows users to design aggressively quantized deep neural networks and train them quantization-aware [40] down to 1 or 2 bits for weights and activations  ... 
arXiv:2110.13041v1 fatcat:cvbo2hmfgfcuxi7abezypw2qrm

Event-based Vision: A Survey

Guillermo Gallego, Tobi Delbruck, Garrick Michael Orchard, Chiara Bartolozzi, Brian Taba, Andrea Censi, Stefan Leutenegger, Andrew Davison, Jorg Conradt, Kostas Daniilidis, Davide Scaramuzza
2020 IEEE Transactions on Pattern Analysis and Machine Intelligence  
Hence, event cameras have a large potential for robotics and computer vision in challenging scenarios for traditional cameras, such as low-latency, high speed, and high dynamic range.  ...  We also discuss the techniques developed to process events, including learning-based techniques, as well as specialized processors for these novel sensors, such as spiking neural networks.  ...  One may follow a generative approach, learning features that enable to accurately reconstruct the input, as was done in [122] with a Deep Belief Network (DBN).  ... 
doi:10.1109/tpami.2020.3008413 pmid:32750812 fatcat:vlxvlv4uynh5rpw4qlmaywqlqq

Hardware and Software Optimizations for Accelerating Deep Neural Networks: Survey of Current Trends, Challenges, and the Road Ahead

Maurizio Capra, Beatrice Bussolino, Alberto Marchisio, Guido Masera, Maurizio Martina, Muhammad Shafique
2020 IEEE Access  
This paper first introduces the key properties of two brain-inspired models like Deep Neural Network (DNN), and Spiking Neural Network (SNN), and then analyzes techniques to produce efficient and high-performance  ...  , explaining how to assess the quality of different networks and hardware systems designed for them.  ...  FIGURE 1 . 1 a) Artificial intelligence overview. b) Hardware platforms comparison [1]. the Neural Networks (NNs), including the Spiking Neural Networks (SNNs) and the Deep Learning (DL) with Deep Neural  ... 
doi:10.1109/access.2020.3039858 fatcat:nticzqgrznftrcji4krhyjxudu

Neural and Synaptic Array Transceiver: A Brain-Inspired Computing Framework for Embedded Learning [article]

Georgios Detorakis, Sadique Sheik, Charles Augustine, Somnath Paul, Bruno U. Pedroni, Nikil Dutt, Jeffrey Krichmar, Gert Cauwenberghs, Emre Neftci
2018 arXiv   pre-print
We anticipate that this contribution will establish the foundation for a new generation of devices enabling adaptive mobile systems, wearable devices, and robots with data-driven autonomy.  ...  NSAT supports event-driven supervised, unsupervised and reinforcement learning algorithms including deep learning.  ...  Acknowledgements This work was partly supported by the Intel Corporation and by the National Science Foundation under grant 1640081, and the Korean Institute of Science and Technology.  ... 
arXiv:1709.10205v3 fatcat:5vqfzqvtkfd6ph5lqzi3te2xwq

Photonic Neural Networks: a Survey

Lorenzo De Marinis, Marco Cococcioni, Piero Castoldi, Nicola Andriolli
2019 IEEE Access  
Photonic solutions are today a mature industrial reality concerning high speed, high throughput data communication and switching infrastructures.  ...  We propose a taxonomy of the existing solutions (categorized into multilayer perceptrons, convolutional neural networks, spiking neural networks, and reservoir computing) with emphasis on proof-of-concept  ...  DISCUSSIONS: THE LONG MARCH TOWARDS TRULY DEEP PNN From the presented survey, it becomes apparent that the challenge of developing truly deep neural networks with photonics is still open.  ... 
doi:10.1109/access.2019.2957245 fatcat:2ydkl3s3pnafnp23mzhjzb3iui
« Previous Showing results 1 — 15 out of 70 results