Deep learning in spiking neural networks
Amirhossein Tavanaei,Masoud Ghodrati,Saeed Reza Kheradpisheh,Timothée Masquelier,Anthony S. Maida +4 more
TLDR
The emerging picture is that SNNs still lag behind ANNs in terms of accuracy, but the gap is decreasing, and can even vanish on some tasks, while SNN's typically require many fewer operations and are the better candidates to process spatio-temporal data.About:
This article is published in Neural Networks.The article was published on 2019-03-01 and is currently open access. It has received 756 citations till now. The article focuses on the topics: Spiking neural network & Artificial neural network.read more
Citations
More filters
Journal ArticleDOI
Surrogate Gradient Learning in Spiking Neural Networks: Bringing the Power of Gradient-based optimization to spiking neural networks
TL;DR: This article elucidates step-by-step the problems typically encountered when training SNNs and guides the reader through the key concepts of synaptic plasticity and data-driven learning in the spiking setting as well as introducing surrogate gradient methods, specifically, as a particularly flexible and efficient method to overcome the aforementioned challenges.
Journal ArticleDOI
Resistive switching materials for information processing
Zhongrui Wang,Huaqiang Wu,Geoffrey W. Burr,Cheol Seong Hwang,Kang L. Wang,Qiangfei Xia,Jianhua Yang +6 more
TL;DR: This Review surveys the four physical mechanisms that lead to resistive switching materials enable novel, in-memory information processing, which may resolve the von Neumann bottleneck and examines the device requirements for systems based on RSMs.
Journal ArticleDOI
Deep Learning With Spiking Neurons: Opportunities and Challenges.
Michael Pfeiffer,Thomas Pfeil +1 more
TL;DR: This review addresses the opportunities that deep spiking networks offer and investigates in detail the challenges associated with training SNNs in a way that makes them competitive with conventional deep learning, but simultaneously allows for efficient mapping to hardware.
Journal ArticleDOI
Bridging Biological and Artificial Neural Networks with Emerging Neuromorphic Devices: Fundamentals, Progress, and Challenges.
Jianshi Tang,Fang Yuan,Xinke Shen,Zhongrui Wang,Mingyi Rao,Yuanyuan He,Yuhao Sun,Xinyi Li,Wenbin Zhang,Yijun Li,Bin Gao,He Qian,Guo-Qiang Bi,Sen Song,Jianhua Yang,Huaqiang Wu +15 more
TL;DR: A systematic overview of biological and artificial neural systems is given, along with their related critical mechanisms, and the existing challenges are highlighted to hopefully shed light on future research directions.
Journal ArticleDOI
EEG based multi-class seizure type classification using convolutional neural network and transfer learning
Shivarudhrappa Raghu,Shivarudhrappa Raghu,Natarajan Sriraam,Yasin Temel,Shyam Vasudeva Rao,Pieter L. Kubben +5 more
TL;DR: It can be concluded that the EEG based classification of seizure type using CNN model could be used in pre-surgical evaluation for treating patients with epilepsy.
References
More filters
Hierarchical Models of the Visual System.
TL;DR: Convolutional networks are closely related connectionist networks with a similar architecture that have been used in multiple real-world machine learning problems including speech and music classification.
Proceedings Article
Variational Learning for Recurrent Spiking Networks
TL;DR: A plausible learning rule for feedforward, feedback and lateral connections in a recurrent network of spiking neurons is derived in the context of a generative model for distributions of spike sequences, derived from variational inference principles.
Book ChapterDOI
The spike response model: a framework to predict neuronal spike trains
TL;DR: It is found that the Spike Response Model achieves prediction of up to 80% of the spikes with correct timing (±2ms) and other characteristics of activity, such as mean rate and coefficient of variation of spike trains, are predicted in the correct range as well.
Posted Content
STDP as presynaptic activity times rate of change of postsynaptic activity
TL;DR: A weight update formula is introduced that is expressed only in terms of firing rates and their derivatives and that results in changes consistent with those associated with spike-timing dependent plasticity (STDP) rules and biological observations, even though the explicit timing of spikes is not needed.
Journal ArticleDOI
Millisecond-Scale Motor Encoding in a Cortical Vocal Area
TL;DR: Analyzing brain activity in songbirds suggests that the nervous system controls behavior by precisely modulating the timing pattern of electrical events.
Related Papers (5)
Loihi: A Neuromorphic Manycore Processor with On-Chip Learning
Michael Davies,Narayan Srinivasa,Tsung-Han Lin,Gautham N. Chinya,Cao Yongqiang,Sri Harsha Choday,Georgios D. Dimou,Prasad Joshi,Nabil Imam,Shweta Jain,Yuyun Liao,Chit-Kwan Lin,Andrew Lines,Ruokun Liu,Deepak A. Mathaikutty,Steven McCoy,Arnab Paul,Jonathan Tse,Guruguhanathan Venkataramanan,Yi-Hsin Weng,Andreas Wild,Yoon Seok Yang,Hong Wang +22 more
Training Deep Spiking Neural Networks Using Backpropagation.
A million spiking-neuron integrated circuit with a scalable communication network and interface
Paul A. Merolla,John V. Arthur,Rodrigo Alvarez-Icaza,Andrew S. Cassidy,Jun Sawada,Filipp Akopyan,Bryan L. Jackson,Nabil Imam,Chen Guo,Yutaka Nakamura,Bernard Brezzo,Ivan Vo,Steven K. Esser,Rathinakumar Appuswamy,Brian Taba,Arnon Amir,Myron D. Flickner,William P. Risk,Rajit Manohar,Dharmendra S. Modha +19 more