1
|
Liu Y, Liu T, Hu Y, Liao W, Xing Y, Sheik S, Qiao N. Chip-In-Loop SNN Proxy Learning: a new method for efficient training of spiking neural networks. Front Neurosci 2024; 17:1323121. [PMID: 38239830 PMCID: PMC10794440 DOI: 10.3389/fnins.2023.1323121] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/17/2023] [Accepted: 11/23/2023] [Indexed: 01/22/2024] Open
Abstract
The primary approaches used to train spiking neural networks (SNNs) involve either training artificial neural networks (ANNs) first and then transforming them into SNNs, or directly training SNNs using surrogate gradient techniques. Nevertheless, both of these methods encounter a shared challenge: they rely on frame-based methodologies, where asynchronous events are gathered into synchronous frames for computation. This strays from the authentic asynchronous, event-driven nature of SNNs, resulting in notable performance degradation when deploying the trained models on SNN simulators or hardware chips for real-time asynchronous computation. To eliminate this performance degradation, we propose a hardware-based SNN proxy learning method that is called Chip-In-Loop SNN Proxy Learning (CIL-SPL). This approach effectively eliminates the performance degradation caused by the mismatch between synchronous and asynchronous computations. To demonstrate the effectiveness of our method, we trained models using public datasets such as N-MNIST and tested them on the SNN simulator or hardware chip, comparing our results to those classical training methods.
Collapse
Affiliation(s)
| | | | - Yalun Hu
- SynSense Co. Ltd., Chengdu, China
| | - Wei Liao
- SynSense Co. Ltd., Chengdu, China
| | | | - Sadique Sheik
- SynSense Co. Ltd., Chengdu, China
- SynSense AG., Zurich, Switzerland
| | - Ning Qiao
- SynSense Co. Ltd., Chengdu, China
- SynSense AG., Zurich, Switzerland
| |
Collapse
|
2
|
Li Y, Yin R, Kim Y, Panda P. Efficient human activity recognition with spatio-temporal spiking neural networks. Front Neurosci 2023; 17:1233037. [PMID: 37781248 PMCID: PMC10536255 DOI: 10.3389/fnins.2023.1233037] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/01/2023] [Accepted: 07/25/2023] [Indexed: 10/03/2023] Open
Abstract
In this study, we explore Human Activity Recognition (HAR), a task that aims to predict individuals' daily activities utilizing time series data obtained from wearable sensors for health-related applications. Although recent research has predominantly employed end-to-end Artificial Neural Networks (ANNs) for feature extraction and classification in HAR, these approaches impose a substantial computational load on wearable devices and exhibit limitations in temporal feature extraction due to their activation functions. To address these challenges, we propose the application of Spiking Neural Networks (SNNs), an architecture inspired by the characteristics of biological neurons, to HAR tasks. SNNs accumulate input activation as presynaptic potential charges and generate a binary spike upon surpassing a predetermined threshold. This unique property facilitates spatio-temporal feature extraction and confers the advantage of low-power computation attributable to binary spikes. We conduct rigorous experiments on three distinct HAR datasets using SNNs, demonstrating that our approach attains competitive or superior performance relative to ANNs, while concurrently reducing energy consumption by up to 94%.
Collapse
Affiliation(s)
- Yuhang Li
- Department of Electrical Engineering, Yale University, New Haven, CT, United States
| | | | | | | |
Collapse
|
3
|
Hwang S, Hwang Y, Kim D, Lee J, Choe HK, Lee J, Kang H, Kung J. ReplaceNet: real-time replacement of a biological neural circuit with a hardware-assisted spiking neural network. Front Neurosci 2023; 17:1161592. [PMID: 37638314 PMCID: PMC10448768 DOI: 10.3389/fnins.2023.1161592] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/08/2023] [Accepted: 07/28/2023] [Indexed: 08/29/2023] Open
Abstract
Recent developments in artificial neural networks and their learning algorithms have enabled new research directions in computer vision, language modeling, and neuroscience. Among various neural network algorithms, spiking neural networks (SNNs) are well-suited for understanding the behavior of biological neural circuits. In this work, we propose to guide the training of a sparse SNN in order to replace a sub-region of a cultured hippocampal network with limited hardware resources. To verify our approach with a realistic experimental setup, we record spikes of cultured hippocampal neurons with a microelectrode array (in vitro). The main focus of this work is to dynamically cut unimportant synapses during SNN training on the fly so that the model can be realized on resource-constrained hardware, e.g., implantable devices. To do so, we adopt a simple STDP learning rule to easily select important synapses that impact the quality of spike timing learning. By combining the STDP rule with online supervised learning, we can precisely predict the spike pattern of the cultured network in real-time. The reduction in the model complexity, i.e., the reduced number of connections, significantly reduces the required hardware resources, which is crucial in developing an implantable chip for the treatment of neurological disorders. In addition to the new learning algorithm, we prototype a sparse SNN hardware on a small FPGA with pipelined execution and parallel computing to verify the possibility of real-time replacement. As a result, we can replace a sub-region of the biological neural circuit within 22 μs using 2.5 × fewer hardware resources, i.e., by allowing 80% sparsity in the SNN model, compared to the fully-connected SNN model. With energy-efficient algorithms and hardware, this work presents an essential step toward real-time neuroprosthetic computation.
Collapse
Affiliation(s)
- Sangwoo Hwang
- Department of Electrical Engineering and Computer Science, DGIST, Daegu, Republic of Korea
| | - Yujin Hwang
- Department of Electrical Engineering and Computer Science, DGIST, Daegu, Republic of Korea
| | - Duhee Kim
- Department of Electrical Engineering and Computer Science, DGIST, Daegu, Republic of Korea
| | - Junhee Lee
- Department of Electrical Engineering and Computer Science, DGIST, Daegu, Republic of Korea
| | - Han Kyoung Choe
- Department of Brain Sciences, DGIST, Daegu, Republic of Korea
| | - Junghyup Lee
- Department of Electrical Engineering and Computer Science, DGIST, Daegu, Republic of Korea
| | - Hongki Kang
- Department of Electrical Engineering and Computer Science, DGIST, Daegu, Republic of Korea
| | - Jaeha Kung
- School of Electrical Engineering, Korea University, Seoul, Republic of Korea
| |
Collapse
|
4
|
Yi Z, Lian J, Liu Q, Zhu H, Liang D, Liu J. Learning Rules in Spiking Neural Networks: A Survey. Neurocomputing 2023. [DOI: 10.1016/j.neucom.2023.02.026] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/18/2023]
|
5
|
Hu L, Liao X. Voltage slope guided learning in spiking neural networks. Front Neurosci 2022; 16:1012964. [PMID: 36440266 PMCID: PMC9685168 DOI: 10.3389/fnins.2022.1012964] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/06/2022] [Accepted: 10/25/2022] [Indexed: 04/19/2024] Open
Abstract
A thorny problem in machine learning is how to extract useful clues related to delayed feedback signals from the clutter of input activity, known as the temporal credit-assignment problem. The aggregate-label learning algorithms make an explicit representation of this problem by training spiking neurons to assign the aggregate feedback signal to potentially effective clues. However, earlier aggregate-label learning algorithms suffered from inefficiencies due to the large amount of computation, while recent algorithms that have solved this problem may fail to learn due to the inability to find adjustment points. Therefore, we propose a membrane voltage slope guided algorithm (VSG) to further cope with this limitation. Direct dependence on the membrane voltage when finding the key point of weight adjustment makes VSG avoid intensive calculation, but more importantly, the membrane voltage that always exists makes it impossible to lose the adjustment point. Experimental results show that the proposed algorithm can correlate delayed feedback signals with the effective clues embedded in background spiking activity, and also achieves excellent performance on real medical classification datasets and speech classification datasets. The superior performance makes it a meaningful reference for aggregate-label learning on spiking neural networks.
Collapse
Affiliation(s)
- Lvhui Hu
- School of Intelligent Medicine, Chengdu University of Traditional Chinese Medicine, Chengdu, China
| | - Xin Liao
- Information Center, Hospital of Chengdu University of Traditional Chinese Medicine, Chengdu, China
| |
Collapse
|
6
|
Yang Z, Yang Y, Li C, Zhou Y, Zhang X, Yu Y, Liu D. Tasseled Crop Rows Detection Based on Micro-Region of Interest and Logarithmic Transformation. FRONTIERS IN PLANT SCIENCE 2022; 13:916474. [PMID: 35832229 PMCID: PMC9272774 DOI: 10.3389/fpls.2022.916474] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 04/09/2022] [Accepted: 05/06/2022] [Indexed: 06/15/2023]
Abstract
Machine vision-based navigation in the maize field is significant for intelligent agriculture. Therefore, precision detection of the tasseled crop rows for navigation of agricultural machinery with an accurate and fast method remains an open question. In this article, we propose a new crop rows detection method at the tasseling stage of maize fields for agrarian machinery navigation. The whole work is achieved mainly through image augment and feature point extraction by micro-region of interest (micro-ROI). In the proposed method, we first augment the distinction between the tassels and background by the logarithmic transformation in RGB color space, and then the image is transformed to hue-saturation-value (HSV) space to extract the tassels. Second, the ROI is approximately selected and updated using the bounding box until the multiple-region of interest (multi-ROI) is determined. We further propose a feature points extraction method based on micro-ROI and the feature points are used to calculate the crop rows detection lines. Finally, the bisector of the acute angle formed by the two detection lines is used as the field navigation line. The experimental results show that the algorithm proposed has good robustness and can accurately detect crop rows. Compared with other existing methods, our method's accuracy and real-time performance have improved by about 5 and 62.3%, respectively, which can meet the accuracy and real-time requirements of agricultural vehicles' navigation in maize fields.
Collapse
Affiliation(s)
- Zhenling Yang
- School of Engineering, Anhui Agricultural University, Hefei, China
| | - Yang Yang
- School of Engineering, Anhui Agricultural University, Hefei, China
- Institute of Artificial Intelligence, Hefei Comprehensive Nation Science Center, Hefei, China
| | - Chaorong Li
- Faculty of Artificial Intelligence and Big Data, Yibin University, Yibin, China
| | - Yang Zhou
- School of Engineering, Anhui Agricultural University, Hefei, China
| | - Xiaoshuang Zhang
- School of Engineering, Anhui Agricultural University, Hefei, China
| | - Yang Yu
- School of Engineering, Anhui Agricultural University, Hefei, China
| | - Dan Liu
- JD AI Research, Beijing, China
| |
Collapse
|
7
|
A method for support neuron selection in NMLI. Neurocomputing 2022. [DOI: 10.1016/j.neucom.2022.03.030] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/20/2022]
|
8
|
Zhang A, Li X, Gao Y, Niu Y. Event-Driven Intrinsic Plasticity for Spiking Convolutional Neural Networks. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2022; 33:1986-1995. [PMID: 34106868 DOI: 10.1109/tnnls.2021.3084955] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/12/2023]
Abstract
The biologically discovered intrinsic plasticity (IP) learning rule, which changes the intrinsic excitability of an individual neuron by adaptively turning the firing threshold, has been shown to be crucial for efficient information processing. However, this learning rule needs extra time for updating operations at each step, causing extra energy consumption and reducing the computational efficiency. The event-driven or spike-based coding strategy of spiking neural networks (SNNs), i.e., neurons will only be active if driven by continuous spiking trains, employs all-or-none pulses (spikes) to transmit information, contributing to sparseness in neuron activations. In this article, we propose two event-driven IP learning rules, namely, input-driven and self-driven IP, based on basic IP learning. Input-driven means that IP updating occurs only when the neuron receives spiking inputs from its presynaptic neurons, whereas self-driven means that IP updating only occurs when the neuron generates a spike. A spiking convolutional neural network (SCNN) is developed based on the ANN2SNN conversion method, i.e., converting a well-trained rate-based artificial neural network to an SNN via directly mapping the connection weights. By comparing the computational performance of SCNNs with different IP rules on the recognition of MNIST, FashionMNIST, Cifar10, and SVHN datasets, we demonstrate that the two event-based IP rules can remarkably reduce IP updating operations, contributing to sparse computations and accelerating the recognition process. This work may give insights into the modeling of brain-inspired SNNs for low-power applications.
Collapse
|
9
|
Learning general temporal point processes based on dynamic weight generation. APPL INTELL 2022. [DOI: 10.1007/s10489-021-02590-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/27/2022]
|
10
|
Wang Y, Xu Y, Yan R, Tang H. Deep Spiking Neural Networks With Binary Weights for Object Recognition. IEEE Trans Cogn Dev Syst 2021. [DOI: 10.1109/tcds.2020.2971655] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.7] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/06/2022]
|
11
|
A memory neural system built based on spiking neural network. Neurocomputing 2021. [DOI: 10.1016/j.neucom.2021.02.044] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/18/2022]
|
12
|
Lan Y, Wang X, Wang Y. Spatio-Temporal Sequential Memory Model With Mini-Column Neural Network. Front Neurosci 2021; 15:650430. [PMID: 34121986 PMCID: PMC8195288 DOI: 10.3389/fnins.2021.650430] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/07/2021] [Accepted: 03/15/2021] [Indexed: 11/13/2022] Open
Abstract
Memory is an intricate process involving various faculties of the brain and is a central component in human cognition. However, the exact mechanism that brings about memory in our brain remains elusive and the performance of the existing memory models is not satisfactory. To overcome these problems, this paper puts forward a brain-inspired spatio-temporal sequential memory model based on spiking neural networks (SNNs). Inspired by the structure of the neocortex, the proposed model is structured by many mini-columns composed of biological spiking neurons. Each mini-column represents one memory item, and the firing of different spiking neurons in the mini-column depends on the context of the previous inputs. The Spike-Timing-Dependant Plasticity (STDP) is used to update the connections between excitatory neurons and formulates association between two memory items. In addition, the inhibitory neurons are employed to prevent incorrect prediction, which contributes to improving the retrieval accuracy. Experimental results demonstrate that the proposed model can effectively store a huge number of data and accurately retrieve them when sufficient context is provided. This work not only provides a new memory model but also suggests how memory could be formulated with excitatory/inhibitory neurons, spike-based encoding, and mini-column structure.
Collapse
Affiliation(s)
- Yawen Lan
- School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China.,School of Information Engineering, Southwest University of Science and Technology, Mianyang, China
| | - Xiaobin Wang
- School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China
| | - Yuchen Wang
- School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China
| |
Collapse
|
13
|
Liu Y, Chen W, Qu H, Mahmud SMH, Miao K. Spatial division networks for weakly supervised detection. Neural Comput Appl 2021. [DOI: 10.1007/s00521-020-05257-z] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
|
14
|
|
15
|
Zhang M, Wu J, Belatreche A, Pan Z, Xie X, Chua Y, Li G, Qu H, Li H. Supervised learning in spiking neural networks with synaptic delay-weight plasticity. Neurocomputing 2020. [DOI: 10.1016/j.neucom.2020.03.079] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/01/2023]
|
16
|
Zuo L, Chen Y, Zhang L, Chen C. A spiking neural network with probability information transmission. Neurocomputing 2020. [DOI: 10.1016/j.neucom.2020.01.109] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/30/2022]
|
17
|
Hussain I, Thounaojam DM. SpiFoG: an efficient supervised learning algorithm for the network of spiking neurons. Sci Rep 2020; 10:13122. [PMID: 32753645 PMCID: PMC7403331 DOI: 10.1038/s41598-020-70136-5] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/20/2020] [Accepted: 07/23/2020] [Indexed: 11/29/2022] Open
Abstract
There has been a lot of research on supervised learning in spiking neural network (SNN) for a couple of decades to improve computational efficiency. However, evolutionary algorithm based supervised learning for SNN has not been investigated thoroughly which is still in embryo stage. This paper introduce an efficient algorithm (SpiFoG) to train multilayer feed forward SNN in supervised manner that uses elitist floating point genetic algorithm with hybrid crossover. The evidence from neuroscience claims that the brain uses spike times with random synaptic delays for information processing. Therefore, leaky-integrate-and-fire spiking neuron is used in this research introducing random synaptic delays. The SpiFoG allows both excitatory and inhibitory neurons by allowing a mixture of positive and negative synaptic weights. In addition, random synaptic delays are also trained with synaptic weights in an efficient manner. Moreover, computational efficiency of SpiFoG was increased by reducing the total simulation time and increasing the time step since increasing time step within the total simulation time takes less iteration. The SpiFoG is benchmarked on Iris and WBC dataset drawn from the UCI machine learning repository and found better performance than state-of-the-art techniques.
Collapse
Affiliation(s)
- Irshed Hussain
- Computer Vision Laboratory, Department of Computer Science and Engineering, National Institute of Technology Silchar, Silchar, Assam, 788010, India.
| | - Dalton Meitei Thounaojam
- Computer Vision Laboratory, Department of Computer Science and Engineering, National Institute of Technology Silchar, Silchar, Assam, 788010, India
| |
Collapse
|
18
|
Wang X, Lin X, Dang X. Supervised learning in spiking neural networks: A review of algorithms and evaluations. Neural Netw 2020; 125:258-280. [PMID: 32146356 DOI: 10.1016/j.neunet.2020.02.011] [Citation(s) in RCA: 43] [Impact Index Per Article: 10.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/21/2019] [Revised: 12/15/2019] [Accepted: 02/20/2020] [Indexed: 01/08/2023]
Abstract
As a new brain-inspired computational model of the artificial neural network, a spiking neural network encodes and processes neural information through precisely timed spike trains. Spiking neural networks are composed of biologically plausible spiking neurons, which have become suitable tools for processing complex temporal or spatiotemporal information. However, because of their intricately discontinuous and implicit nonlinear mechanisms, the formulation of efficient supervised learning algorithms for spiking neural networks is difficult, and has become an important problem in this research field. This article presents a comprehensive review of supervised learning algorithms for spiking neural networks and evaluates them qualitatively and quantitatively. First, a comparison between spiking neural networks and traditional artificial neural networks is provided. The general framework and some related theories of supervised learning for spiking neural networks are then introduced. Furthermore, the state-of-the-art supervised learning algorithms in recent years are reviewed from the perspectives of applicability to spiking neural network architecture and the inherent mechanisms of supervised learning algorithms. A performance comparison of spike train learning of some representative algorithms is also made. In addition, we provide five qualitative performance evaluation criteria for supervised learning algorithms for spiking neural networks and further present a new taxonomy for supervised learning algorithms depending on these five performance evaluation criteria. Finally, some future research directions in this research field are outlined.
Collapse
Affiliation(s)
- Xiangwen Wang
- College of Computer Science and Engineering, Northwest Normal University, Lanzhou, 730070, People's Republic of China
| | - Xianghong Lin
- College of Computer Science and Engineering, Northwest Normal University, Lanzhou, 730070, People's Republic of China.
| | - Xiaochao Dang
- College of Computer Science and Engineering, Northwest Normal University, Lanzhou, 730070, People's Republic of China
| |
Collapse
|
19
|
Pan Z, Chua Y, Wu J, Zhang M, Li H, Ambikairajah E. An Efficient and Perceptually Motivated Auditory Neural Encoding and Decoding Algorithm for Spiking Neural Networks. Front Neurosci 2020; 13:1420. [PMID: 32038132 PMCID: PMC6987407 DOI: 10.3389/fnins.2019.01420] [Citation(s) in RCA: 16] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/23/2019] [Accepted: 12/16/2019] [Indexed: 12/11/2022] Open
Abstract
The auditory front-end is an integral part of a spiking neural network (SNN) when performing auditory cognitive tasks. It encodes the temporal dynamic stimulus, such as speech and audio, into an efficient, effective and reconstructable spike pattern to facilitate the subsequent processing. However, most of the auditory front-ends in current studies have not made use of recent findings in psychoacoustics and physiology concerning human listening. In this paper, we propose a neural encoding and decoding scheme that is optimized for audio processing. The neural encoding scheme, that we call Biologically plausible Auditory Encoding (BAE), emulates the functions of the perceptual components of the human auditory system, that include the cochlear filter bank, the inner hair cells, auditory masking effects from psychoacoustic models, and the spike neural encoding by the auditory nerve. We evaluate the perceptual quality of the BAE scheme using PESQ; the performance of the BAE based on sound classification and speech recognition experiments. Finally, we also built and published two spike-version of speech datasets: the Spike-TIDIGITS and the Spike-TIMIT, for researchers to use and benchmarking of future SNN research.
Collapse
Affiliation(s)
- Zihan Pan
- Department of Electrical and Computer Engineering, National University of Singapore, Singapore, Singapore
| | - Yansong Chua
- Institute for Infocomm Research, Agency for Science, Technology and Research, Singapore, Singapore
| | - Jibin Wu
- Department of Electrical and Computer Engineering, National University of Singapore, Singapore, Singapore
| | - Malu Zhang
- Department of Electrical and Computer Engineering, National University of Singapore, Singapore, Singapore
| | - Haizhou Li
- Department of Electrical and Computer Engineering, National University of Singapore, Singapore, Singapore
| | - Eliathamby Ambikairajah
- School of Electrical Engineering and Telecommunications, University of New South Wales, Sydney, NSW, Australia
| |
Collapse
|
20
|
Spiking Neural Network Based on Cusp Catastrophe Theory. FOUNDATIONS OF COMPUTING AND DECISION SCIENCES 2019. [DOI: 10.2478/fcds-2019-0014] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/20/2022] Open
Abstract
Abstract
This paper addresses the problem of effective processing using third generation neural networks. The article features two new models of spiking neurons based on the cusp catastrophe theory. The effectiveness of the models is demonstrated with an example of a network composed of three neurons solving the problem of linear inseparability of the XOR function. The proposed solutions are dedicated to hardware implementation using the Edge computing strategy. The paper presents simulation results and outlines further research direction in the field of practical applications and implementations using nanometer CMOS technologies and the current processing mode.
Collapse
|
21
|
Luo X, Qu H, Zhang Y, Chen Y. First Error-Based Supervised Learning Algorithm for Spiking Neural Networks. Front Neurosci 2019; 13:559. [PMID: 31244594 PMCID: PMC6563788 DOI: 10.3389/fnins.2019.00559] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/26/2019] [Accepted: 05/15/2019] [Indexed: 11/13/2022] Open
Abstract
Neural circuits respond to multiple sensory stimuli by firing precisely timed spikes. Inspired by this phenomenon, the spike timing-based spiking neural networks (SNNs) are proposed to process and memorize the spatiotemporal spike patterns. However, the response speed and accuracy of the existing learning algorithms of SNNs are still lacking compared to the human brain. To further improve the performance of learning precisely timed spikes, we propose a new weight updating mechanism which always adjusts the synaptic weights at the first wrong output spike time. The proposed learning algorithm can accurately adjust the synaptic weights that contribute to the membrane potential of desired and non-desired firing time. Experimental results demonstrate that the proposed algorithm shows higher accuracy, better robustness, and less computational resources compared with the remote supervised method (ReSuMe) and the spike pattern association neuron (SPAN), which are classic sequence learning algorithms. In addition, the SNN-based computational model equipped with the proposed learning method achieves better recognition results in speech recognition task compared with other bio-inspired baseline systems.
Collapse
Affiliation(s)
- Xiaoling Luo
- School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China
| | - Hong Qu
- School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China
| | - Yun Zhang
- School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China
| | - Yi Chen
- School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China
| |
Collapse
|
22
|
Li J, Lu K, Huang Z, Zhu L, Shen HT. Heterogeneous Domain Adaptation Through Progressive Alignment. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2019; 30:1381-1391. [PMID: 30281489 DOI: 10.1109/tnnls.2018.2868854] [Citation(s) in RCA: 72] [Impact Index Per Article: 14.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/08/2023]
Abstract
In real-world transfer learning tasks, especially in cross-modal applications, the source domain and the target domain often have different features and distributions, which are well known as the heterogeneous domain adaptation (HDA) problem. Yet, existing HDA methods focus on either alleviating the feature discrepancy or mitigating the distribution divergence due to the challenges of HDA. In fact, optimizing one of them can reinforce the other. In this paper, we propose a novel HDA method that can optimize both feature discrepancy and distribution divergence in a unified objective function. Specifically, we present progressive alignment, which first learns a new transferable feature space by dictionary-sharing coding, and then aligns the distribution gaps on the new space. Different from previous HDA methods that are limited to specific scenarios, our approach can handle diverse features with arbitrary dimensions. Extensive experiments on various transfer learning tasks, such as image classification, text categorization, and text-to-image recognition, verify the superiority of our method against several state-of-the-art approaches.
Collapse
|