Spike timing-based unsupervised learning of orientation, disparity, and motion representations in a spiking neural network

Recent neuroscience research results show that the nerve information in the brain is not only encoded by the spatial information. Spiking neural network based on pulse frequency coding plays a very important role in dealing with the problem of brain signal, especially complicated space-time information. In this paper, an unsupervised learning algorithm for bilayer feedforward spiking neural networks based on spike-timing dependent plasticity (STDP) competitiveness is proposed and applied to SAR image classification on MSTAR for the first time. The SNN learns autonomously from the input value without any labeled signal and the overall classification accuracy of SAR targets reached 80.8%. The experimental results show that the algorithm adopts the synaptic neurons and network structure with stronger biological rationality, and has the ability to classify targets on SAR image. Meanwhile, the feature map extraction ability of neurons is visualized by the generative property of SNN, which is a beneficial attempt to apply the brain-like neural network into SAR image interpretation.

Download Full-text

Improving Robustness of ReRAM-based Spiking Neural Network Accelerator with Stochastic Spike-timing-dependent-plasticity

2019 International Joint Conference on Neural Networks (IJCNN) ◽

10.1109/ijcnn.2019.8851825 ◽

2019 ◽

Cited By ~ 4

Author(s):

Xueyuan She ◽

Yun Long ◽

Saibal Mukhopadhyay

Keyword(s):

Neural Network ◽

Spike Timing ◽

Spiking Neural Network ◽

Spike Timing Dependent Plasticity ◽

Dependent Plasticity

Download Full-text

A Heterogeneous Spiking Neural Network for Unsupervised Learning of Spatiotemporal Patterns

Frontiers in Neuroscience ◽

10.3389/fnins.2020.615756 ◽

2021 ◽

Vol 14 ◽

Author(s):

Xueyuan She ◽

Saurabh Dash ◽

Daehyun Kim ◽

Saibal Mukhopadhyay

Keyword(s):

Neural Network ◽

Moving Objects ◽

Short Term Memory ◽

Back Propagation ◽

Spike Timing ◽

Spatiotemporal Patterns ◽

Spiking Neural Network ◽

Spatial And Temporal Patterns ◽

Unsupervised Training ◽

Improved Performance

This paper introduces a heterogeneous spiking neural network (H-SNN) as a novel, feedforward SNN structure capable of learning complex spatiotemporal patterns with spike-timing-dependent plasticity (STDP) based unsupervised training. Within H-SNN, hierarchical spatial and temporal patterns are constructed with convolution connections and memory pathways containing spiking neurons with different dynamics. We demonstrate analytically the formation of long and short term memory in H-SNN and distinct response functions of memory pathways. In simulation, the network is tested on visual input of moving objects to simultaneously predict for object class and motion dynamics. Results show that H-SNN achieves prediction accuracy on similar or higher level than supervised deep neural networks (DNN). Compared to SNN trained with back-propagation, H-SNN effectively utilizes STDP to learn spatiotemporal patterns that have better generalizability to unknown motion and/or object classes encountered during inference. In addition, the improved performance is achieved with 6x fewer parameters than complex DNNs, showing H-SNN as an efficient approach for applications with constrained computation resources.

Download Full-text

Compact Graphene-Based Spiking Neural Network With Unsupervised Learning Capabilities

IEEE Open Journal of Nanotechnology ◽

10.1109/ojnano.2020.3041198 ◽

2020 ◽

Vol 1 ◽

pp. 135-144

Author(s):

He Wang ◽

Nicoleta Cucu Laurenciu ◽

Yande Jiang ◽

Sorin Dan Cotofana

Keyword(s):

Neural Network ◽

Unsupervised Learning ◽

Spiking Neural Network ◽

Learning Capabilities

Download Full-text

Memristor Neural Network Training with Clock Synchronous Neuromorphic System

Micromachines ◽

10.3390/mi10060384 ◽

2019 ◽

Vol 10 (6) ◽

pp. 384 ◽

Cited By ~ 6

Author(s):

Sumin Jo ◽

Wookyung Sun ◽

Bokyung Kim ◽

Sunhee Kim ◽

Junhee Park ◽

...

Keyword(s):

Neural Network ◽

Unsupervised Learning ◽

Spike Timing ◽

Machine Learning Algorithms ◽

Training Methods ◽

Nonlinear Characteristic ◽

Hardware System ◽

Neuromorphic Hardware ◽

Mathematical Formulas ◽

Inputs And Outputs

Memristor devices are considered to have the potential to implement unsupervised learning, especially spike timing-dependent plasticity (STDP), in the field of neuromorphic hardware research. In this study, a neuromorphic hardware system for multilayer unsupervised learning was designed, and unsupervised learning was performed with a memristor neural network. We showed that the nonlinear characteristic memristor neural network can be trained by unsupervised learning only with the correlation between inputs and outputs. Moreover, a method to train nonlinear memristor devices in a supervised manner, named guide training, was devised. Memristor devices have a nonlinear characteristic, which makes implementing machine learning algorithms, such as backpropagation, difficult. The guide-training algorithm devised in this paper updates the synaptic weights by only using the correlations between inputs and outputs, and therefore, neither complex mathematical formulas nor computations are required during the training. Thus, it is considered appropriate to train a nonlinear memristor neural network. All training and inference simulations were performed using the designed neuromorphic hardware system. With the system and memristor neural network, the image classification was successfully done using both the Hebbian unsupervised training and guide supervised training methods.

Download Full-text

STDP Provides the Substrate for Igniting Synfire Chains by Spatiotemporal Input Patterns

Neural Computation ◽

10.1162/neco.2007.11-05-043 ◽

2008 ◽

Vol 20 (2) ◽

pp. 415-435 ◽

Cited By ~ 21

Author(s):

Ryosuke Hosaka ◽

Osamu Araki ◽

Tohru Ikeguchi

Keyword(s):

Neural Network ◽

Experimental Studies ◽

Spike Timing ◽

Inhibitory Neurons ◽

Spatiotemporal Pattern ◽

Spiking Neural Network ◽

Synfire Chains ◽

The Neural Network ◽

Stdp Rule ◽

Neural Network Structure

Spike-timing-dependent synaptic plasticity (STDP), which depends on the temporal difference between pre- and postsynaptic action potentials, is observed in the cortices and hippocampus. Although several theoretical and experimental studies have revealed its fundamental aspects, its functional role remains unclear. To examine how an input spatiotemporal spike pattern is altered by STDP, we observed the output spike patterns of a spiking neural network model with an asymmetrical STDP rule when the input spatiotemporal pattern is repeatedly applied. The spiking neural network comprises excitatory and inhibitory neurons that exhibit local interactions. Numerical experiments show that the spiking neural network generates a single global synchrony whose relative timing depends on the input spatiotemporal pattern and the neural network structure. This result implies that the spiking neural network learns the transformation from spatiotemporal to temporal information. In the literature, the origin of the synfire chain has not been sufficiently focused on. Our results indicate that spiking neural networks with STDP can ignite synfire chains in the cortices.

Download Full-text

An integrate-and-fire spiking neural network model simulating artificially induced cortical plasticity

10.1101/2020.07.23.217265 ◽

2020 ◽

Author(s):

Larry Shupe ◽

Eberhard E. Fetz

Keyword(s):

Neural Network ◽

Cortical Neurons ◽

Closed Loop ◽

Cortical Plasticity ◽

Spike Timing ◽

Emg Activity ◽

Beta Activity ◽

Spiking Neural Network ◽

Integrate And Fire ◽

Closed Loop Stimulation

AbstractWe describe an integrate-and-fire (IF) spiking neural network that incorporates spike-timing dependent plasticity (STDP) and simulates the experimental outcomes of four different conditioning protocols that produce cortical plasticity. The original conditioning experiments were performed in freely moving non-human primates with an autonomous head-fixed bidirectional brain-computer interface. Three protocols involved closed-loop stimulation triggered from (a) spike activity of single cortical neurons, (b) EMG activity from forearm muscles, and (c) cycles of spontaneous cortical beta activity. A fourth protocol involved open-loop delivery of pairs of stimuli at neighboring cortical sites. The IF network that replicates the experimental results consists of 360 units with simulated membrane potentials produced by synaptic inputs and triggering a spike when reaching threshold. The 240 cortical units produce either excitatory or inhibitory post-synaptic potentials in their target units. In addition to the experimentally observed conditioning effects, the model also allows computation of underlying network behavior not originally documented. Furthermore, the model makes predictions about outcomes from protocols not yet investigated, including spike-triggered inhibition, gamma-triggered stimulation and disynaptic conditioning. The success of the simulations suggests that a simple voltage-based IF model incorporating STDP can capture the essential mechanisms mediating targeted plasticity with closed-loop stimulation.

Download Full-text