Deep Convolutional Spiking Neural Networks for Image Classification

Vaila, Ruthvik; Chiasson, John; Saxena, Vishal

doi:10.48550/arxiv.1903.12272

Cited by 10 publications

(12 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To monitor the weight updates (synapse changes) in the spiking network, the software provides the capability to monitor spike activity, weight evolution (updates), feature extraction (spikes per map per label), and synapse convergence, etc. This software tool was used here and in [34] [35]. Similar to our work, Mozafari et al released the software tool SPYKETORCH in [43] which is based on the PYTORCH [44] deep learning tool.…”

Section: Software Toolmentioning

confidence: 98%

A Deep Unsupervised Feature Learning Spiking Neural Network with Binarized Classification Layers for EMNIST Classification using SpykeFlow

Vaila¹,

Chiasson²,

Saxena³

2020

Preprint

Self Cite

View full text Add to dashboard Cite

End user AI is trained on large server farms with data collected from the users. With ever increasing demand for IOT devices, there is a need for deep learning approaches that can be implemented (at the edge) in an energy efficient manner. In this work we approach this using spiking neural networks. The unsupervised learning technique of spike timing dependent plasticity (STDP) and binary activations are used to extract features from spiking input data. Gradient descent (backpropagation) is used only on the output layer to perform the training for classification. The accuracies obtained for the balanced EMNIST data set compare favorably with other approaches. The effect of stochastic gradient descent (SGD) approximations on learning capabilities of our network are also explored. We also introduce SPYKEFLOW, a PYTHON based software tool that we developed.

show abstract

Section: Software Toolmentioning

confidence: 98%

A Deep Unsupervised Feature Learning Spiking Neural Network with Binarized Classification Layers for EMNIST Classification using SpykeFlow

Vaila¹,

Chiasson²,

Saxena³

2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…It should be noted, however, that the average number of spikes is greatly increased due to the adaptive sampling increasing the resolution of the signal. It is worth noting that the fitness function can be adjusted, using m and n parameters in (6), based on the specific application requirement to emphasize on the precision or computation efficiency:…”

Section: B Threshold Optimizationmentioning

confidence: 99%

“…In this paper, we are focusing on the encoding of static images for image classification with SNNs into spike trains. Two of the well-known methods for encoding static images are firing rate-based encoding [2]- [4] and population rank order encoding [5], [6]. In the rate-based encoding, each input is a Poisson spike train with a firing rate proportional to the intensity of the of the corresponding pixel in the image [4].…”

Section: Introductionmentioning

confidence: 99%

An Adaptive Sampling and Edge Detection Approach for Encoding Static Images for Spiking Neural Networks

Chandarana¹,

Ou²,

Zand³

2021

Preprint

View full text Add to dashboard Cite

Current state-of-the-art methods of image classification using convolutional neural networks are often constrained by both latency and power consumption. This places a limit on the devices, particularly low-power edge devices, that can employ these methods. Spiking neural networks (SNNs) are considered to be the third generation of artificial neural networks which aim to address these latency and power constraints by taking inspiration from biological neuronal communication processes. Before data such as images can be input into an SNN, however, they must be first encoded into spike trains. Herein, we propose a method for encoding static images into temporal spike trains using edge detection and an adaptive signal sampling method for use in SNNs. The edge detection process consists of first performing Canny edge detection on the 2D static images and then converting the edge detected images into two X and Y signals using an image-to-signal conversion method. The adaptive signaling approach consists of sampling the signals such that the signals maintain enough detail and are sensitive to abrupt changes in the signal. Temporal encoding mechanisms such as threshold-based representation (TBR) and step-forward (SF) are then able to be used to convert the sampled signals into spike trains. We use various error and indicator metrics to optimize and evaluate the efficiency and precision of the proposed image encoding approach. Comparison results between the original and reconstructed signals from spike trains generated using edgedetection and adaptive temporal encoding mechanism exhibit 18× and 7× reduction in average root mean square error (RMSE) compared to the conventional SF and TBR encoding, respectively, while used for encoding MNIST dataset.

show abstract

“…We achieved 98.40% accuracy without more expensive training techniques such as error normalization in [7]. We outperformed convolutional SNNs such as [11], [15] and DNNs such as [1], [12].…”

Section: A Spiking Dataset Classificationmentioning

confidence: 99%

“…The dataset has 20 classes, and splits into 8156 and 2264 samples for training and testing respectively. A sample of the SHD dataset is shown [7] 98.66 Spiking MLP [3] 47.5 Phased LSTM [12] 97.28 R-SNN [3] 83.2 Spiking CNN [11] 95.72 LSTM [3] 89.0 Graph CNN [1] 98.5 R-SNN [20] 82.0 Spiking CNN [15] 98.32 SRNN [18] 84.4 II. We achieved 85.69% accuracy, which is the best in SNN domain.…”

Section: A Spiking Dataset Classificationmentioning

confidence: 99%

Neuromorphic Algorithm-hardware Codesign for Temporal Pattern Learning

Fang

Taylor

et al. 2021

Preprint

View full text Add to dashboard Cite

Neuromorphic computing and spiking neural networks (SNN) mimic the behavior of biological systems and have drawn interest for their potential to perform cognitive tasks with high energy efficiency. However, some factors such as temporal dynamics and spike timings prove critical for information processing but are often ignored by existing works, limiting the performance and applications of neuromorphic computing. On one hand, due to the lack of effective SNN training algorithms, it is difficult to utilize the temporal neural dynamics. Many existing algorithms still treat neuron activation statistically. On the other hand, utilizing temporal neural dynamics also poses challenges to hardware design. Synapses exhibit temporal dynamics, serving as memory units that hold historical information, but are often simplified as a connection with weight. Most current models integrate synaptic activations in some storage medium to represent membrane potential and institute a hard reset of membrane potential after the neuron emits a spike. This is done for its simplicity in hardware, requiring only a "clear" signal to wipe the storage medium, but destroys temporal information stored in the neuron.In this work, we derive an efficient training algorithm for Leaky Integrate and Fire neurons, which is capable of training a SNN to learn complex spatial temporal patterns. We achieved competitive accuracy on two complex datasets. We also demonstrate the advantage of our model by a novel temporal pattern association task. Codesigned with this algorithm, we have developed a CMOS circuit implementation for a memristor-based network of neuron and synapses which retains critical neural dynamics with reduced complexity. This circuit implementation of the neuron model is simulated to demonstrate its ability to react to temporal spiking patterns with an adaptive threshold.

show abstract

Deep Convolutional Spiking Neural Networks for Image Classification

Cited by 10 publications

References 47 publications

A Deep Unsupervised Feature Learning Spiking Neural Network with Binarized Classification Layers for EMNIST Classification using SpykeFlow

A Deep Unsupervised Feature Learning Spiking Neural Network with Binarized Classification Layers for EMNIST Classification using SpykeFlow

An Adaptive Sampling and Edge Detection Approach for Encoding Static Images for Spiking Neural Networks

Neuromorphic Algorithm-hardware Codesign for Temporal Pattern Learning

Contact Info

Product

Resources

About