scispace - formally typeset
Search or ask a question
Journal ArticleDOI

Supervised Learning With First-to-Spike Decoding in Multilayer Spiking Neural Networks.

12 Apr 2021-Frontiers in Computational Neuroscience (Frontiers Media SA)-Vol. 15, pp 617862-617862
TL;DR: In this paper, the authors propose a supervised learning method that can train multilayer spiking neural networks to solve classification problems based on a rapid, first-to-spike decoding strategy.
Abstract: Experimental studies support the notion of spike-based neuronal information processing in the brain, with neural circuits exhibiting a wide range of temporally-based coding strategies to rapidly and efficiently represent sensory stimuli. Accordingly, it would be desirable to apply spike-based computation to tackling real-world challenges, and in particular transferring such theory to neuromorphic systems for low-power embedded applications. Motivated by this, we propose a new supervised learning method that can train multilayer spiking neural networks to solve classification problems based on a rapid, first-to-spike decoding strategy. The proposed learning rule supports multiple spikes fired by stochastic hidden neurons, and yet is stable by relying on first-spike responses generated by a deterministic output layer. In addition to this, we also explore several distinct, spike-based encoding strategies in order to form compact representations of presented input data. We demonstrate the classification performance of the learning rule as applied to several benchmark datasets, including MNIST. The learning rule is capable of generalising from the data, and is successful even when used with constrained network architectures containing few input and hidden layer neurons. Furthermore, we highlight a novel encoding strategy, termed 'scanline encoding', that can transform image data into compact spatiotemporal patterns for subsequent network processing. Designing constrained, but optimised, network structures and performing input dimensionality reduction has strong implications for neuromorphic applications.

Content maybe subject to copyright    Report

Citations
More filters
Journal ArticleDOI
TL;DR: In this article , numerical simulations of different algorithms that utilize ultrafast photonic spiking neurons as receptive fields to allow for image recognition without an offline computing step are presented, and the merits of event, spike-time and rank-order based algorithms adapted to this system.
Abstract: Classification and recognition tasks performed on photonic hardware-based neural networks often require at least one offline computational step, such as in the increasingly popular reservoir computing paradigm. Removing this offline step can significantly improve the response time and energy efficiency of such systems. We present numerical simulations of different algorithms that utilize ultrafast photonic spiking neurons as receptive fields to allow for image recognition without an offline computing step. In particular, we discuss the merits of event, spike-time and rank-order based algorithms adapted to this system. These techniques have the potential to significantly improve the efficiency and effectiveness of optical classification systems, minimizing the number of spiking nodes required for a given task and leveraging the parallelism offered by photonic hardware.
Posted Content
TL;DR: In this paper, a new supervised learning algorithm is proposed to train spiking neural networks for classification, which overcomes a limitation of existing multi-spike learning methods: it solves the problem of interference between interacting output spikes during a learning trial.
Abstract: We introduce a new supervised learning algorithm based to train spiking neural networks for classification. The algorithm overcomes a limitation of existing multi-spike learning methods: it solves the problem of interference between interacting output spikes during a learning trial. This problem of learning interference causes learning performance in existing approaches to decrease as the number of output spikes increases, and represents an important limitation in existing multi-spike learning approaches. We address learning interference by introducing a novel mechanism to balance the magnitudes of weight adjustments during learning, which in theory allows every spike to simultaneously converge to their desired timings. Our results indicate that our method achieves significantly higher memory capacity and faster convergence compared to existing approaches for multi-spike classification. In the ubiquitous Iris and MNIST datasets, our algorithm achieves competitive predictive performance with state-of-the-art approaches.
References
More filters
Proceedings ArticleDOI
Jia Deng1, Wei Dong1, Richard Socher1, Li-Jia Li1, Kai Li1, Li Fei-Fei1 
20 Jun 2009
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.
Abstract: The explosion of image data on the Internet has the potential to foster more sophisticated and robust models and algorithms to index, retrieve, organize and interact with images and multimedia data. But exactly how such data can be harnessed and organized remains a critical problem. We introduce here a new database called “ImageNet”, a large-scale ontology of images built upon the backbone of the WordNet structure. ImageNet aims to populate the majority of the 80,000 synsets of WordNet with an average of 500-1000 clean and full resolution images. This will result in tens of millions of annotated images organized by the semantic hierarchy of WordNet. This paper offers a detailed analysis of ImageNet in its current state: 12 subtrees with 5247 synsets and 3.2 million images in total. We show that ImageNet is much larger in scale and diversity and much more accurate than the current image datasets. Constructing such a large-scale database is a challenging task. We describe the data collection scheme with Amazon Mechanical Turk. Lastly, we illustrate the usefulness of ImageNet through three simple applications in object recognition, image classification and automatic object clustering. We hope that the scale, accuracy, diversity and hierarchical structure of ImageNet can offer unparalleled opportunities to researchers in the computer vision community and beyond.

49,639 citations

Journal ArticleDOI
01 Jan 1998
TL;DR: In this article, a graph transformer network (GTN) is proposed for handwritten character recognition, which can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters.
Abstract: Multilayer neural networks trained with the back-propagation algorithm constitute the best example of a successful gradient based learning technique. Given an appropriate network architecture, gradient-based learning algorithms can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters, with minimal preprocessing. This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task. Convolutional neural networks, which are specifically designed to deal with the variability of 2D shapes, are shown to outperform all other techniques. Real-life document recognition systems are composed of multiple modules including field extraction, segmentation recognition, and language modeling. A new learning paradigm, called graph transformer networks (GTN), allows such multimodule systems to be trained globally using gradient-based methods so as to minimize an overall performance measure. Two systems for online handwriting recognition are described. Experiments demonstrate the advantage of global training, and the flexibility of graph transformer networks. A graph transformer network for reading a bank cheque is also described. It uses convolutional neural network character recognizers combined with global training techniques to provide record accuracy on business and personal cheques. It is deployed commercially and reads several million cheques per day.

42,067 citations

Journal ArticleDOI
TL;DR: The results underscore the importance of precise spike timing, synaptic strength, and postsynaptic cell type in the activity-induced modification of central synapses and suggest that Hebb’s rule may need to incorporate a quantitative consideration of spike timing that reflects the narrow and asymmetric window for the induction of synaptic modification.
Abstract: In cultures of dissociated rat hippocampal neurons, persistent potentiation and depression of glutamatergic synapses were induced by correlated spiking of presynaptic and postsynaptic neurons. The relative timing between the presynaptic and postsynaptic spiking determined the direction and the extent of synaptic changes. Repetitive postsynaptic spiking within a time window of 20 msec after presynaptic activation resulted in long-term potentiation (LTP), whereas postsynaptic spiking within a window of 20 msec before the repetitive presynaptic activation led to long-term depression (LTD). Significant LTP occurred only at synapses with relatively low initial strength, whereas the extent of LTD did not show obvious dependence on the initial synaptic strength. Both LTP and LTD depended on the activation of NMDA receptors and were absent in cases in which the postsynaptic neurons were GABAergic in nature. Blockade of L-type calcium channels with nimodipine abolished the induction of LTD and reduced the extent of LTP. These results underscore the importance of precise spike timing, synaptic strength, and postsynaptic cell type in the activity-induced modification of central synapses and suggest that Hebb’s rule may need to incorporate a quantitative consideration of spike timing that reflects the narrow and asymmetric window for the induction of synaptic modification.

4,382 citations

Journal ArticleDOI
TL;DR: A new computational model for real-time computing on time-varying input that provides an alternative to paradigms based on Turing machines or attractor neural networks, based on principles of high-dimensional dynamical systems in combination with statistical learning theory and can be implemented on generic evolved or found recurrent circuitry.
Abstract: A key challenge for neural modeling is to explain how a continuous stream of multimodal input from a rapidly changing environment can be processed by stereotypical recurrent circuits of integrate-and-fire neurons in real time. We propose a new computational model for real-time computing on time-varying input that provides an alternative to paradigms based on Turing machines or attractor neural networks. It does not require a task-dependent construction of neural circuits. Instead, it is based on principles of high-dimensional dynamical systems in combination with statistical learning theory and can be implemented on generic evolved or found recurrent circuitry. It is shown that the inherent transient dynamics of the high-dimensional dynamical system formed by a sufficiently large and heterogeneous neural circuit may serve as universal analog fading memory. Readout neurons can learn to extract in real time from the current state of such recurrent neural circuit information about current and past inputs that may be needed for diverse tasks. Stable internal states are not required for giving a stable output, since transient internal states can be transformed by readout neurons into stable target outputs due to the high dimensionality of the dynamical system. Our approach is based on a rigorous computational model, the liquid state machine, that, unlike Turing machines, does not require sequential transitions between well-defined discrete internal states. It is supported, as the Turing machine is, by rigorous mathematical results that predict universal computational power under idealized conditions, but for the biologically more realistic scenario of real-time processing of time-varying inputs. Our approach provides new perspectives for the interpretation of neural coding, the design of experiments and data analysis in neurophysiology, and the solution of problems in robotics and neurotechnology.

3,446 citations