Skimming Digits: Neuromorphic Classification of Spike-Encoded Images

Cohen, Gregory; Orchard, Garrick; Leng, Sio-Hoi; Tapson, Jonathan; Benosman, Ryad; Schaik, André van

doi:10.3389/fnins.2016.00184

Cited by 54 publications

(32 citation statements)

References 19 publications

(27 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As shown in Table I, the standard deviations across all configurations is less than 0.70%. These results exceed those achieved using the same number of hidden layer neurons with the SKIM algorithm alone as previously reported in [39]. Combining the learnt features with the SKIM network creates a fully event-based network from end to end.…”

Section: A N-mnist Digit Classification Resultscontrasting

confidence: 68%

“…While the N-MNIST dataset represents a good benchmarking task for event-based classification systems, with results reported in multiple papers [27], [39]- [41], it represents a heavily controlled classification task. The use of the fixed and predictable saccade motion creates an unrealistic assumption on which to test feature detection algorithms destined for less controlled real-world tasks.…”

Section: A Datasetsmentioning

confidence: 99%

“…The implementation of the network requires a number of modifications in order to utilize the algorithm for a classification task. A full discussion of these alterations is provided in [39].…”

Section: B Classifiersmentioning

confidence: 99%

See 2 more Smart Citations

Event-Based Feature Extraction Using Adaptive Selection Thresholds

Afshar

Ralph

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

Unsupervised feature extraction algorithms form one of the most important building blocks in machine learning systems. These algorithms are often adapted to the event-based domain to perform online learning in neuromorphic hardware. However, not designed for the purpose, such algorithms typically require significant simplification during implementation to meet hardware constraints, creating trade offs with performance. Furthermore, conventional feature extraction algorithms are not designed to generate useful intermediary signals which are valuable only in the context of neuromorphic hardware limitations. In this work a novel event-based feature extraction method is proposed that focuses on these issues. The algorithm operates via simple adaptive selection thresholds which allow a simpler implementation of network homeostasis than previous works by trading off a small amount of information loss in the form of missed events that fall outside the selection thresholds. The behavior of the selection thresholds and the output of the network as a whole are shown to provide uniquely useful signals indicating network weight convergence without the need to access network weights. A novel heuristic method for network size selection is proposed which makes use of noise events and their feature representations. The use of selection thresholds is shown to produce network activation patterns that predict classification accuracy allowing rapid evaluation and optimization of system parameters without the need to run back-end classifiers.The feature extraction method is tested on both the N-MNIST benchmarking dataset and a dataset of airplanes passing through the field of view. Multiple configurations with different classifiers are tested with the results quantifying the resultant performance gains at each processing stage.

show abstract

Section: A N-mnist Digit Classification Resultscontrasting

confidence: 68%

Section: A Datasetsmentioning

confidence: 99%

See 1 more Smart Citation

Event-Based Feature Extraction Using Adaptive Selection Thresholds

Afshar

Ralph

et al. 2020

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…Our method improves the best previously-reported ANN result of 1.7% error rate, and in addition achieves an almost 3 times smaller error rate than the best previous spiking CNN (4.28%). It is also far better than a fully-connected SNN with 10 k hidden units (7.13%) in Cohen et al (2016) even though our network uses only 800 hidden units. This result clearly shows the importance and possible benefits of training SNNs directly on event streams.…”

Section: Resultsmentioning

confidence: 64%

Training Deep Spiking Neural Networks Using Backpropagation

2016

View full text Add to dashboard Cite

Deep spiking neural networks (SNNs) hold the potential for improving the latency and energy efficiency of deep neural networks through data-driven event-based computation. However, training such networks is difficult due to the non-differentiable nature of spike events. In this paper, we introduce a novel technique, which treats the membrane potentials of spiking neurons as differentiable signals, where discontinuities at spike times are considered as noise. This enables an error backpropagation mechanism for deep SNNs that follows the same principles as in conventional deep networks, but works directly on spike signals and membrane potentials. Compared with previous methods relying on indirect training and conversion, our technique has the potential to capture the statistics of spikes more precisely. We evaluate the proposed framework on artificially generated events from the original MNIST handwritten digit benchmark, and also on the N-MNIST benchmark recorded with an event-based dynamic vision sensor, in which the proposed method reduces the error rate by a factor of more than three compared to the best previous SNN, and also achieves a higher accuracy than a conventional convolutional neural network (CNN) trained and tested on the same data. We demonstrate in the context of the MNIST task that thanks to their event-driven operation, deep SNNs (both fully connected and convolutional) trained with our method achieve accuracy equivalent with conventional neural networks. In the N-MNIST example, equivalent accuracy is achieved with about five times fewer computational operations.

show abstract

“…Besides, a biologically-inspired Gabor feature approach based on spiking neural networks with Leaky-Integrate and Fire neurons has been presented (Tsitiridis et al, 2015). A Synaptic Kernel Inverse Method (SKIM) based on principles of dendritic computation is applied to N-MNIST dataset (Orchard et al, 2015a) to perform a large-scale classification task (Cohen et al, 2016). …”

Section: Introductionmentioning

confidence: 99%

An Event-Based Neurobiological Recognition System with Orientation Detector for Objects in Multiple Orientations

Wang

Gao

et al. 2016

Front. Neurosci.

View full text Add to dashboard Cite

A new multiple orientation event-based neurobiological recognition system is proposed by integrating recognition and tracking function in this paper, which is used for asynchronous address-event representation (AER) image sensors. The characteristic of this system has been enriched to recognize the objects in multiple orientations with only training samples moving in a single orientation. The system extracts multi-scale and multi-orientation line features inspired by models of the primate visual cortex. An orientation detector based on modified Gaussian blob tracking algorithm is introduced for object tracking and orientation detection. The orientation detector and feature extraction block work in simultaneous mode, without any increase in categorization time. An addresses lookup table (addresses LUT) is also presented to adjust the feature maps by addresses mapping and reordering, and they are categorized in the trained spiking neural network. This recognition system is evaluated with the MNIST dataset which have played important roles in the development of computer vision, and the accuracy is increased owing to the use of both ON and OFF events. AER data acquired by a dynamic vision senses (DVS) are also tested on the system, such as moving digits, pokers, and vehicles. The experimental results show that the proposed system can realize event-based multi-orientation recognition. The work presented in this paper makes a number of contributions to the event-based vision processing system for multi-orientation object recognition. It develops a new tracking-recognition architecture to feedforward categorization system and an address reorder approach to classify multi-orientation objects using event-based data. It provides a new way to recognize multiple orientation objects with only samples in single orientation.

show abstract

Skimming Digits: Neuromorphic Classification of Spike-Encoded Images

Cited by 54 publications

References 19 publications

Event-Based Feature Extraction Using Adaptive Selection Thresholds

Event-Based Feature Extraction Using Adaptive Selection Thresholds

Training Deep Spiking Neural Networks Using Backpropagation

An Event-Based Neurobiological Recognition System with Orientation Detector for Objects in Multiple Orientations

Contact Info

Product

Resources

About