Understanding images in biological and computer vision

Schofield, Andrew J.; Gilchrist, Iain D.; Bloj, Marina; Leonardis, Aleš; Bellotto, Nicola

doi:10.1098/rsfs.2018.0027

Cited by 3 publications

(1 citation statement)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the last few years, diverse machine learning (ML) methods have been proposed for the recognition of spike patterns generated by neural populations (Ambard and Rotter, 2012;Tapson et al, 2013;Grassia et al, 2017;Nazari and Faes, 2019). The ability to learn and decode spike patterns is not only useful for the interpretation of biological mechanisms (Koyama et al, 2010;Rudnicki et al, 2012;Heelan et al, 2019) but also for engineering applications, such as artificial vision and hearing (Nogueira et al, 2007;Zai et al, 2015;Schofield et al, 2018) analysis of brain signals (Susi et al, 2018), forecasting of energy consumption (Kulkarni et al, 2013), and so on. Most of such ML methods are based on neural networks, and specifically on the bio-inspired spiking neural networks (SNNs) (Maass, 1997;Florian, 2012).…”

Section: Introductionmentioning

confidence: 99%

nMNSD—A Spiking Neuron-Based Classifier That Combines Weight-Adjustment and Delay-Shift

et al. 2021

View full text Add to dashboard Cite

The recent “multi-neuronal spike sequence detector” (MNSD) architecture integrates the weight- and delay-adjustment methods by combining heterosynaptic plasticity with the neurocomputational feature spike latency, representing a new opportunity to understand the mechanisms underlying biological learning. Unfortunately, the range of problems to which this topology can be applied is limited because of the low cardinality of the parallel spike trains that it can process, and the lack of a visualization mechanism to understand its internal operation. We present here the nMNSD structure, which is a generalization of the MNSD to any number of inputs. The mathematical framework of the structure is introduced, together with the “trapezoid method,” that is a reduced method to analyze the recognition mechanism operated by the nMNSD in response to a specific input parallel spike train. We apply the nMNSD to a classification problem previously faced with the classical MNSD from the same authors, showing the new possibilities the nMNSD opens, with associated improvement in classification performances. Finally, we benchmark the nMNSD on the classification of static inputs (MNIST database) obtaining state-of-the-art accuracies together with advantageous aspects in terms of time- and energy-efficiency if compared to similar classification methods.

show abstract