Insect-Inspired Elementary Motion Detection Embracing Resistive Memory and Spiking Neural Networks

Dalgaty, Thomas; Vianello, Elisa; Ly, D. R. B.; Indiveri, Giacomo; Salvo, B. De; Nowak, E.; Casas, Jérôme

doi:10.1007/978-3-319-95972-6_13

Cited by 9 publications

(4 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Bio-inspired systems for motion detection have incorporated mechanisms from the visual system into spiking networks to achieve motion detection (Ridwan and Cheng, 2017;Dalgaty et al, 2018).…”

Section: Motion Detectionmentioning

confidence: 99%

Event-Based Sensing and Signal Processing in the Visual, Auditory, and Olfactory Domain: A Review

Tayarani-Najaran

Schmuker

2021

Front. Neural Circuits

View full text Add to dashboard Cite

The nervous systems converts the physical quantities sensed by its primary receptors into trains of events that are then processed in the brain. The unmatched efficiency in information processing has long inspired engineers to seek brain-like approaches to sensing and signal processing. The key principle pursued in neuromorphic sensing is to shed the traditional approach of periodic sampling in favor of an event-driven scheme that mimicks sampling as it occurs in the nervous system, where events are preferably emitted upon the change of the sensed stimulus. In this paper we highlight the advantages and challenges of event-based sensing and signal processing in the visual, auditory and olfactory domains. We also provide a survey of the literature covering neuromorphic sensing and signal processing in all three modalities. Our aim is to facilitate research in event-based sensing and signal processing by providing a comprehensive overview of the research performed previously as well as highlighting conceptual advantages, current progress and future challenges in the field.

show abstract

Section: Motion Detectionmentioning

confidence: 99%

Event-Based Sensing and Signal Processing in the Visual, Auditory, and Olfactory Domain: A Review

Tayarani-Najaran

Schmuker

2021

Front. Neural Circuits

View full text Add to dashboard Cite

show abstract

“…Brain-inspired learning in spiking neural networks with RRAM synapses has been widely explored in recent years [84][85][86][87][88][89][90][91][92][93][94][95][96]. A perceptron-like neuromorphic hardware capable of STDP was presented in [90].…”

Section: Self-learning Network With Memristive Synapsesmentioning

confidence: 99%

Synaptic realizations based on memristive devices

Milo

Dalgaty

Ielmini

et al. 2020

Memristive Devices for Brain-Inspired Computing

View full text Add to dashboard Cite

“…In the field of neuromorphic computing, where a more “bottom-up” approach is taken to artificial intelligence, research into biological nervous systems has, as in the case of CNNs, also provided a source of architectural inspiration. This has led to models which, for example, incorporate dynamical and topological motifs inspired by the Drosophila visual, the honey-bee olfactory, honey-bee central complex, cricket auditory, and cockroach motor systems into models for motion detection (Dalgaty et al, 2018 ), contrast enhancement (Schmuker et al, 2014 ), path integration (Stone et al, 2017 ), temporal pattern detection (Sandin and Nilsson, 2020 ), and locomotion (Beer et al, 1992 ), respectively. However, such approaches have been somewhat limited by lack of an effective means of defining model parameters, whereby manual parameter tuning or correlation-based Hebbian learning rules (Hebb, 1949 ) are typically employed.…”

Section: Introductionmentioning

confidence: 99%

Bio-Inspired Architectures Substantially Reduce the Memory Requirements of Neural Network Models

et al. 2021

Self Cite

View full text Add to dashboard Cite

We propose a neural network model for the jumping escape response behavior observed in the cricket cercal sensory system. This sensory system processes low-intensity air currents in the animal's immediate environment generated by predators, competitors, and mates. Our model is inspired by decades of physiological and anatomical studies. We compare the performance of our model with a model derived through a universal approximation, or a generic deep learning, approach, and demonstrate that, to achieve the same performance, these models required between one and two orders of magnitude more parameters. Furthermore, since the architecture of the bio-inspired model is defined by a set of logical relations between neurons, we find that the model is open to interpretation and can be understood. This work demonstrates the potential of incorporating bio-inspired architectural motifs, which have evolved in animal nervous systems, into memory efficient neural network models.

show abstract

Insect-Inspired Elementary Motion Detection Embracing Resistive Memory and Spiking Neural Networks

Cited by 9 publications

References 23 publications

Event-Based Sensing and Signal Processing in the Visual, Auditory, and Olfactory Domain: A Review

Event-Based Sensing and Signal Processing in the Visual, Auditory, and Olfactory Domain: A Review

Synaptic realizations based on memristive devices

Bio-Inspired Architectures Substantially Reduce the Memory Requirements of Neural Network Models

Contact Info

Product

Resources

About