Learning in Neural Networks

Bogdan, Petrut; García, Garibaldi Pineda; Hopkins, Michael; Jones, Edward; Knight, James C.; Perrett, Adam

doi:10.1561/9781680836530.ch7

Cited by 2 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Applications running on SpiNNaker have shown it is capable of real time simulations, inference, and learning (Bogdan et al, 2020a , b ; Galluppi et al, 2020 ). Particularly, Rhodes et al ( 2019 ) have simulated a large-scale, biologically representative spiking neural network in real time supported by the use of a heterogeneous parallelization scheme.…”

Section: Introductionmentioning

confidence: 99%

Towards a Bio-Inspired Real-Time Neuromorphic Cerebellum

Bogdan

Marcinnò

Casellato

et al. 2021

Front. Cell. Neurosci.

View full text Add to dashboard Cite

This work presents the first simulation of a large-scale, bio-physically constrained cerebellum model performed on neuromorphic hardware. A model containing 97,000 neurons and 4.2 million synapses is simulated on the SpiNNaker neuromorphic system. Results are validated against a baseline simulation of the same model executed with NEST, a popular spiking neural network simulator using generic computational resources and double precision floating point arithmetic. Individual cell and network-level spiking activity is validated in terms of average spike rates, relative lead or lag of spike times, and membrane potential dynamics of individual neurons, and SpiNNaker is shown to produce results in agreement with NEST. Once validated, the model is used to investigate how to accelerate the simulation speed of the network on the SpiNNaker system, with the future goal of creating a real-time neuromorphic cerebellum. Through detailed communication profiling, peak network activity is identified as one of the main challenges for simulation speed-up. Propagation of spiking activity through the network is measured, and will inform the future development of accelerated execution strategies for cerebellum models on neuromorphic hardware. The large ratio of granule cells to other cell types in the model results in high levels of activity converging onto few cells, with those cells having relatively larger time costs associated with the processing of communication. Organizing cells on SpiNNaker in accordance with their spatial position is shown to reduce the peak communication load by 41%. It is hoped that these insights, together with alternative parallelization strategies, will pave the way for real-time execution of large-scale, bio-physically constrained cerebellum models on SpiNNaker. This in turn will enable exploration of cerebellum-inspired controllers for neurorobotic applications, and execution of extended duration simulations over timescales that would currently be prohibitive using conventional computational platforms.

show abstract

Section: Introductionmentioning

confidence: 99%

Towards a Bio-Inspired Real-Time Neuromorphic Cerebellum

Bogdan

Marcinnò

Casellato

et al. 2021

Front. Cell. Neurosci.

View full text Add to dashboard Cite

show abstract

Event-driven proto-object based saliency in 3D space to attract a robot’s attention

Ghosh

D’Angelo

Glover

et al. 2022

Sci Rep

View full text Add to dashboard Cite

To interact with its environment, a robot working in 3D space needs to organise its visual input in terms of objects or their perceptual precursors, proto-objects. Among other visual cues, depth is a submodality used to direct attention to visual features and objects. Current depth-based proto-object attention models have been implemented for standard RGB-D cameras that produce synchronous frames. In contrast, event cameras are neuromorphic sensors that loosely mimic the function of the human retina by asynchronously encoding per-pixel brightness changes at very high temporal resolution, thereby providing advantages like high dynamic range, efficiency (thanks to their high degree of signal compression), and low latency. We propose a bio-inspired bottom-up attention model that exploits event-driven sensing to generate depth-based saliency maps that allow a robot to interact with complex visual input. We use event-cameras mounted in the eyes of the iCub humanoid robot to directly extract edge, disparity and motion information. Real-world experiments demonstrate that our system robustly selects salient objects near the robot in the presence of clutter and dynamic scene changes, for the benefit of downstream applications like object segmentation, tracking and robot interaction with external objects.

show abstract

Learning in Neural Networks

Cited by 2 publications

References 0 publications

Towards a Bio-Inspired Real-Time Neuromorphic Cerebellum

Towards a Bio-Inspired Real-Time Neuromorphic Cerebellum

Event-driven proto-object based saliency in 3D space to attract a robot’s attention

Contact Info

Product

Resources

About