English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Spiking Neural Networks (SNNs), the third generation NNs, have come under thespotlight for machine learning based applications due to their biologicalplausibility and reduced complexity compared to traditional artificial DeepNeural Networks (DNNs). These SNNs can be implemented with extreme energyefficiency on neuromorphic processors like the Intel Loihi research chip, andfed by event-based sensors, such as DVS cameras. However, DNNs with many layerscan achieve relatively high accuracy on image classification and recognitiontasks, as the research on learning rules for SNNs for real-world applicationsis still not mature. The accuracy results for SNNs are typically obtainedeither by converting the trained DNNs into SNNs, or by directly designing andtraining SNNs in the spiking domain. Towards the conversion from a DNN to anSNN, we perform a comprehensive analysis of such process, specifically designedfor Intel Loihi, showing our methodology for the design of an SNN that achievesnearly the same accuracy results as its corresponding DNN. Towards the usage ofthe event-based sensors, we design a pre-processing method, evaluated for theDvsGesture dataset, which makes it possible to be used in the DNN domain.Hence, based on the outcome of the first analysis, we train a DNN for thepre-processed DvsGesture dataset, and convert it into the spike domain for itsdeployment on Intel Loihi, which enables real-time gesture recognition. Theresults show that our SNN achieves 89.64% classification accuracy and occupiesonly 37 Loihi cores. The source code for generating our experiments isavailable online at https://github.com/albertomarchisio/EfficientSNN.

An Efficient Spiking Neural Network for Recognizing Gestures with a DVS Camera on the Loihi Neuromorphic Processor