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

Spiking Neural Networks (SNNs), the third generation NNs, have come under the spotlight for machine learning based applications due to their biological plausibility and reduced complexity compared to traditional artificial Deep Neural Networks (DNNs). These SNNs can be implemented with extreme energ...

Full description

Saved in:
Bibliographic Details
Main Authors: Massa, Riccardo, Marchisio, Alberto, Martina, Maurizio, Shafique, Muhammad
Format: Conference Proceeding
Language:English
Subjects:
Accuracy
Biological system modeling
Cameras
Conversion
DVS Camera
Event-Based Processing
Gesture Recognition
Hardware
Loihi
Machine Learning
Neuromorphic Processor
Neuromorphics
Neurons
Spiking Neural Networks
Training
Voltage control
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Spiking Neural Networks (SNNs), the third generation NNs, have come under the spotlight for machine learning based applications due to their biological plausibility and reduced complexity compared to traditional artificial Deep Neural Networks (DNNs). These SNNs can be implemented with extreme energy efficiency on neuromorphic processors like the Intel Loihi research chip, and fed by event-based sensors, such as DVS cameras. However, DNNs with many layers can achieve relatively high accuracy on image classification and recognition tasks, as the research on learning rules for SNNs for real-world applications is still not mature. The accuracy results for SNNs are typically obtained either by converting the trained DNNs into SNNs, or by directly designing and training SNNs in the spiking domain. Towards the conversion from a DNN to an SNN, we perform a comprehensive analysis of such process, specifically designed for Intel Loihi, showing our methodology for the design of an SNN that achieves nearly the same accuracy results as its corresponding DNN. Towards the usage of the event-based sensors, we design a pre-processing method, evaluated for the DvsGesture 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 the pre-processed DvsGesture dataset, and convert it into the spike domain for its deployment on Intel Loihi, which enables real-time gesture recognition. The results show that our SNN achieves 89.64% classification accuracy and occupies only 37 Loihi cores.
ISSN:2161-4407
DOI:10.1109/IJCNN48605.2020.9207109