Implementing Spiking Neural Networks forEdge AI: A Practical Pipeline, Benchmarks, andDeployment on Neuromorphic Hardware

Author(s)	Ms. K Sarojini
Country	India
Abstract	Spiking Neural Networks (SNNs) offer event‑driven, low‑energy computation for Edge AI, and we present an end‑to‑end pipeline covering spike encoding, surrogate‑gradient training, hardware benchmarking, and deployment on neuromorphic systems including Loihi 2 and BrainScaleS‑2. Comparative evaluations show 18× faster and ~250× lower‑energy keyword spotting on Loihi 2 over Jetson Orin Nano, and >10× energy savings for directly trained SNNs over ANN baselines on MNIST. We further outline toolchains, event‑sensor integration, and benchmarking practices for real‑time edge deployment.
Keywords	Edge AI, Spiking Neural Networks, Neuromorphic Computing, Loihi 2, BrainScaleS-2, TinyML, Surrogate Gradients, Event Cameras, Energy Efficiency
Field	Computer Applications
Published In	Volume 8, Issue 1, January-February 2026
Published On	2026-02-21
DOI	https://doi.org/10.36948/ijfmr.2026.v08i01.69599

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research