Demonstrating Analog Inference on the BrainScaleS-2 Mobile System
Yannik Stradmann, Sebastian Billaudelle, Oliver Breitwieser, Falk Leonard Ebert, Arne Emmel, Dan Husmann, Joscha Ilmberger, Eric M\"uller, Philipp Spilger, Johannes Weis, Johannes Schemmel

TL;DR
This paper demonstrates a compact analog inference system based on BrainScaleS-2 ASIC capable of classifying ECG data with high accuracy and low power, suitable for edge applications and real-world deployment.
Contribution
It introduces a portable analog inference system using BrainScaleS-2 ASIC for medical data classification, enabling reliable edge inference outside laboratory settings.
Findings
Achieved 93.7% detection rate for atrial fibrillation
Classified ECG samples in 276 microseconds per sample
Consumed only 192 microjoules per inference at 5.6W power
Abstract
We present the BrainScaleS-2 mobile system as a compact analog inference engine based on the BrainScaleS-2 ASIC and demonstrate its capabilities at classifying a medical electrocardiogram dataset. The analog network core of the ASIC is utilized to perform the multiply-accumulate operations of a convolutional deep neural network. At a system power consumption of 5.6W, we measure a total energy consumption of 192uJ for the ASIC and achieve a classification time of 276us per electrocardiographic patient sample. Patients with atrial fibrillation are correctly identified with a detection rate of (93.70.7)% at (14.01.0)% false positives. The system is directly applicable to edge inference applications due to its small size, power envelope, and flexible I/O capabilities. It has enabled the BrainScaleS-2 ASIC to be operated reliably outside a specialized lab setting. In future…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Memory and Neural Computing · Ferroelectric and Negative Capacitance Devices · Neural dynamics and brain function
