# Demonstrating Analog Inference on the BrainScaleS-2 Mobile System

arXiv: https://arxiv.org/abs/2103.15960 · HTML: https://mlsanity.com/paper/2103.15960/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 76 references that are in the map.
- First posted on arXiv 29 Mar 2021.

## Builds on (most cited first, 21 of 21)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Massively Multilingual Neural Machine Translation](https://mlsanity.com/paper/1903.00089/) (2019)
- [Photonics for artificial intelligence and neuromorphic computing](https://mlsanity.com/paper/2011.00111/) (2020)
- [A scalable multi-core architecture with heterogeneous memory structures for Dynamic Neuromorphic Asynchronous Processors (DYNAPs)](https://mlsanity.com/paper/1708.04198/) (2017)
- [Surrogate gradients for analog neuromorphic computing](https://mlsanity.com/paper/2006.07239/) (2020)
- [Deep Learning Inference in Facebook Data Centers: Characterization, Performance Optimizations and Hardware Implications](https://mlsanity.com/paper/1811.09886/) (2018)
- [Neuromorphic Hardware In The Loop: Training a Deep Spiking Network on the BrainScaleS Wafer-Scale System](https://mlsanity.com/paper/1703.01909/) (2017)
- [Versatile emulation of spiking neural networks on an accelerated neuromorphic substrate](https://mlsanity.com/paper/1912.12980/) (2019)
- [Nengo and low-power AI hardware for robust, embedded neurorobotics](https://mlsanity.com/paper/2007.10227/) (2020)
- [MorphIC: A 65-nm 738k-Synapse/mm2 Quad-Core Binary-Weight Digital Neuromorphic Processor with Stochastic Spike-Driven Online Learning](https://mlsanity.com/paper/1904.08513/) (2019)
- [A 28-nm Convolutional Neuromorphic Processor Enabling Online Learning with Spike-Based Retinas](https://mlsanity.com/paper/2005.06318/) (2020)
- [Accelerated Analog Neuromorphic Computing](https://mlsanity.com/paper/2003.11996/) (2020)
- [Demonstrating Hybrid Learning in a Flexible Neuromorphic Hardware System](https://mlsanity.com/paper/1604.05080/) (2016)
- [An Accelerated LIF Neuronal Network Array for a Large Scale Mixed-Signal Neuromorphic Architecture](https://mlsanity.com/paper/1804.01906/) (2018)
- [Graphcore C2 Card performance for image-based deep learning application: A Report](https://mlsanity.com/paper/2002.11670/) (2020)
- [An Accelerated Analog Neuromorphic Hardware System Emulating NMDA- and Calcium-Based Non-Linear Dendrites](https://mlsanity.com/paper/1703.07286/) (2017)
- [SpiNNTools: The Execution Engine for the SpiNNaker Platform](https://mlsanity.com/paper/1810.06835/) (2018)
- [Inference with Artificial Neural Networks on Analog Neuromorphic Hardware](https://mlsanity.com/paper/2006.13177/) (2020)
- [Extending BrainScaleS OS for BrainScaleS-2](https://mlsanity.com/paper/2003.13750/) (2020)
- [hxtorch: PyTorch for BrainScaleS-2 -- Perceptrons on Analog Neuromorphic Hardware](https://mlsanity.com/paper/2006.13138/) (2020)
- [The Operating System of the Neuromorphic BrainScaleS-1 System](https://mlsanity.com/paper/2003.13749/) (2020)

## Built on by (most cited first, 1 of 1)

- [Beyond Noise: Understanding and Overcoming Temperature Effects in Analog DNN Inference](https://mlsanity.com/paper/2609.15527/) (2026)

## Abstract (arXiv)

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 (93.7±0.7)% at (14.0±1.0)% 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 applications, the system allows for a combination of conventional machine learning layers with online learning in spiking neural networks on a single neuromorphic platform.