paper-with-me

홈 › Papers

Inference with Artificial Neural Networks on Analog Neuromorphic Hardware

2020-06-23 · Johannes Weis, Philipp Spilger, Sebastian Billaudelle, Yannik Stradmann, Arne Emmel, Eric Müller, Oliver Breitwieser, Andreas Grübl, Joscha Ilmberger, Vitali Karasenko, Mitja Kleider, Christian Mauch, Korbinian Schreiber, Johannes Schemmel

The neuromorphic BrainScaleS-2 ASIC comprises mixed-signal neurons and synapse circuits as well as two versatile digital microprocessors. Primarily designed to emulate spiking neural networks, the system can also operate in a vector-matrix multiplication and accumulation mode for artificial neural networks. Analog multiplication is carried out in the synapse circuits, while the results are accumulated on the neurons' membrane capacitors. Designed as an analog, in-memory computing device, it promises high energy efficiency. Fixed-pattern noise and trial-to-trial variations, however, require the implemented networks to cope with a certain level of perturbations. Further limitations are imposed by the digital resolution of the input values (5 bit), matrix weights (6 bit) and resulting neuron activations (8 bit). In this paper, we discuss BrainScaleS-2 as an analog inference accelerator and present calibration as well as optimization strategies, highlighting the advantages of training with hardware in the loop. Among other benchmarks, we classify the MNIST handwritten digits dataset using a two-dimensional convolution and two dense layers. We reach 98.0% test accuracy, closely matching the performance of the same network evaluated in software.

📄 PDF Abstract BibTeX arXiv:2006.13177

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

hxtorch: PyTorch for BrainScaleS-2 -- Perceptrons on Analog Neuromorphic Hardware

2020-06-23 · Philipp Spilger, Eric Müller, Arne Emmel, Aron Leibfried 외

We present software facilitating the usage of the BrainScaleS-2 analog neuromorphic hardware system as an inference accelerator for artificial neural networks. The accelerator hardware is transparently integrated into th…

Neuromorphic Hebbian learning with magnetic tunnel junction synapses

2023-08-21 · Peng Zhou, Alexander J. Edwards, Frederick B. Mancoff, Sanjeev Aggarwal 외

Neuromorphic computing aims to mimic both the function and structure of biological neural networks to provide artificial intelligence with extreme efficiency. Conventional approaches store synaptic weights in non-volatil…

Handwritten Digit Recognition

Spiking neuromorphic chip learns entangled quantum states

2020-08-03 · Stefanie Czischek, Andreas Baumbach, Sebastian Billaudelle, Benjamin Cramer 외

The approximation of quantum states with artificial neural networks has gained a lot of attention during the last years. Meanwhile, analog neuromorphic chips, inspired by structural and dynamical properties of the biolog…

Benchmarking energy consumption and latency for neuromorphic computing in condensed matter and particle physics

2022-09-21 · Dominique J. Kösters, Bryan A. Kortman, Irem Boybat, Elena Ferro 외

The massive use of artificial neural networks (ANNs), increasingly popular in many areas of scientific computing, rapidly increases the energy consumption of modern high-performance computing systems. An appealing and po…

Anomaly DetectionBenchmarking

Benchmarking Deep Spiking Neural Networks on Neuromorphic Hardware

2020-04-03 · Christoph Ostrau, Jonas Homburg, Christian Klarhorst, Michael Thies 외

With more and more event-based neuromorphic hardware systems being developed at universities and in industry, there is a growing need for assessing their performance with domain specific measures. In this work, we use th…

BenchmarkingCPUGPUNeural Architecture Search