The Heidelberg Spiking Data Sets for the Systematic Evaluation of Spiking Neural Networks
By Benjamin Cramer, Yannik Stradmann, Johannes Schemmel, Friedemann Zenke. IEEE Transactions on Neural Networks and Learning Systems, 2019
337 citations recorded by the source corpus.
Spiking neural networks are the basis of versatile and power-efficient information processing in the brain. Although we currently lack a detailed understanding of how these networks compute, recently developed optimization techniques allow us to instantiate increasingly complex functional spiking neural networks in-silico. These methods hold the promise to build more efficient non-von-Neumann computing hardware and will offer new vistas in the quest of unraveling brain circuit function. To accelerate the development of such methods, objective ways to compare their performance are indispensable. Presently, however, there are no widely accepted means for comparing the computational performance of spiking neural networks. To address this issue, we introduce two spike-based classification data sets, broadly applicable to benchmark both software and neuromorphic hardware implementations of spiking neural networks. To accomplish this, we developed a general audio-to-spiking conversion procedure inspired by neurophysiology. Furthermore, we applied this conversion to an existing and a novel speech data set. The latter is the free, high-fidelity, and word-level aligned Heidelberg digit data set that we created specifically for this study. By training a range of conventional and spiking classifiers, we show that leveraging spike timing information within these data sets is essential for good classification accuracy. These results serve as the first reference for future performance comparisons of spiking neural networks.
Subfields: Cognitive Neuroscience, Electrical and Electronic Engineering
View Paper: https://www.semanticscholar.org/paper/90cecfb1c12530f1a4ecc83ab48a47e35ee60fab
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Cognitive Neuroscience
- Friedemann Zenke
- Emre O. Neftci
- Tim P. Vogels
- Shruti R. Kulkarni
- Catherine D. Schuman
- J. Parker Mitchell
- Bill Kay
- Maryam Parsa
In Electrical and Electronic Engineering
- Friedemann Zenke
- Emre O. Neftci
- Tim P. Vogels
- Shruti R. Kulkarni
- Catherine D. Schuman
- J. Parker Mitchell
- Bill Kay
- Maryam Parsa
Citations in the corpus
- Training Spiking Neural Networks Using Lessons From Deep Learning (2021, methodology): “SSC [106] Spiking version of the Speech Commands dataset converted using a simulated cochlear model.”
- Opportunities for neuromorphic computing algorithms and applications (2022, background): “As surveyed by Zenke and Neftci 40 , approaches such as backpropagation through time and real-time recurrent learning have been demonstrated on neuromorphic datasets, such as the Spiking Heidelberg Digits (SHD) and the Spiking Speech Command (SSC) dataset 41 .”
- Neural heterogeneity promotes robust learning (2020, background): “, 2017) feature visual stimuli, while the Spiking Heidelberg Digits (SHD) and Spiking Speech Commands (SSC) datasets (Cramer et al., 2019) are auditory.”
- The remarkable robustness of surrogate gradient learning for instilling complex function in spiking neural networks (2020, methodology): “To test this idea, we converted the raw audio data of the Heidelberg Digits [23] to Mel-spaced spectrograms (7d; Methods).”