Spikemax: Spike-based Loss Methods for Classification

Shrestha, Sumit Bam; Zhu, Longwei; Sun, Pengfei

doi:10.1109/ijcnn55064.2022.9892379

Cited by 6 publications

(6 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our experiments seem to agree with the above and further confirm the great potential of using spike timing as part of the solution to an ASR problem. Furthermore, the use of spike-based losses [31] can expedite decision-making, thereby reducing the impact of additional latency even more.…”

Section: Discussionmentioning

confidence: 99%

Adaptive Axonal Delays in Feedforward Spiking Neural Networks for Accurate Spoken Word Recognition

Sun

Eqlimi

Chua

et al. 2023

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

Spiking neural networks (SNN) are a promising research avenue for building accurate and efficient automatic speech recognition systems. Recent advances in audio-to-spike encoding and training algorithms enable SNN to be applied in practical tasks. Biologically-inspired SNN communicates using sparse asynchronous events. Therefore, spike-timing is critical to SNN performance. In this aspect, most works focus on training synaptic weights and few have considered delays in event transmission, namely axonal delay. In this work, we consider a learnable axonal delay capped at a maximum value, which can be adapted according to the axonal delay distribution in each network layer. We show that our proposed method achieves the best classification results reported on the SHD dataset (92.45%) and NTIDIGITS dataset (95.09%). Our work illustrates the potential of training axonal delays for tasks with complex temporal structures.

show abstract

Section: Discussionmentioning

confidence: 99%

Adaptive Axonal Delays in Feedforward Spiking Neural Networks for Accurate Spoken Word Recognition

Sun

Eqlimi

Chua

et al. 2023

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Secondly, after audio is encoded, the actual execution of the audio processing in the neuromorphic domain is a very open research opportunity. Neuromorphic audio processing systems can employ a wide variety of strategies to perform processing in the neuromorphic domain, such as simplistic DNN conversion [66], using a network of feedforward or recurrent leaky integrate-and-fire neurons [7,67,68], a network of complex resonate-and-fire neurons [52], or a sigma-delta neural network (SDNN) as we describe in the following subsection for our baseline solution. Methodologies inspired by conventional deep learning, e.g.…”

Section: Neuromorphic Audio Processing and Promising Directionsmentioning

confidence: 99%

“…The axonal delays endow the network with a short-term memory capability that allows the interaction of audio/features originating at different points in time. Learnable axonal delays have been shown to increase the expressivity and performance of networks, particularly for applications with spatio-temporal features [68,77]. Audio denoising is one such application.…”

Section: Sigma-delta Neural Network Architecturementioning

confidence: 99%

The Intel neuromorphic DNS challenge

Timcheck

Shrestha

Rubin

et al. 2023

Neuromorph. Comput. Eng.

View full text Add to dashboard Cite

A critical enabler for progress in neuromorphic computing research is the ability to transparently evaluate different neuromorphic solutions on important tasks and to compare them to state-of-the-art conventional solutions. The Intel Neuromorphic Deep Noise Suppression Challenge (Intel N-DNS Challenge), inspired by the Microsoft DNS Challenge, tackles a ubiquitous and commercially relevant task: real-time audio denoising. Audio denoising is likely to reap the benefits of neuromorphic computing due to its low-bandwidth, temporal nature and its relevance for low-power devices. The Intel N-DNS Challenge consists of two tracks: a simulation-based algorithmic track to encourage algorithmic innovation, and a neuromorphic hardware (Loihi 2) track to rigorously evaluate solutions. For both tracks, we specify an evaluation methodology based on energy, latency, and resource consumption in addition to output audio quality. We make the Intel N-DNS Challenge dataset scripts and evaluation code freely accessible, encourage community participation with monetary prizes, and release a neuromorphic baseline solution which shows promising audio quality, high power efficiency, and low resource consumption when compared to Microsoft NsNet2 and a proprietary Intel denoising model used in production. We hope the Intel N-DNS Challenge will hasten innovation in neuromorphic algorithms research, especially in the area of training tools and methods for real-time signal processing. We expect the winners of the challenge will demonstrate that for problems like audio denoising, significant gains in power and resources can be realized on neuromorphic devices available today compared to conventional state-of-the-art solutions.

show abstract

“… Method Acc (%) DVSGesture Hetero. RSNN (Perez-Nieves et al, 2021 ) 82.9 SLAYER (Shrestha and Orchard, 2018 ) 93.64 ± 0.49 DECOLLE (Kaiser et al, 2020 ) 95.54 SLAYER + SpikeMax (Shrestha et al, 2022 ) 95.83 ± 0.48 PLIF (Fang et al, 2021 ) (STBP) 97.57 STSC-SNN (Yu et al, 2022 ) 98.96 Ours (CUBA-LIF) 92.8 SHD Hetero. RSNN (Perez-Nieves et al, 2021 ) 82.7 ± 0.8 RSNN with data aug. + noise (Cramer et al, 2022 ) 83.2 ± 1.3 Adaptive SRNN (Yin et al, 2021 ) 90.4 TA-SNN (Yao et al, 2021 ) 91.08 STSC-SNN (Yu et al, 2022 ) 92.36 RadLIF (Bittar and Garner, 2022 ) 94.62 …”

Section: Table A1mentioning

confidence: 99%

First-spike coding promotes accurate and efficient spiking neural networks for discrete events with rich temporal structures

Liu,

Leung,

Dragotti

2023

Front. Neurosci.

View full text Add to dashboard Cite

Spiking neural networks (SNNs) are well-suited to process asynchronous event-based data. Most of the existing SNNs use rate-coding schemes that focus on firing rate (FR), and so they generally ignore the spike timing in events. On the contrary, methods based on temporal coding, particularly time-to-first-spike (TTFS) coding, can be accurate and efficient but they are difficult to train. Currently, there is limited research on applying TTFS coding to real events, since traditional TTFS-based methods impose one-spike constraint, which is not realistic for event-based data. In this study, we present a novel decision-making strategy based on first-spike (FS) coding that encodes FS timings of the output neurons to investigate the role of the first-spike timing in classifying real-world event sequences with complex temporal structures. To achieve FS coding, we propose a novel surrogate gradient learning method for discrete spike trains. In the forward pass, output spikes are encoded into discrete times to generate FS times. In the backpropagation, we develop an error assignment method that propagates error from FS times to spikes through a Gaussian window, and then supervised learning for spikes is implemented through a surrogate gradient approach. Additional strategies are introduced to facilitate the training of FS timings, such as adding empty sequences and employing different parameters for different layers. We make a comprehensive comparison between FS and FR coding in the experiments. Our results show that FS coding achieves comparable accuracy to FR coding while leading to superior energy efficiency and distinct neuronal dynamics on data sequences with very rich temporal structures. Additionally, a longer time delay in the first spike leads to higher accuracy, indicating important information is encoded in the timing of the first spike.

show abstract

Spikemax: Spike-based Loss Methods for Classification

Cited by 6 publications

References 31 publications

Adaptive Axonal Delays in Feedforward Spiking Neural Networks for Accurate Spoken Word Recognition

Adaptive Axonal Delays in Feedforward Spiking Neural Networks for Accurate Spoken Word Recognition

The Intel neuromorphic DNS challenge

First-spike coding promotes accurate and efficient spiking neural networks for discrete events with rich temporal structures

Contact Info

Product

Resources

About