Spotlight

Papers

Field

Top tools here

Open problems in Efficient spiking neural

Efficient quantization for spiking neural networks1 paper raises it · 1 addresses it
Low-bit weights and membrane potentials are needed for neuromorphic hardware but existing PTQ methods ignore spike-specific errors.
- SpikeQ: Spike-Guided Post-Training Quantization for Spiking Neural Networksraises · addresses
Redundant subthreshold computation in SNNs1 paper raises it · 1 addresses it
Postsynaptic neurons in subthreshold states waste computation despite low firing probability.
- The Dormant Spiking Neuron: A State-Driven Mechanism for Efficient Spiking Neural Networksraises · addresses
Catastrophic forgetting in continual learning for SNNs1 paper raises it · 1 addresses it
SNNs suffer from accuracy loss when learning tasks sequentially under memory constraints.
- Saliency-Guided Replay for Continual Learning in Deep Spiking Neural Networksraises · addresses
Hardware-aware training and inference for SNNs1 paper raises it · 2 address it
Efficient on-device deployment requires specialized hardware and training methods to avoid memory and latency overhead.
- An FPGA-Based Spiking Neural Network for Spatiotemporal Pattern Learning and Classificationraises · addresses
- Removing the Compute Bottleneck for Event-based Visual Place Recognition with Spiking Neural Networksaddresses
Accuracy gap in spiking language models1 paper raises it · 1 addresses it
Spiking language models lag behind dense models in accuracy, with a persistent loss gap even at scale.
- Compute-Optimal Scaling Laws for Spiking Language Modelsraises · addresses

Named by an AI from these papers' abstracts.

Open problems

Recently funded

Topics in this field

efficient spiking neural · spiking neural networks · networks spiking neural39 papers2 this week

Topics in this field

Active contributors · 90 days

Active contributors

Activity · 12 weeks

Coming with more sources: repos

Activity

★ Spotlight this month

arXiv cs.CVOct 15

The Dormant Spiking Neuron: A State-Driven Mechanism for Efficient Spiking Neural Networks

Ruichen Ma, Yicai Chen, Pujun Zhou, Yue Zuo, Chongyang Li +3

Spiking neural networks (SNNs) offer a compelling pathway toward energy-efficient artificial intelligence, fundamentally anchored in presynaptic input-driven sparsity. However, a substantial yet chronically overlooked source of computational overhead persists: the continuous subthreshold dynamics of postsynaptic neurons. Quantitative analysis reveals that up to 44% of neurons in an ImageNet-trained ResNet-18 model reside in a deeply inhibited state, imposing a persistent computational burden despite having a negligible probability of firing. To address this inefficiency, the Dormant Spiking Neuron (DSN) model is introduced. By incorporating a state-driven dynamic gate, the DSN allows a neuron to enter a dormant state when its membrane potential falls below a predefined negative threshold, dynamically pruning redundant computations at the instance level. Crucially, this dormancy mechanism is directly integrated into the neuronal dynamics and trained end-to-end via backpropagation through time using surrogate gradients, enabling the network to actively learn a robust dormancy policy that adaptively preserves critical information flow. Extensive experiments across static and…

PDF arXiv page Details

Spotlight

Recent papers

All in Research →

arXiv cs.NEOct 16
SpikeQ: Spike-Guided Post-Training Quantization for Spiking Neural Networks
Kai Sun, Peibo Duan, Zhanglu Yan, Guowei Zhang, Yongsheng Huang +1
On neuromorphic chips, spiking neural networks (SNNs) consume far less energy than artificial neural networks (ANNs), but the limited memory of these chips requires low-bit synaptic weights and membrane potentials. Existing post-training quantization (PTQ) methods provide them without retraining and, like those for ANNs, minimize numerical errors such as the mean squared error (MSE). In an SNN, however, a quantization error reaches later layers only through the spikes it flips. We find that errors of equal MSE can cause very different accuracy losses, whereas errors that flip the same fraction of spikes cause the same loss. We therefore propose SpikeQ, a spike-guided PTQ framework. For weights, we select the level of each weight by simulating the downstream neurons and minimizing their spike errors. For membrane potentials, most existing methods quantize the state after the reset, whereas neuromorphic chips compare the threshold with the membrane potential stored at a fixed bit width. We target this pre-fire quantization and build a reset-aware grid that places the threshold on a rounding boundary, so rounding never flips the spike at the current time step. We evaluate SpikeQ on…
PDF arXiv
arXiv cs.CVOct 15
The Dormant Spiking Neuron: A State-Driven Mechanism for Efficient Spiking Neural Networks
Ruichen Ma, Yicai Chen, Pujun Zhou, Yue Zuo, Chongyang Li +3
Spiking neural networks (SNNs) offer a compelling pathway toward energy-efficient artificial intelligence, fundamentally anchored in presynaptic input-driven sparsity. However, a substantial yet chronically overlooked source of computational overhead persists: the continuous subthreshold dynamics of postsynaptic neurons. Quantitative analysis reveals that up to 44% of neurons in an ImageNet-trained ResNet-18 model reside in a deeply inhibited state, imposing a persistent computational burden despite having a negligible probability of firing. To address this inefficiency, the Dormant Spiking Neuron (DSN) model is introduced. By incorporating a state-driven dynamic gate, the DSN allows a neuron to enter a dormant state when its membrane potential falls below a predefined negative threshold, dynamically pruning redundant computations at the instance level. Crucially, this dormancy mechanism is directly integrated into the neuronal dynamics and trained end-to-end via backpropagation through time using surrogate gradients, enabling the network to actively learn a robust dormancy policy that adaptively preserves critical information flow. Extensive experiments across static and…
PDF arXiv
arXiv cs.LGOct 13
Saliency-Guided Replay for Continual Learning in Deep Spiking Neural Networks
Francesco Panetta, Federico Di Valerio, Michela Proietti
Spiking Neural Networks (SNNs) are promising for energy-efficient neuromorphic computing, but they still suffer from catastrophic forgetting when learning tasks sequentially. This work investigates the integration of Experience Packing and Replay (EPR) as a memory-efficient continual learning strategy for deep SNNs under low-latency constraints. The proposed framework combines Batch Normalization Through Time stabilized VGG9 SNNs with Spike Activation Maps (SAM), which provide forward-only explanations based on spike activity. These explanations are temporally aggregated into spatial attention maps and used to select the most informative image patches for replay, instead of storing full images. Experiments on Split CIFAR10 and Split CIFAR100 show that SAM-guided EPR improves the accuracy-memory trade-off under tight memory budgets, and remains competitive while requiring substantially less storage.
PDF arXiv
arXiv cs.LGOct 13
Sea-Net: A Small and Inherently Interpretable Neural Network for Time Series Classification
Ubaid Ur Rehman, Tanmoy Mondal
Traditional time-series classification methods often operate as black boxes, providing a class prediction without indicating which time point or time interval within the series led to that prediction. To improve temporal interpretability, MILLET (Multiple Instance Learning with Temporal Explanation), which combines an InceptionTime encoder with Conjunctive Pooling, provides both classification and temporal explanations. However, MILLET contains approximately 424 K parameters, making it unsuitable for deployment on resource-constrained micro-controllers, and it achieves an overall time-series accuracy of 0.888 and an explanation score of 0.681 NDCG@n. We therefore propose SEA-Net, a lightweight architecture using small multi-scale depthwise-separable convolutional TSC encoders and improved Multiple Instance Learning (MIL) pooling heads. Our SEA-Net bottleneck encoder with Top-k pooling achieves 0.931 accuracy and 0.765 NDCG@n with only 41 K parameters. Another variant, using a gated encoder with Top-k pooling, achieves 0.955 accuracy and 0.750 NDCG@n with 62 K parameters. These results demonstrate that lightweight architectures can maintain strong classification performance and…
PDF arXiv
arXiv cs.AIOct 12
An FPGA-Based Spiking Neural Network for Spatiotemporal Pattern Learning and Classification
Jingang Jin, Yue Ma, Zhenhang Zhang, Qinru Qiu
Spiking Neural Networks (SNNs) are promising for energy-efficient spatiotemporal pattern recognition at the edge, but efficient deployment and on-device adaptation require specialized hardware. In this work, we present an FPGA implementation of multilayer SNNs for spatiotemporal pattern classification, in which both inference and training take place on the same hardware. Our design adopts a temporal-forward-only training algorithm that avoids the memory and latency overhead associated with traditional Backpropagation Through Time (BPTT). A mixed-precision scheme balances training stability with resource efficiency, and architectural optimization maximizes hardware and memory utilization. We further identify and resolve hazards that arise when inference and learning share the same memory, including port conflicts between the forward and backward access patterns and read-after-write dependencies in floating-point potential accumulation. Experimental evaluations on MNIST and five multivariate time-series classification datasets demonstrate that, with fully on-chip training, our SNN model achieves accuracy comparable to SNN or LSTM trained with BPTT. Compared to CPU and GPU based…
PDF arXiv
arXiv cs.ETOct 12
Neuromorphic Decoding and Dynamical Image Reconstruction from Populations of Spiking Retinal Ganglion Cells
Ning Zhang, Arto Nurmikko
Decoding visual stimuli from the spiking activity of retinal ganglion cells (RGCs) informs both our understanding of the retinal code and the design of visual prostheses. Natural vision is dynamic, yet state-of-the-art decoders mostly reconstruct single frames with artificial neural networks that process dense, continuous-valued signals rather than the retina's sparse, asynchronous spikes. We asked whether dynamic scenes can be reconstructed and tracked entirely within the spike domain, and at what computational cost. We built an end-to-end spiking neural network (SNN) whose neurons integrate the recorded RGC spikes over time. Populations of up to 1836 RGCs were recorded ex vivo from mouse retina on high-density microelectrode arrays while flashed images, moving bars, drifting gratings and randomly moving handwritten digits were presented. For moving digits, one shared spiking encoder fed two readouts, one reconstructing the image and one decoding the digit's position. Compute energy was estimated from counted synaptic operations. The SNN decoded what and where at once. It reconstructed the stimuli with a structural similarity (SSIM) of up to 0.93, refining the reconstruction as…
PDF arXiv

Papers

Topics in this field

efficient spiking neural · spiking neural networks · networks spiking neural39 papers2 this week

★ Spotlight this month

arXiv cs.CVOct 15

The Dormant Spiking Neuron: A State-Driven Mechanism for Efficient Spiking Neural Networks

Ruichen Ma, Yicai Chen, Pujun Zhou, Yue Zuo, Chongyang Li +3

Spiking neural networks (SNNs) offer a compelling pathway toward energy-efficient artificial intelligence, fundamentally anchored in presynaptic input-driven sparsity. However, a substantial yet chronically overlooked source of computational overhead persists: the continuous subthreshold dynamics of postsynaptic neurons. Quantitative analysis reveals that up to 44% of neurons in an ImageNet-trained ResNet-18 model reside in a deeply inhibited state, imposing a persistent computational burden despite having a negligible probability of firing. To address this inefficiency, the Dormant Spiking Neuron (DSN) model is introduced. By incorporating a state-driven dynamic gate, the DSN allows a neuron to enter a dormant state when its membrane potential falls below a predefined negative threshold, dynamically pruning redundant computations at the instance level. Crucially, this dormancy mechanism is directly integrated into the neuronal dynamics and trained end-to-end via backpropagation through time using surrogate gradients, enabling the network to actively learn a robust dormancy policy that adaptively preserves critical information flow. Extensive experiments across static and…

PDF arXiv page Details

Active contributors · 90 days

Recent papers

All in Research →

arXiv cs.NEOct 16
SpikeQ: Spike-Guided Post-Training Quantization for Spiking Neural Networks
Kai Sun, Peibo Duan, Zhanglu Yan, Guowei Zhang, Yongsheng Huang +1
On neuromorphic chips, spiking neural networks (SNNs) consume far less energy than artificial neural networks (ANNs), but the limited memory of these chips requires low-bit synaptic weights and membrane potentials. Existing post-training quantization (PTQ) methods provide them without retraining and, like those for ANNs, minimize numerical errors such as the mean squared error (MSE). In an SNN, however, a quantization error reaches later layers only through the spikes it flips. We find that errors of equal MSE can cause very different accuracy losses, whereas errors that flip the same fraction of spikes cause the same loss. We therefore propose SpikeQ, a spike-guided PTQ framework. For weights, we select the level of each weight by simulating the downstream neurons and minimizing their spike errors. For membrane potentials, most existing methods quantize the state after the reset, whereas neuromorphic chips compare the threshold with the membrane potential stored at a fixed bit width. We target this pre-fire quantization and build a reset-aware grid that places the threshold on a rounding boundary, so rounding never flips the spike at the current time step. We evaluate SpikeQ on…
PDF arXiv
arXiv cs.CVOct 15
The Dormant Spiking Neuron: A State-Driven Mechanism for Efficient Spiking Neural Networks
Ruichen Ma, Yicai Chen, Pujun Zhou, Yue Zuo, Chongyang Li +3
Spiking neural networks (SNNs) offer a compelling pathway toward energy-efficient artificial intelligence, fundamentally anchored in presynaptic input-driven sparsity. However, a substantial yet chronically overlooked source of computational overhead persists: the continuous subthreshold dynamics of postsynaptic neurons. Quantitative analysis reveals that up to 44% of neurons in an ImageNet-trained ResNet-18 model reside in a deeply inhibited state, imposing a persistent computational burden despite having a negligible probability of firing. To address this inefficiency, the Dormant Spiking Neuron (DSN) model is introduced. By incorporating a state-driven dynamic gate, the DSN allows a neuron to enter a dormant state when its membrane potential falls below a predefined negative threshold, dynamically pruning redundant computations at the instance level. Crucially, this dormancy mechanism is directly integrated into the neuronal dynamics and trained end-to-end via backpropagation through time using surrogate gradients, enabling the network to actively learn a robust dormancy policy that adaptively preserves critical information flow. Extensive experiments across static and…
PDF arXiv
arXiv cs.LGOct 13
Saliency-Guided Replay for Continual Learning in Deep Spiking Neural Networks
Francesco Panetta, Federico Di Valerio, Michela Proietti
Spiking Neural Networks (SNNs) are promising for energy-efficient neuromorphic computing, but they still suffer from catastrophic forgetting when learning tasks sequentially. This work investigates the integration of Experience Packing and Replay (EPR) as a memory-efficient continual learning strategy for deep SNNs under low-latency constraints. The proposed framework combines Batch Normalization Through Time stabilized VGG9 SNNs with Spike Activation Maps (SAM), which provide forward-only explanations based on spike activity. These explanations are temporally aggregated into spatial attention maps and used to select the most informative image patches for replay, instead of storing full images. Experiments on Split CIFAR10 and Split CIFAR100 show that SAM-guided EPR improves the accuracy-memory trade-off under tight memory budgets, and remains competitive while requiring substantially less storage.
PDF arXiv
arXiv cs.LGOct 13
Sea-Net: A Small and Inherently Interpretable Neural Network for Time Series Classification
Ubaid Ur Rehman, Tanmoy Mondal
Traditional time-series classification methods often operate as black boxes, providing a class prediction without indicating which time point or time interval within the series led to that prediction. To improve temporal interpretability, MILLET (Multiple Instance Learning with Temporal Explanation), which combines an InceptionTime encoder with Conjunctive Pooling, provides both classification and temporal explanations. However, MILLET contains approximately 424 K parameters, making it unsuitable for deployment on resource-constrained micro-controllers, and it achieves an overall time-series accuracy of 0.888 and an explanation score of 0.681 NDCG@n. We therefore propose SEA-Net, a lightweight architecture using small multi-scale depthwise-separable convolutional TSC encoders and improved Multiple Instance Learning (MIL) pooling heads. Our SEA-Net bottleneck encoder with Top-k pooling achieves 0.931 accuracy and 0.765 NDCG@n with only 41 K parameters. Another variant, using a gated encoder with Top-k pooling, achieves 0.955 accuracy and 0.750 NDCG@n with 62 K parameters. These results demonstrate that lightweight architectures can maintain strong classification performance and…
PDF arXiv
arXiv cs.AIOct 12
An FPGA-Based Spiking Neural Network for Spatiotemporal Pattern Learning and Classification
Jingang Jin, Yue Ma, Zhenhang Zhang, Qinru Qiu
Spiking Neural Networks (SNNs) are promising for energy-efficient spatiotemporal pattern recognition at the edge, but efficient deployment and on-device adaptation require specialized hardware. In this work, we present an FPGA implementation of multilayer SNNs for spatiotemporal pattern classification, in which both inference and training take place on the same hardware. Our design adopts a temporal-forward-only training algorithm that avoids the memory and latency overhead associated with traditional Backpropagation Through Time (BPTT). A mixed-precision scheme balances training stability with resource efficiency, and architectural optimization maximizes hardware and memory utilization. We further identify and resolve hazards that arise when inference and learning share the same memory, including port conflicts between the forward and backward access patterns and read-after-write dependencies in floating-point potential accumulation. Experimental evaluations on MNIST and five multivariate time-series classification datasets demonstrate that, with fully on-chip training, our SNN model achieves accuracy comparable to SNN or LSTM trained with BPTT. Compared to CPU and GPU based…
PDF arXiv
arXiv cs.ETOct 12
Neuromorphic Decoding and Dynamical Image Reconstruction from Populations of Spiking Retinal Ganglion Cells
Ning Zhang, Arto Nurmikko
Decoding visual stimuli from the spiking activity of retinal ganglion cells (RGCs) informs both our understanding of the retinal code and the design of visual prostheses. Natural vision is dynamic, yet state-of-the-art decoders mostly reconstruct single frames with artificial neural networks that process dense, continuous-valued signals rather than the retina's sparse, asynchronous spikes. We asked whether dynamic scenes can be reconstructed and tracked entirely within the spike domain, and at what computational cost. We built an end-to-end spiking neural network (SNN) whose neurons integrate the recorded RGC spikes over time. Populations of up to 1836 RGCs were recorded ex vivo from mouse retina on high-density microelectrode arrays while flashed images, moving bars, drifting gratings and randomly moving handwritten digits were presented. For moving digits, one shared spiking encoder fed two readouts, one reconstructing the image and one decoding the digit's position. Compute energy was estimated from counted synaptic operations. The SNN decoded what and where at once. It reconstructed the stimuli with a structural similarity (SSIM) of up to 0.93, refining the reconstruction as…
PDF arXiv

Activity · 12 weeks

Coming with more sources: repos

Fields · AI · updated 27m ago

Efficient spiking neural

Found by the topic model: efficient spiking neural.

2papers this week−85.7% vs last week

All papers · 39 With code · 0

Newest Most relevant

36 papers this month

Open problems in Efficient spiking neural

Efficient quantization for spiking neural networks1 paper raises it · 1 addresses it
Low-bit weights and membrane potentials are needed for neuromorphic hardware but existing PTQ methods ignore spike-specific errors.
- SpikeQ: Spike-Guided Post-Training Quantization for Spiking Neural Networksraises · addresses
Redundant subthreshold computation in SNNs1 paper raises it · 1 addresses it
Postsynaptic neurons in subthreshold states waste computation despite low firing probability.
- The Dormant Spiking Neuron: A State-Driven Mechanism for Efficient Spiking Neural Networksraises · addresses
Catastrophic forgetting in continual learning for SNNs1 paper raises it · 1 addresses it
SNNs suffer from accuracy loss when learning tasks sequentially under memory constraints.
- Saliency-Guided Replay for Continual Learning in Deep Spiking Neural Networksraises · addresses
Hardware-aware training and inference for SNNs1 paper raises it · 2 address it
Efficient on-device deployment requires specialized hardware and training methods to avoid memory and latency overhead.
- An FPGA-Based Spiking Neural Network for Spatiotemporal Pattern Learning and Classificationraises · addresses
- Removing the Compute Bottleneck for Event-based Visual Place Recognition with Spiking Neural Networksaddresses
Accuracy gap in spiking language models1 paper raises it · 1 addresses it
Spiking language models lag behind dense models in accuracy, with a persistent loss gap even at scale.
- Compute-Optimal Scaling Laws for Spiking Language Modelsraises · addresses

Named by an AI from these papers' abstracts.