arXiv subjects

Jongkil Park

Publications and source records attributed to Jongkil Park.

6 recordsLinked to original sources

arXiv2026

A2SG:Adaptive and Asymmetric Surrogate Gradients for Training Deep Spiking Neural Networks

Training deep spiking neural networks (SNNs) remains challenging due to sharp loss landscapes and temporal inconsistency caused by surrogate gradients. To address these challenges, we propose a unified framework: adaptive and asymmetric surrogate gradients A2SG. The adaptive gradients adjust an effective window for spatio-temporal adaptation, reducing spatial gradient variation and maintaining directional consistency of gradients over time. The asymmetric gradients reflect neuronal dynamics by assigning larger gradients to neurons with higher membrane potentials, and we prove that they yield lower variation than symmetric surrogates. Our analysis further establishes a direct connection between local gradient variation and the curvature of the loss landscape, providing a principled explanation for how A2SG promotes convergence to flatter minima and improves generalization. We conduct extensive experiments on diverse models, including CNN-based and Transformer-based SNNs, across various tasks such as image classification using both static and neuromorphic datasets, as well as segmentation. The results demonstrate that A2SG consistently improves accuracy and energy efficiency, establishing it as a general and reliable solution for training deep SNNs. Our code is available at https://github.com/KIST-NCL/A2SG.git.

cs.NE↗

arXiv2025

Ovonic switches enable energy-efficient dendrite-like computing

Over the last decade, dendrites within individual biological neurons, which were previously thought to generally perform information pooling and networking, have now been shown to express complex temporal dynamics, Boolean-like logic, arithmetic, signal discrimination, and edge detection for image and sound recognition. Mimicking this rich functional density could offer a powerful primitive for neuromorphic computing, which has sought to replace the aging digital computing paradigms using biological inspirations. Here, using electrically driven Ovonic threshold switching in Sb-Te-doped GeSe, we demonstrate a single two-terminal component capable of self-sustained dynamics and universal Boolean logic, in addition to XOR operations (which is traditionally thought to require a network of active components). We then employ logic-driven dynamics in a single component to detect and estimate the gradients of edges in images, a task that otherwise requires elaborate circuits. A network of Ovonic switches exhibits properties of a half adder and a full adder, in addition to discriminative logic accommodating inhibitory and excitatory signals. We show that this computational primitive is not only seemingly simpler, but also offers many orders of magnitude improved energy efficiency compared to prevailing digital solutions. As such, this work paves the path for potentially emulating dendrites for efficient post-digital neuromorphic computing.

cs.ET↗

arXiv2025

NeuroBench: A Framework for Benchmarking Neuromorphic Computing Algorithms and Systems

Neuromorphic computing shows promise for advancing computing efficiency and capabilities of AI applications using brain-inspired principles. However, the neuromorphic research field currently lacks standardized benchmarks, making it difficult to accurately measure technological advancements, compare performance with conventional methods, and identify promising future research directions. Prior neuromorphic computing benchmark efforts have not seen widespread adoption due to a lack of inclusive, actionable, and iterative benchmark design and guidelines. To address these shortcomings, we present NeuroBench: a benchmark framework for neuromorphic computing algorithms and systems. NeuroBench is a collaboratively-designed effort from an open community of researchers across industry and academia, aiming to provide a representative structure for standardizing the evaluation of neuromorphic approaches. The NeuroBench framework introduces a common set of tools and systematic methodology for inclusive benchmark measurement, delivering an objective reference framework for quantifying neuromorphic approaches in both hardware-independent (algorithm track) and hardware-dependent (system track) settings. In this article, we outline tasks and guidelines for benchmarks across multiple application domains, and present initial performance baselines across neuromorphic and conventional approaches for both benchmark tracks. NeuroBench is intended to continually expand its benchmarks and features to foster and track the progress made by the research community.

cs.AI↗

arXiv2024

A More Accurate Approximation of Activation Function with Few Spikes Neurons

Recent deep neural networks (DNNs), such as diffusion models [1], have faced high computational demands. Thus, spiking neural networks (SNNs) have attracted lots of attention as energy-efficient neural networks. However, conventional spiking neurons, such as leaky integrate-and-fire neurons, cannot accurately represent complex non-linear activation functions, such as Swish [2]. To approximate activation functions with spiking neurons, few spikes (FS) neurons were proposed [3], but the approximation performance was limited due to the lack of training methods considering the neurons. Thus, we propose tendency-based parameter initialization (TBPI) to enhance the approximation of activation function with FS neurons, exploiting temporal dependencies initializing the training parameters.

cs.NE↗

arXiv2023

Gradient Scaling on Deep Spiking Neural Networks with Spike-Dependent Local Information

Deep spiking neural networks (SNNs) are promising neural networks for their model capacity from deep neural network architecture and energy efficiency from SNNs' operations. To train deep SNNs, recently, spatio-temporal backpropagation (STBP) with surrogate gradient was proposed. Although deep SNNs have been successfully trained with STBP, they cannot fully utilize spike information. In this work, we proposed gradient scaling with local spike information, which is the relation between pre- and post-synaptic spikes. Considering the causality between spikes, we could enhance the training performance of deep SNNs. According to our experiments, we could achieve higher accuracy with lower spikes by adopting the gradient scaling on image classification tasks, such as CIFAR10 and CIFAR100.

cs.NE↗

arXiv2020

Frequency-tunable nano-oscillator based on Ovonic Threshold Switch (OTS)

Nano-oscillator devices are gaining more and more attention as a prerequisite for developing novel energy-efficient computing systems based on coupled oscillators. Here, we introduce a highly scalable, frequency-tunable nano-oscillator consisting of one Ovonic threshold switch (OTS) and a field-effect transistor (FET). It is presented that the proposed device shows an oscillating behavior with a natural frequency (f_{nat}) adjustable from 0.5 to 2 MHz depending on the gate voltage applied to the FET. In addition, under a small periodic input, it is observed that the oscillating frequency (f_{osc}) of the device is locked to the frequency (f_{in}) of the input when f_{in} ~ f_{nat}, demonstrating the so-called synchronization phenomenon. It also shows the phase lock of the combined oscillator network using circuit simulation, where the phase relation between the oscillators can be controlled by the coupling strength. These results imply that the proposed device is promising for applications in oscillator-based computing systems.

cond-mat.mtrl-sci↗