Kangyou Bao

Kangyou Bao


Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
16 October 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
EBEunhye Baek
Eunhye Baek
QZQingtian Zhang
Qingtian Zhang
TAThomas Adler
Thomas Adler
KBKangyou Bao
Kangyou Bao
ZRZhao Rong
Zhao Rong
Carlo Vittorio CannistraciCarlo Vittorio Cannistraci
Carlo Vittorio Cannistraci
Neuromorphic AI increasingly draws on sparse dendritic computation, yet a network-science framework linking sub-neuronal circuit organization to function remains underdeveloped. Here we introduce the neural processing component (NPC) paradigm, representing synapses, dendrites, somata and axons as network elements whose sparse topology shapes computation. We implement this paradigm in a dendritic reservoir-based network for trajectory detection, demonstrating in device-informed simulations that real-time motion trajectories can be detected through fixed NPC design rather than training. Using hyperbolic network geometry, we reveal that NPC neuromorphic circuits with dendrites possess latent hierarchical and modular organization that is not visible from circuit diagrams alone. We further show that this geometric representation identifies vulnerable modules and critical routing nodes that can be selectively redesigned, reducing detection error under router-node failure by 50.9%. These results establish NPC network geometry as a method for circuit-level interpretability androbustness-oriented design of sparse neuromorphic AI.

21 August 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
KBKangyou Bao
Kangyou Bao
WGWenqi Gu
Wenqi Gu
JLjiaqing lyu
jiaqing lyu
XDXizheng Deng
Xizheng Deng
Carlo Vittorio CannistraciCarlo Vittorio Cannistraci
Carlo Vittorio Cannistraci
ANN-to-SNN conversion is an important approach for obtaining high-performance spiking neural networks (SNNs), yet current conversion methodologies predominantly focus on dense architectures, overlooking the struc- tural sparsity that characterizes biological neural systems. In this work, we propose a sparse ANN-to-SNN conversion framework that inherits learned sparse topology into SNNs. We instantiate this framework with Cannistraci-Hebb Training (CHT), a brain-inspired dynamic sparse training method. Across CNN experiments on CIFAR-10, CIFAR-100, and DVSGesture, and ViT experiments on ImageNet-1K, SNNs produced by our framework achieve near-dense performance while outperforming SNNs obtained from static pruning and sparse- training baselines in accuracy. Compared with dense SNN counterparts in the principal CIFAR and ImageNet comparisons, our framework also substantially reduces energy consumption. Beyond these accuracy-efficiency gains, the resulting sparse SNNs are characterized by biologically plausible structural properties, including meta- depth and scale-free organization. These results suggest that learned sparse topology is a useful design dimension for ANN-to-SNN conversion, enabling high-accuracy sparse SNNs with substantially reduced energy consumption.