7 Papers
1 Citations
Rui Yan is an academic researcher from Zhejiang University of Technology. The author has contributed to research in topics: Spiking neural network & Computer science. The author has an hindex of 1, co-authored 7 publications.
Chat about Author
Papers
Why grid cells function as a metric for space
TL;DR: In this article, the grid cell population codes can be taken as a metric for space, and the inner product of the grid cells population code exponentially converges to the kernel, which can be used for high-order nonspatial information.
14
Spike Trains Encoding Optimization for Spiking Neural Networks Implementation in FPGA
Biao Fang,Yuhao Zhang,Rui Yan,Huajin Tang +3 more
- 01 Aug 2020
TL;DR: To enable SNNs to process information about natural images, a method to accelerate the spikes encoding on the Field Programmable Gate Array (FPGA) is presented and a low-power implementation of real-time system for digital recognition using multi-kernels parallel (16PEs) is demonstrated.
13
Few-Shot Learning in Spiking Neural Networks by Multi-Timescale Optimization.
TL;DR: In this article, an adaptive-gated LSTM is proposed to accommodate two different timescales of neural dynamics: short-term learning and long-term evolution. But the LSTMs are not optimized to tune SNN parameters on a long timescale.
12
An Event-based Categorization Model Using Spatio-temporal Features in a Spiking Neural Network
Junwei Lu,Junfei Dong,Rui Yan,Huajin Tang +3 more
- 01 Aug 2020
TL;DR: An event-based categorization model that makes full use of the precise timing information inherently present in the output of a bio-inspired vision sensor and utilizes event-driven processing to keep the form of address event representation (AER) has been introduced.
8
Multi-Scale Extension in an Entorhinal-Hippocampal Model for Cognitive Map Building
Jiru Wang,Rui Yan,Huajin Tang +2 more
TL;DR: In this article, an optimized dynamical model of grid cells is built for path integration in which recurrent weight connections between grid cells are parameterized in a more optimized way and the nonlinearity of sigmoidal neural transfer function is utilized to enhance grid cell activity packets.