Picture for Jing Pei

Jing Pei

Unveiling the Potential of Spiking Dynamics in Graph Representation Learning through Spatial-Temporal Normalization and Coding Strategies

Add code
Jul 30, 2024
Figure 1 for Unveiling the Potential of Spiking Dynamics in Graph Representation Learning through Spatial-Temporal Normalization and Coding Strategies
Figure 2 for Unveiling the Potential of Spiking Dynamics in Graph Representation Learning through Spatial-Temporal Normalization and Coding Strategies
Figure 3 for Unveiling the Potential of Spiking Dynamics in Graph Representation Learning through Spatial-Temporal Normalization and Coding Strategies
Figure 4 for Unveiling the Potential of Spiking Dynamics in Graph Representation Learning through Spatial-Temporal Normalization and Coding Strategies
Viaarxiv icon

Enhancing Graph Representation Learning with Attention-Driven Spiking Neural Networks

Add code
Mar 25, 2024
Figure 1 for Enhancing Graph Representation Learning with Attention-Driven Spiking Neural Networks
Figure 2 for Enhancing Graph Representation Learning with Attention-Driven Spiking Neural Networks
Figure 3 for Enhancing Graph Representation Learning with Attention-Driven Spiking Neural Networks
Figure 4 for Enhancing Graph Representation Learning with Attention-Driven Spiking Neural Networks
Viaarxiv icon

Understanding the Functional Roles of Modelling Components in Spiking Neural Networks

Add code
Mar 25, 2024
Viaarxiv icon

Exploiting Spiking Dynamics with Spatial-temporal Feature Normalization in Graph Learning

Add code
Jun 30, 2021
Figure 1 for Exploiting Spiking Dynamics with Spatial-temporal Feature Normalization in Graph Learning
Figure 2 for Exploiting Spiking Dynamics with Spatial-temporal Feature Normalization in Graph Learning
Figure 3 for Exploiting Spiking Dynamics with Spatial-temporal Feature Normalization in Graph Learning
Figure 4 for Exploiting Spiking Dynamics with Spatial-temporal Feature Normalization in Graph Learning
Viaarxiv icon

Brain-inspired global-local hybrid learning towards human-like intelligence

Add code
Jun 05, 2020
Figure 1 for Brain-inspired global-local hybrid learning towards human-like intelligence
Figure 2 for Brain-inspired global-local hybrid learning towards human-like intelligence
Figure 3 for Brain-inspired global-local hybrid learning towards human-like intelligence
Figure 4 for Brain-inspired global-local hybrid learning towards human-like intelligence
Viaarxiv icon

Adversarial symmetric GANs: bridging adversarial samples and adversarial networks

Add code
Jan 01, 2020
Figure 1 for Adversarial symmetric GANs: bridging adversarial samples and adversarial networks
Figure 2 for Adversarial symmetric GANs: bridging adversarial samples and adversarial networks
Figure 3 for Adversarial symmetric GANs: bridging adversarial samples and adversarial networks
Figure 4 for Adversarial symmetric GANs: bridging adversarial samples and adversarial networks
Viaarxiv icon

Transfer Learning in General Lensless Imaging through Scattering Media

Add code
Dec 28, 2019
Figure 1 for Transfer Learning in General Lensless Imaging through Scattering Media
Figure 2 for Transfer Learning in General Lensless Imaging through Scattering Media
Figure 3 for Transfer Learning in General Lensless Imaging through Scattering Media
Figure 4 for Transfer Learning in General Lensless Imaging through Scattering Media
Viaarxiv icon

GXNOR-Net: Training deep neural networks with ternary weights and activations without full-precision memory under a unified discretization framework

Add code
May 02, 2018
Figure 1 for GXNOR-Net: Training deep neural networks with ternary weights and activations without full-precision memory under a unified discretization framework
Figure 2 for GXNOR-Net: Training deep neural networks with ternary weights and activations without full-precision memory under a unified discretization framework
Figure 3 for GXNOR-Net: Training deep neural networks with ternary weights and activations without full-precision memory under a unified discretization framework
Figure 4 for GXNOR-Net: Training deep neural networks with ternary weights and activations without full-precision memory under a unified discretization framework
Viaarxiv icon