Search Results for author: Yuanpei Chen

Found 17 papers, 9 papers with code

Take A Shortcut Back: Mitigating the Gradient Vanishing for Training Spiking Neural Networks

no code implementations9 Jan 2024 Yufei Guo, Yuanpei Chen

However, training an SNN directly poses a challenge due to the undefined gradient of the firing spike process.

Ternary Spike: Learning Ternary Spikes for Spiking Neural Networks

1 code implementation11 Dec 2023 Yufei Guo, Yuanpei Chen, Xiaode Liu, Weihang Peng, Yuhan Zhang, Xuhui Huang, Zhe Ma

To handle the problem, we propose a ternary spike neuron to transmit information.

Sequential Dexterity: Chaining Dexterous Policies for Long-Horizon Manipulation

no code implementations2 Sep 2023 Yuanpei Chen, Chen Wang, Li Fei-Fei, C. Karen Liu

However, the challenges arise due to the high-dimensional action space of dexterous hand and complex compositional dynamics of the long-horizon tasks.

Reinforcement Learning (RL)

NeuroCLIP: Neuromorphic Data Understanding by CLIP and SNN

1 code implementation21 Jun 2023 Yufei Guo, Yuanpei Chen, Zhe Ma

However, the neuromorphic data consists of asynchronous event spikes, which makes it difficult to construct a big benchmark to train a power general neural network model, thus limiting the neuromorphic data understanding for ``unseen" objects by deep learning.

Few-Shot Learning

Joint A-SNN: Joint Training of Artificial and Spiking Neural Networks via Self-Distillation and Weight Factorization

no code implementations3 May 2023 Yufei Guo, Weihang Peng, Yuanpei Chen, Liwen Zhang, Xiaode Liu, Xuhui Huang, Zhe Ma

In this paper, we propose a joint training framework of ANN and SNN, in which the ANN can guide the SNN's optimization.

Real Spike: Learning Real-valued Spikes for Spiking Neural Networks

1 code implementation13 Oct 2022 Yufei Guo, Liwen Zhang, Yuanpei Chen, Xinyi Tong, Xiaode Liu, YingLei Wang, Xuhui Huang, Zhe Ma

Motivated by this assumption, a training-inference decoupling method for SNNs named as Real Spike is proposed, which not only enjoys both unshared convolution kernels and binary spikes in inference-time but also maintains both shared convolution kernels and Real-valued Spikes during training.

End-to-End Affordance Learning for Robotic Manipulation

1 code implementation26 Sep 2022 Yiran Geng, Boshi An, Haoran Geng, Yuanpei Chen, Yaodong Yang, Hao Dong

Such contact prediction process then leads to an end-to-end affordance learning framework that can generalize over different types of manipulation tasks.

Reinforcement Learning (RL)

Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement Learning

1 code implementation17 Jun 2022 Yuanpei Chen, Tianhao Wu, Shengjie Wang, Xidong Feng, Jiechuang Jiang, Stephen Marcus McAleer, Yiran Geng, Hao Dong, Zongqing Lu, Song-Chun Zhu, Yaodong Yang

In this study, we propose the Bimanual Dexterous Hands Benchmark (Bi-DexHands), a simulator that involves two dexterous hands with tens of bimanual manipulation tasks and thousands of target objects.

Few-Shot Learning Offline RL +2

RecDis-SNN: Rectifying Membrane Potential Distribution for Directly Training Spiking Neural Networks

no code implementations CVPR 2022 Yufei Guo, Xinyi Tong, Yuanpei Chen, Liwen Zhang, Xiaode Liu, Zhe Ma, Xuhui Huang

Unfortunately, with the propagation of binary spikes, the distribution of membrane potential will shift, leading to degeneration, saturation, and gradient mismatch problems, which would be disadvantageous to the network optimization and convergence.


Cannot find the paper you are looking for? You can Submit a new open access paper.