Despite spiking neural networks (SNNs) have demonstrated notable energy efficiency across various fields, the limited firing patterns of spiking neurons within fixed time steps restrict the expression of information, ...
In the domain of space-time video super-resolution, it is typically challenging to handle complex motions (including large and nonlinear motions) and varying illumination scenes due to the lack of inter-frame informat...
Although existing fMRI-to-image reconstruction methods could predict high-quality images, they do not explicitly consider the semantic gap between training and testing data, resulting in reconstruction with unstable a...
详细信息
High Dynamic Range (HDR) video reconstruction seeks to accurately restore the extensive dynamic range present in real-world scenes and is widely employed in downstream applications. Existing methods typically operate ...
详细信息
The precise movement speed regulation is a key factor to improve the control effect and efficiency of the cyborg ***,the current stimulation techniques cannot realize the graded control of the *** this study,we achiev...
详细信息
The precise movement speed regulation is a key factor to improve the control effect and efficiency of the cyborg ***,the current stimulation techniques cannot realize the graded control of the *** this study,we achieved the multi-level speed regulation of cyborg rats in the large open field and treadmill by specifically targeting the Cuneiform Nucleus(CnF)of the Mesencephalic Locomotor Region(MLR).Detailed,we measured the influence of each stimulation parameter on the speed control process which included the real-time speed,accelerated speed,response time,and acceleration *** concluded that the pulse period and the pulse width were the main determinants influencing the accelerated speed of cyborg *** the amplitude of stimulation was found to affect the response time exhibited by the cyborg *** study provides valuable insights into the regulation of rat locomotion speed and highlights the potential for utilizing this approach in various experimental settings.
Denoising diffusion probabilistic models (DDPMs) have gained popularity in devising neural vocoders and obtained outstanding performance. However, existing DDPM-based neural vocoders struggle to handle the prosody div...
详细信息
Neural decoding, which transforms neural signals into motor commands, plays a key role in brain-computer interfaces (BCIs). Existing neural decoding approaches mainly rely on the assumption of independent noises, whic...
Recovering the foreground color and opacity/alpha matte from a single image (i.e., image matting) is a challenging and ill-posed problem where data priors play a critical role in achieving precise results. Due to the ...
A key aspect of Safe Reinforcement Learning (Safe RL) involves estimating the constraint condition for the next policy, which is crucial for guiding the optimization of safe policy updates. However, the existing Advan...
详细信息
A key aspect of Safe Reinforcement Learning (Safe RL) involves estimating the constraint condition for the next policy, which is crucial for guiding the optimization of safe policy updates. However, the existing Advantage-based Estimation (ABE) method relies on the infinite-horizon discounted advantage function. This dependence leads to catastrophic errors in finite-horizon scenarios with non-discounted constraints, resulting in safety-violation updates. In response, we propose the first estimation method for finite-horizon non-discounted constraints in deep Safe RL, termed Gradient-based Estimation (GBE), which relies on the analytic gradient derived along trajectories. Our theoretical and empirical analyses demonstrate that GBE can effectively estimate constraint changes over a finite horizon. Constructing a surrogate optimization problem with GBE, we developed a novel Safe RL algorithm called Constrained Gradient-based Policy Optimization (CGPO). CGPO identifies feasible optimal policies by iteratively resolving sub-problems within trust regions. Our empirical results reveal that CGPO, unlike baseline algorithms, successfully estimates the constraint functions of subsequent policies, thereby ensuring the efficiency and feasibility of each update. Copyright 2024 by the author(s)
Spiking neural networks(SNNs) are gaining increasing attention for their biological plausibility and potential for improved computational efficiency. To match the high spatial-temporal dynamics in SNNs,neuromorphic ch...
详细信息
Spiking neural networks(SNNs) are gaining increasing attention for their biological plausibility and potential for improved computational efficiency. To match the high spatial-temporal dynamics in SNNs,neuromorphic chips are highly desired to execute SNNs in hardware-based neuron and synapse circuits directly. This paper presents a large-scale neuromorphic chip named Darwin3 with a novel instruction set architecture, which comprises 10 primary instructions and a few extended instructions. It supports flexible neuron model programming and local learning rule designs. The Darwin3 chip architecture is designed in a mesh of computing nodes with an innovative routing algorithm. We used a compression mechanism to represent synaptic connections, significantly reducing memory usage. The Darwin3 chip supports up to2.35 million neurons, making it the largest of its kind on the neuron scale. The experimental results showed that the code density was improved by up to 28.3× in Darwin3, and that the neuron core fan-in and fan-out were improved by up to 4096× and 3072× by connection compression compared to the physical memory depth. Our Darwin3 chip also provided memory saving between 6.8× and 200.8× when mapping convolutional spiking neural networks onto the chip, demonstrating state-of-the-art performance in accuracy and latency compared to other neuromorphic chips.
暂无评论