Delay tolerant networks may become unexpectedly partitioned due to node mobility or variation in signal strength. However, most widely used models in some relative works are generally very simplistic. In order to expl...
详细信息
Delay tolerant networks may become unexpectedly partitioned due to node mobility or variation in signal strength. However, most widely used models in some relative works are generally very simplistic. In order to exploit intelligent forwarding algorithms, a novel nodal mobile model of delay tolerant networks is presented to map reality with more accuracy. And several approaches are introduced to analyze the network structure, such as n-cliques, n-clans, degree, closeness and betweenness. Our research results showed that the centralizations became smaller when the wireless connections were concerned. It meant that quite a number of nodes became potential relays because of the new structure of networks.
Network sparsity or pruning is an extensively studied method to optimize the computation efficiency of deep neural networks (DNNs) for CMOS-based accelerators, such as FPGAs and GPUs. Though the RRAM-based accelerator...
详细信息
ISBN:
(纸本)9781665432740
Network sparsity or pruning is an extensively studied method to optimize the computation efficiency of deep neural networks (DNNs) for CMOS-based accelerators, such as FPGAs and GPUs. Though the RRAM-based accelerator has demonstrated superior performance and energy efficiency for DNN tasks, deploying the sparse neural networks desires dedicated consideration to save resource consumption without introducing the expensive index overhead and sophisticated control. To exploit the potential of sparse neural network design on the RRAM-based accelerator, we propose an automatic structured bit-pruning design, ASBP, to harmonize the optimization objective of DNN sparsity with efficient RRAM deployment. Specifically, ASBP prunes the bits of weight which are split into different crossbars and thus, free the zero-value crossbar when mapping the neural network into RRAM-based accelerators without extra hardware modification. Meanwhile, ASBP employs the reinforcement learning (RL) approach to automatically select the best crossbar-aware bit-sparsity strategy for any given neural network without laborious human efforts. According to our experiments on a set of representative neural networks, ASBP saves up to 79.01% energy consumption and 54.79% area overhead compared to the baseline that deploys the original DNN on the RRAM-based accelerator. Besides, ASBP outperforms the state-of-the-art bit-sparsity design by 1.4x in terms of the energy reduction on the RRAM-based accelerator.
Matrix computing plays a vital role in many scientific and engineering applications, but previous work can only handle the data with specified precision based on FPGA. This study first presents algorithms, data flows,...
详细信息
The capability of a robot to perform tasks depends not only on precise motion control, but also on a well-suited body morphology. Adapting both morphology and control of robots to improve their task performance has be...
The capability of a robot to perform tasks depends not only on precise motion control, but also on a well-suited body morphology. Adapting both morphology and control of robots to improve their task performance has been a widely studied and long-standing issue. While the bio-inspired bi-level optimization framework has gained popularity in recent years, it suffers from high computation complexity due to the time-consuming and inefficient learning process for each morphology. In fact, in nature, besides the adaptive morphology and the intelligent brain, animals also possess an important gift, which is physical instinct. These instincts allow animals to respond quickly to their surroundings in the neonatal period, facilitating skills acquisition. Inspired by this, we propose an evolvable instinct controller to enhance the morphology-control co-adaption. The instinct controller suggests rough motion inclinations, which require minimal domain knowledge and entail less sophisticated design. Its purpose is to assist the main controller in learning fine-grained and robust control efficiently. We implemented this idea in the context of legged locomotion and designed the instinct controller using phase-based FSMs. We propose the instinct-based co-adaption algorithm and construct GPU parallel simulation experiments on different morphology prototypes. The results indicate that combining the co-adaption process with instinct evolution leads to the development of superior morphologies and robust controllers compared with the conventional co-adaption approach, with minimal additional time cost.
In many realistic scenarios, it is necessary but challenging to acquire a large number of annotated radar emitter samples for training a recognition model. This study proposes a cross-domain radar emitter recognition ...
In many realistic scenarios, it is necessary but challenging to acquire a large number of annotated radar emitter samples for training a recognition model. This study proposes a cross-domain radar emitter recognition method with few-shot learning, which introduces model-agnostic meta-learning (MAML) to recognize radar emitter and improves it to adapt to various types of radar emitter in different domains without spending a lot of time and data to retrain the model. This method can learn an ideal initialization parameter with a few source domain samples, and then initialize with this parameter on a completely different target domain. It can obtain good generalization effect by fine-tuning with fewer samples, so as to realize cross-domain recognition of radar emitter. Simulation results show that the accuracy of the proposed method can reach more than 90% in high-noise target domains with completely different data distribution from the source domain, which shows its superiority in recognition performance and sample size compared with other radar emitter recognition methods.
Deep reinforcement learning (DRL) has greatly improved the intelligence of AI in recent years and the community has proposed several common software to facilitate the development of DRL. However, in robotics the utili...
详细信息
Edge visual systems demand high energy-efficiency vision processors like neuromorphic hardware leveraging spikebased computations. But their disability of directly interacting with non-spike information in the real wo...
详细信息
Transformer-based trackers have achieved promising success and become the dominant tracking paradigm because of their accuracy and efficiency. Despite the substantial progress, most of the existing approaches handle o...
详细信息
Transformer-based trackers have achieved promising success and become the dominant tracking paradigm because of their accuracy and efficiency. Despite the substantial progress, most of the existing approaches handle object tracking as a deterministic coordinate regression problem, while the target localization uncertainty has been largely overlooked, which hampers trackers’ ability to maintain reliable target state prediction in challenging scenarios. To address this issue, we propose UncTrack, a novel uncertainty-aware transformer-based tracker that predicts the target localization uncertainty and incorporates this uncertainty information for accurate target state inference. Specifically, UncTrack uses a transformer encoder to perform feature interactions between the template and search images. The output features are passed into an uncertainty-aware localization decoder (ULD) to coarsely predict the corner-based localization and the corresponding localization uncertainty. Then, the localization uncertainty is sent into a prototype memory network (PMN) to excavate valuable historical information to identify whether the target state prediction is reliable. To enhance the template representation, the samples with high confidence are fed back into the prototype memory bank for memory updating, which makes the tracker more robust to challenging appearance variations. Extensive experiments demonstrate that our method outperforms the state-of-the-art methods. Our code is available at https://***/ManOfStory/UncTrack
The rapid advancements in artificial intelligence(AI)are catalyzing transformative changes in atomic modeling,simulation,and ***-driven potential energy models havedemonstrated the capability to conduct large-scale,lo...
详细信息
The rapid advancements in artificial intelligence(AI)are catalyzing transformative changes in atomic modeling,simulation,and ***-driven potential energy models havedemonstrated the capability to conduct large-scale,long-duration simulations with the accuracy of ab initio electronic structure ***,the model generation process remains a bottleneck for large-scale *** propose a shift towards a model-centric ecosystem,wherein a large atomic model(LAM),pretrained across multiple disciplines,can be efficiently fine-tuned and distilled for various downstream tasks,thereby establishing a new framework for molecular *** this study,we introduce the DPA-2 architecture as a prototype for ***-trained on a diverse array of chemical and materials systemsusing a multi-task approach,DPA-2demonstrates superior generalization capabilities across multiple downstream tasks compared to the traditional single-task pre-training and fine-tuning *** approach sets the stage for the development and broad application of LAMs in molecular and materials simulation research.
In ophthalmology, early fundus screening is an economic and effective way to prevent blindness caused by ophthalmic diseases. Clinically, due to the lack of medical resources, manual diagnosis is time-consuming and ma...
详细信息
暂无评论