The attention mechanism has become a pivotal component in artificial intelligence, significantly enhancing the performance of deep learning applications. However, its quadratic computational complexity and intricate c...
详细信息
The attention mechanism has become a pivotal component in artificial intelligence, significantly enhancing the performance of deep learning applications. However, its quadratic computational complexity and intricate computations lead to substantial inefficiencies when processing long sequences. To address these challenges, we introduce Attar, a resistive random access memory(RRAM)-based in-memory accelerator designed to optimize attention mechanisms through software-hardware co-optimization. Attar leverages efficient Top-k pruning and quantization strategies to exploit the sparsity and redundancy of attention matrices, and incorporates an RRAM-based in-memory softmax engine by harnessing the versatility of the RRAM crossbar. Comprehensive evaluations demonstrate that Attar achieves a performance improvement of up to 4.88× and energy saving of 55.38% over previous computing-in-memory(CIM)-based accelerators across various models and datasets while maintaining comparable accuracy. This work underscores the potential of in-memory computing to enhance the efficiency of attention-based models without compromising their effectiveness.
Instance segmentation is a critical component of medical image analysis, enabling tasks such as tissue and organ delineation, and disease detection. This paper provides a detailed comparative analysis of two fine-tune...
详细信息
The utilization of visual attention enhances the performance of image classification *** attentionbased models have demonstrated notable performance,but many of these models exhibit reduced accuracy when confronted wi...
详细信息
The utilization of visual attention enhances the performance of image classification *** attentionbased models have demonstrated notable performance,but many of these models exhibit reduced accuracy when confronted with inter-class and intra-class similarities and ***-Controlled Differential Equations(N-CDE’s)and Neural Ordinary Differential Equations(NODE’s)are extensively utilized within this ***’s possesses the capacity to effectively illustrate both inter-class and intra-class similarities and differences with enhanced *** this end,an attentive neural network has been proposed to generate attention maps,which uses two different types of N-CDE’s,one for adopting hidden layers and the other to generate attention *** distinct attention techniques are implemented including time-wise attention,also referred to as bottom N-CDE’s;and element-wise attention,called topN-CDE’***,a trainingmethodology is proposed to guarantee that the training problem is sufficiently *** classification tasks including fine-grained visual classification andmulti-label classification,are utilized to evaluate the *** proposedmethodology is employed on five publicly available datasets,including CUB-200-2011,ImageNet-1K,PASCAL VOC 2007,PASCAL VOC 2012,and MS *** obtained visualizations have demonstrated that N-CDE’s are better appropriate for attention-based activities in comparison to conventional NODE’s.
People are increasingly concerned about their mental health wellness. Scientific studies suggest that online counselling for anxiety and depression is just as effective as in-person treatment. Additionally, journaling...
详细信息
Evaluating physicians’ performance is one of the fundamental pillars of improving the quality of healthcare in medical institutions, as it contributes to measuring their ability to provide appropriate treatment, inte...
详细信息
The evaluation of disease severity through endoscopy is pivotal in managing patients with ulcerative colitis,a condition with significant clinical ***,endoscopic assessment is susceptible to inherent variations,both w...
详细信息
The evaluation of disease severity through endoscopy is pivotal in managing patients with ulcerative colitis,a condition with significant clinical ***,endoscopic assessment is susceptible to inherent variations,both within and between observers,compromising the reliability of individual *** study addresses this challenge by harnessing deep learning to develop a robust model capable of discerning discrete levels of endoscopic disease *** initiate this endeavor,a multi-faceted approach is embarked *** dataset is meticulously preprocessed,enhancing the quality and discriminative features of the images through contrast limited adaptive histogram equalization(CLAHE).A diverse array of data augmentation techniques,encompassing various geometric transformations,is leveraged to fortify the dataset’s diversity and facilitate effective feature extraction.A fundamental aspect of the approach involves the strategic incorporation of transfer learning principles,harnessing a modified ResNet-50 *** augmentation,informed by domain expertise,contributed significantly to enhancing the model’s classification *** outcome of this research endeavor yielded a highly promising model,demonstrating an accuracy rate of 86.85%,coupled with a recall rate of 82.11%and a precision rate of 89.23%.
As a pivotal enabler of intelligent transportation system(ITS), Internet of vehicles(Io V) has aroused extensive attention from academia and industry. The exponential growth of computation-intensive, latency-sensitive...
详细信息
As a pivotal enabler of intelligent transportation system(ITS), Internet of vehicles(Io V) has aroused extensive attention from academia and industry. The exponential growth of computation-intensive, latency-sensitive,and privacy-aware vehicular applications in Io V result in the transformation from cloud computing to edge computing,which enables tasks to be offloaded to edge nodes(ENs) closer to vehicles for efficient execution. In ITS environment,however, due to dynamic and stochastic computation offloading requests, it is challenging to efficiently orchestrate offloading decisions for application requirements. How to accomplish complex computation offloading of vehicles while ensuring data privacy remains challenging. In this paper, we propose an intelligent computation offloading with privacy protection scheme, named COPP. In particular, an Advanced Encryption Standard-based encryption method is utilized to implement privacy protection. Furthermore, an online offloading scheme is proposed to find optimal offloading policies. Finally, experimental results demonstrate that COPP significantly outperforms benchmark schemes in the performance of both delay and energy consumption.
Heart diseases are the undisputed leading causes of death ***,the conventional approach of relying solely on the patient’s medical history is not enough to reliably diagnose heart *** potentially indicative factors e...
详细信息
Heart diseases are the undisputed leading causes of death ***,the conventional approach of relying solely on the patient’s medical history is not enough to reliably diagnose heart *** potentially indicative factors exist,such as abnormal pulse rate,high blood pressure,diabetes,high cholesterol,*** analyzing these health signals’interactions is challenging and requires years of medical training and ***,this work aims to harness machine learning techniques that have proved helpful for data-driven applications in the rise of the artificial intelligence *** specifically,this paper builds a hybrid model as a tool for data mining algorithms like feature *** goal is to determine the most critical factors that play a role in discriminating patients with heart illnesses from healthy *** contribution in this field is to provide the patients with accurate and timely tentative results to help prevent further complications and heart attacks using minimum *** developed model achieves 84.24%accuracy,89.22%Recall,and 83.49%Precision using only a subset of the features.
A potential concept that could be effective for multiple applications is a“cyber-physical system”(CPS).The Internet of Things(IoT)has evolved as a research area,presenting new challenges in obtaining valuable data t...
详细信息
A potential concept that could be effective for multiple applications is a“cyber-physical system”(CPS).The Internet of Things(IoT)has evolved as a research area,presenting new challenges in obtaining valuable data through environmental *** existing work solely focuses on classifying the audio system of CPS without utilizing feature *** study employs a deep learning method,CNN-LSTM,and two-way feature extraction to classify audio systems within *** primary objective of this system,which is built upon a convolutional neural network(CNN)with Long Short Term Memory(LSTM),is to analyze the vocalization patterns of two different species of *** has been demonstrated that CNNs,when combined with mel-spectrograms for sound analysis,are suitable for classifying ambient ***,the data is augmented and ***,the mel spectrogram features are extracted through two-way feature ***,Principal Component Analysis(PCA)is utilized for dimensionality reduction,followed by Transfer learning for audio feature ***,the classification is performed using the CNN-LSTM *** methodology can potentially be employed for categorizing various biological acoustic objects and analyzing biodiversity indexes in natural environments,resulting in high classification *** study highlights that this CNNLSTM approach enables cost-effective and resource-efficient monitoring of large natural *** dissemination of updated CNN-LSTM models across distant IoT nodes is facilitated flexibly and dynamically through the utilization of CPS.
Sparse Knowledge Graph(KG)scenarios pose a challenge for previous Knowledge Graph Completion(KGC)methods,that is,the completion performance decreases rapidly with the increase of graph *** problem is also exacerbated ...
详细信息
Sparse Knowledge Graph(KG)scenarios pose a challenge for previous Knowledge Graph Completion(KGC)methods,that is,the completion performance decreases rapidly with the increase of graph *** problem is also exacerbated because of the widespread existence of sparse KGs in practical *** alleviate this challenge,we present a novel framework,LR-GCN,that is able to automatically capture valuable long-range dependency among entities to supplement insufficient structure features and distill logical reasoning knowledge for sparse *** proposed approach comprises two main components:a GNN-based predictor and a reasoning path *** reasoning path distiller explores high-order graph structures such as reasoning paths and encodes them as rich-semantic edges,explicitly compositing long-range dependencies into the *** step also plays an essential role in densifying KGs,effectively alleviating the sparse ***,the path distiller further distills logical reasoning knowledge from these mined reasoning paths into the *** two components are jointly optimized using a well-designed variational EM *** experiments and analyses on four sparse benchmarks demonstrate the effectiveness of our proposed method.
暂无评论