Optoelectronic synapses that integrate visual perception and pre-processing hold significant potential for neuromorphic vision systems(NVSs). However, due to a lack of wavelength sensitivity, existing NVS mainly foc...
详细信息
Optoelectronic synapses that integrate visual perception and pre-processing hold significant potential for neuromorphic vision systems(NVSs). However, due to a lack of wavelength sensitivity, existing NVS mainly focuses on gray-scale image processing, making it challenging to recognize color images. Additionally, the high power consumption of optoelectronic synapses, compared to the 10 fJ energy consumption of biological synapses, limits their broader application. To address these challenges, an energy-efficient NVS capable of color target recognition in a noisy environment was developed,utilizing a MoS2optoelectronic synapse with wavelength sensitivity. Benefiting from the distinct photon capture capabilities of 450, 535, and 650 nm light, the optoelectronic synapse exhibits wavelength-dependent synaptic plasticity, including excitatory postsynaptic current(EPSC), paired-pulse facilitation(PPF), and long-term plasticity(LTP). These properties can effectively mimic the visual memory and color discrimination functions of the human vision system. Results demonstrate that the NVS, based on MoS2optoelectronic synapses, can eliminate the color noise at the sensor level, increasing color image recognition accuracy from 50% to 90%. Importantly, the optoelectronic synapse operates at a low voltage spike of0.0005 V, consuming only 0.075 fJ per spike, surpassing the energy efficiency of both existing optoelectronic and biological synapses. This ultra-low power, color-sensitive device eliminates the need for color filters and offers great promise for future deployment in filter-free NVS.
Diabetes disease is prevalent worldwide, and predicting its progression is crucial. Several model have been proposed to predict such disease. Those models only determine the disease label, leaving the likelihood of de...
详细信息
Mobile edge computing(MEC) provides edge services to users in a distributed and on-demand *** to the heterogeneity of edge applications, deploying latency and resource-intensive applications on resourceconstrained dev...
详细信息
Mobile edge computing(MEC) provides edge services to users in a distributed and on-demand *** to the heterogeneity of edge applications, deploying latency and resource-intensive applications on resourceconstrained devices is a key challenge for service providers. This is especially true when underlying edge infrastructures are fault and error-prone. In this paper, we propose a fault tolerance approach named DFGP, for enforcing mobile service fault-tolerance in MEC. It synthesizes a generative optimization network(GON) model for predicting resource failure and a deep deterministic policy gradient(DDPG) model for yielding preemptive migration *** show through extensive simulation experiments that DFGP is more effective in fault detection and guaranteeing quality of service, in terms of fault detection accuracy, migration efficiency, task migration time, task scheduling time,and energy consumption than other existing methods.
Deploying models on resource-constrained edge devices remains always a critical challenge for the application of neural network. Quantization is one of the most popular methods to compress the model for meeting the pe...
详细信息
Existing lip synchronization(lip-sync)methods generate accurately synchronized mouths and faces in a generated ***,they still confront the problem of artifacts in regions of non-interest(RONI),e.g.,background and othe...
详细信息
Existing lip synchronization(lip-sync)methods generate accurately synchronized mouths and faces in a generated ***,they still confront the problem of artifacts in regions of non-interest(RONI),e.g.,background and other parts of a face,which decreases the overall visual *** solve these problems,we innovatively introduce diverse image inpainting to lip-sync *** propose Modulated Inpainting Lip-sync GAN(MILG),an audio-constraint inpainting network to predict synchronous *** utilizes prior knowledge of RONI and audio sequences to predict lip shape instead of image generation,which can keep the RONI ***,we integrate modulated spatially probabilistic diversity normalization(MSPD Norm)in our inpainting network,which helps the network generate fine-grained diverse mouth movements guided by the continuous audio ***,to lower the training overhead,we modify the contrastive loss in lipsync to support small-batch-size and few-sample *** experiments demonstrate that our approach outperforms the existing state-of-the-art of image quality and authenticity while keeping lip-sync.
Recurrent neural networks (RNNs) have been heavily used in applications relying on sequence data such as time series and natural languages. As a matter of fact, their behaviors lack rigorous quality assurance due to t...
详细信息
Recurrent neural networks (RNNs) have been heavily used in applications relying on sequence data such as time series and natural languages. As a matter of fact, their behaviors lack rigorous quality assurance due to the black-box nature of deep learning. It is an urgent and challenging task to formally reason about the behaviors of RNNs. To this end, we first present an extension of linear-time temporal logic to reason about properties with respect to RNNs, such as local robustness, reachability, and some temporal properties. Based on the proposed logic, we formalize the verification obligation as a Hoare-like triple, from both qualitative and quantitative perspectives. The former concerns whether all the outputs resulting from the inputs fulfilling the pre-condition satisfy the post-condition, whereas the latter is to compute the probability that the post-condition is satisfied on the premise that the inputs fulfill the pre-condition. To tackle these problems, we develop a systematic verification framework, mainly based on polyhedron propagation, dimension-preserving abstraction, and the Monte Carlo sampling. We also implement our algorithm with a prototype tool and conduct experiments to demonstrate its feasibility and efficiency.
Accurate forecasting of time series is crucial across various *** prediction tasks rely on effectively segmenting,matching,and time series data *** instance,regardless of time series with the same granularity,segmenti...
详细信息
Accurate forecasting of time series is crucial across various *** prediction tasks rely on effectively segmenting,matching,and time series data *** instance,regardless of time series with the same granularity,segmenting them into different granularity events can effectively mitigate the impact of varying time scales on prediction ***,these events of varying granularity frequently intersect with each other,which may possess unequal *** minor differences can result in significant errors when matching time series with future ***,directly using matched events but unaligned events as state vectors in machine learning-based prediction models can lead to insufficient prediction ***,this paper proposes a short-term forecasting method for time series based on a multi-granularity event,MGE-SP(multi-granularity event-based short-termprediction).First,amethodological framework for MGE-SP established guides the implementation *** framework consists of three key steps,including multi-granularity event matching based on the LTF(latest time first)strategy,multi-granularity event alignment using a piecewise aggregate approximation based on the compression ratio,and a short-term prediction model based on *** data from a nationwide online car-hailing service in China ensures the method’s *** average RMSE(root mean square error)and MAE(mean absolute error)of the proposed method are 3.204 and 2.360,lower than the respective values of 4.056 and 3.101 obtained using theARIMA(autoregressive integratedmoving average)method,as well as the values of 4.278 and 2.994 obtained using k-means-SVR(support vector regression)*** other experiment is conducted on stock data froma public data *** proposed method achieved an average RMSE and MAE of 0.836 and 0.696,lower than the respective values of 1.019 and 0.844 obtained using the ARIMA method,as well as the values of 1.350 and 1.172 obtained usin
Sea ice has a significant impact on climate change and ship navigation. Therefore, it is essential to create maps charting that accurately depict the geographic distribution of different types of sea ice. To satisfy t...
详细信息
Harmful meme detection presents a significant multimodal challenge that necessitates contextual background knowledge and comprehensive inference. Although some research studies have been related to harmful meme detect...
详细信息
This study provides a detailed study of a Сonvolutional Neural Network (СNN) model optimized for facial eхpression recognition with Fuzzy logic using Fuzzy2DPooling and Fuzzy Neural Networks (FNN), and discusses da...
详细信息
暂无评论