Various daily applications, including image categorization, natural language comprehension, and voice identification, heavily rely on fully connected and convolutional neuralnetworks. When tackling classification pro...
详细信息
neural controlled differential equations (NCDEs), which are continuous analogues to recurrent neuralnetworks (RNNs), are a specialized model in (irregular) time-series processing. In comparison with similar models, e...
详细信息
ISBN:
(纸本)9781577358800
neural controlled differential equations (NCDEs), which are continuous analogues to recurrent neuralnetworks (RNNs), are a specialized model in (irregular) time-series processing. In comparison with similar models, e.g., neural ordinary differential equations (NODEs), the key distinctive characteristics of NCDEs are i) the adoption of the continuous path created by an interpolation algorithm from each raw discrete time-series sample and ii) the adoption of the Riemann-Stieltjes integral. It is the continuous path which makes NCDEs be analogues to continuous RNNs. However, NCDEs use existing interpolation algorithms to create the path, which is unclear whether they can create an optimal path. To this end, we present a method to generate another latent path (rather than relying on existing interpolation algorithms), which is identical to learning an appropriate interpolation method. We design an encoder-decoder module based on NCDEs and NODEs, and a special training method for it. Our method shows the best performance in both time-series classification and forecasting.
Cycling stress assessment, which quantifies cyclists' perceived stress imposed by the built environment and motor traffics, increasingly informs cycling infrastructure planning and cycling route recommendation. Ho...
详细信息
ISBN:
(纸本)1577358872
Cycling stress assessment, which quantifies cyclists' perceived stress imposed by the built environment and motor traffics, increasingly informs cycling infrastructure planning and cycling route recommendation. However, currently calculating cycling stress is slow and data-intensive, which hinders its broader application. In this paper, We propose a deep learning framework to support accurate, fast, and large-scale cycling stress assessments for urban road networks based on street-view images. Our framework features i) a contrastive learning approach that leverages the ordinal relationship among cycling stress labels, and ii) a post-processing technique that enforces spatial smoothness into our predictions. On a dataset of 39,153 road segments collected in Toronto, Canada, our results demonstrate the effectiveness of our deep learning framework and the value of using image data for cycling stress assessment in the absence of high-quality road geometry and motor traffic data.
Federated learning enhanced with Differential Privacy (DP) is a powerful privacy-preserving strategy to protect individuals sharing their sensitive data for processing in fields such as medicine and healthcare. Many m...
详细信息
ISBN:
(纸本)9783031776090;9783031776106
Federated learning enhanced with Differential Privacy (DP) is a powerful privacy-preserving strategy to protect individuals sharing their sensitive data for processing in fields such as medicine and healthcare. Many medical applications, for example magnetic resonance imaging (MRI), rely on complex-valued signal processing techniques for data acquisition and analysis. However, the appropriate application of DP to complex-valued data is still underexplored. To address this issue, from the theoretical side, we introduce the complex-valued Gaussian mechanism, whose behaviour we characterise in terms of f-DP, (epsilon, delta)-DP and Renyi-DP. Moreover, we generalise the fundamental algorithm DP stochastic gradient descent to complex-valued neuralnetworks and present novel complex-valued neural network primitives compatible with DP. Experimentally, we showcase a proof-of-concept by training federated complex-valued neuralnetworks with DP on a real-world task (MRI pulse sequence classification in k-space), yielding excellent utility and privacy. Our results highlight the relevance of combining federated learning with robust privacy-preserving techniques in the MRI context.
This work investigates the potential of neuralnetworks in the processing of artificial intelligence, especially in smart systems, and explores their applications regarding advancing automation, user experience, and r...
详细信息
This paper summarizes the video sample collection and processing methods based on artificial intelligence platform, focusing on video noise cancellation, content segmentation and classification, and feature extraction...
详细信息
This paper investigates the application of artificialneuralnetworks optimized based on genetic algorithms in human resource management in hospital enterprises and constructs a human resource management and predictiv...
详细信息
The DNCS (Cascaded CNN-ANN) enabled Food Recognition (FR) and Associated Calorie Level Estimation System presents a novel approach to food classification and calorie estimation using a cascaded neural network architec...
详细信息
This research aims to develop a multi-threading method for rapid tool wear detection by integrating image classification and object detection techniques to address the challenge of tool wear detection. The research pr...
详细信息
The wavelet transform has emerged as a powerful tool in deciphering structural information within images. And now, the latest research suggests that combining the prowess of wavelet transform with neuralnetworks can ...
详细信息
ISBN:
(纸本)1577358872
The wavelet transform has emerged as a powerful tool in deciphering structural information within images. And now, the latest research suggests that combining the prowess of wavelet transform with neuralnetworks can lead to unparalleled image deraining results. By harnessing the strengths of both the spatial domain and frequency space, this innovative approach is poised to revolutionize the field of imageprocessing. The fascinating challenge of developing a comprehensive framework that takes into account the intrinsic frequency property and the correlation between rain residue and background is yet to be fully explored. In this work, we propose to investigate the potential relationships among rainfree and residue components at the frequency domain, forming a frequency mutual revision network (FMRNet) for image deraining. Specifically, we explore the mutual representation of rain residue and background components at frequency domain, so as to better separate the rain layer from clean background while preserving structural textures of the degraded images. Meanwhile, the rain distribution prediction from the low-frequency coefficient, which can be seen as the degradation prior is used to refine the separation of rain residue and background components. Inversely, the updated rain residue is used to benefit the low-frequency rain distribution prediction, forming the multi-layer mutual learning. Extensive experiments demonstrate that our proposed FMRNet delivers significant performance gains for seven datasets on image deraining task, surpassing the state-of-the-art method ELFormer by 1.14 dB in PSNR on the Rain100L dataset, while with similar computation cost. Code and retrained models are available at https://***/kuijiang94/FMRNet.
暂无评论