检索结果-内蒙古大学图书馆

Cross-domain neural-kernel networks 31

学校读者我要写书评

暂无评论

Cross-domain neural-kernel networks

31st Benelux Conference on Artificial Intelligence and the 28th Belgian Dutch Conference on Machine Learning, BNAIC/BENELEARN 2019

作者： Mehrkanoon, Siamak Department of Data Science and Knowledge Engineering Maastricht University Netherlands

A novel cross-domain neural-kernel networks architecture for semi-supervised domain adaption problem is introduced. The proposed model consists of two stream neural-kernel networks corresponding to the source and target domains which are enriched with a coupling term. Each stream neural-kernel networks follows a combination of neural network layer and an explicit feature map constructed by means of random Fourier features. The introduced coupling term aims at enforcing correlations among the output of the intermediate layers of the two stream networks as well as encouraging the two networks to learn shared representation of the data from both source and target domains. Experimental results are given to illustrate the effectiveness of the proposed approaches on real-life datasets. © 2019 for this paper by its authors.

关键词： Network layers

Deep shared representation learning for weather elements forecasting 31

学校读者我要写书评

暂无评论

Deep shared representation learning for weather elements for...

31st Benelux Conference on Artificial Intelligence and the 28th Belgian Dutch Conference on Machine Learning, BNAIC/BENELEARN 2019

作者： Mehrkanoon, Siamak Department of Data Science and Knowledge Engineering Maastricht University Netherlands

This paper introduces a data-driven predictive model based on deep convolutional neural networks (CNN) architecture for wind speed prediction in weather data. The model exploits the spatio-temporal multivariate weather data for learning shared representations and forecasting weather elements for a number of user defined weather stations simultaneously in an end-to-end fashion. The embedded feature learning component of the model as well as coupling the learned features of different input layers have shown to have a significant impact on the prediction task. An experimental setup has been considered based on a high temporal resolution dataset collected from the National Climatic data Center (NCDC) at five stations located in Denmark. The experiment concerns wind speed prediction at three weather stations located in Denmark for 6 and 12 hours ahead. © 2019 for this paper by its authors.

关键词： Deep neural networks

Deep coastal sea elements forecasting using U-Net based models

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Fernández, Jesús García Abdellaoui, Ismail Alaoui Mehrkanoon, Siamak Department of Data Science and Knowledge Engineering Maastricht University Netherlands

The supply and demand of energy is influenced by meteorological conditions. The relevance of accurate weather forecasts increases as the demand for renewable energy sources increases. The energy providers and policy makers require weather information to make informed choices and establish optimal plans according to the operational objectives. Due to the recent development of deep learning techniques applied to satellite imagery, weather forecasting that uses remote sensing data has also been the subject of major progress. The present paper investigates multiple steps ahead frame prediction for coastal sea elements in the Netherlands using U-Net based architectures. Hourly data from the Copernicus observation programme spanned over a period of 2 years has been used to train the models and make the forecasting, including seasonal predictions. We propose a variation of the U-Net architecture and further extend this novel model using residual connections, parallel convolutions and asymmetric convolutions in order to introduce three additional architectures. In particular, we show that the architecture equipped with parallel and asymmetric convolutions as well as skip connections outperforms the other three discussed models. © 2020, CC BY.

关键词： Convolution

Deep brain state classification of MEG data

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Abdellaoui, Ismail Alaoui Fernandez, Jesus Garcia Sahinli, Caner Mehrkanoon, Siamak Department of Data Science and Knowledge Engineering Maastricht University Netherlands

Neuroimaging techniques have shown to be useful when studying the brains activity. This paper uses Magnetoencephalography (MEG) data, provided by the Human Connectome Project (HCP), in combination with various deep artificial neural network models to perform brain decoding. More specifically, here we investigate to which extent can we infer the task performed by a subject based on its MEG data. Three models based on compact convolution, combined convolutional and long short-term architecture as well as a model based on multi-view learning that aims at fusing the outputs of the two stream networks are proposed and examined. These models exploit the spatio-temporal MEG data for learning new representations that are used to decode the relevant tasks across subjects. In order to realize the most relevant features of the input signals, two attention mechanisms, i.e. self and global attention, are incorporated in all the models. The experimental results of cross subject multi-class classification on the studied MEG dataset show that the inclusion of attention improves the generalization of the models across subjects. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolutional neural networks

Computable random variables and conditioning

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Collins, Pieter Department of Data Science and Knowledge Engineering Maastricht University Netherlands

The aim of this paper is to present an elementary computable theory of random variables, based on the approach to probability via valuations. The theory is based on a type of lower-measurable sets, which are controlled limits of open sets, and extends existing work in this area by providing a computable theory of conditional random variables. The theory is based within the framework of type-two effectivity, so has an explicit direct link with Turing computation, and is expressed in a system of computable types and operations, so has a clean mathematical *** Codes 60A10 03D80 03D78 © 2020, CC BY.

关键词： Random variables

Bridging face and sound modalities through domain adaptation metric learning 27

学校读者我要写书评

暂无评论

Bridging face and sound modalities through domain adaptation...

27th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2019

作者： Athanasiadis, Christos Hortal, Enrique Asteriadis, Stylianos Department of Data Science and Knowledge Engineering Maastricht University Netherlands

ISBN: (纸本)9782875870650

Robust emotion recognition systems require extensive training by employing huge number of training samples with purpose of generating sophisticated models. Furthermore, research is mostly focused on facial expression recognition due, mainly to, the wide availability of related datasets. However, the existence of rich and publicly available datasets is not the case for other modalities like sound and so forth. In this work, a heterogeneous domain adaptation framework is introduced for bridging two inherently different domains (namely face and audio). The purpose is to perform affect recognition on the modality where only a small amount of data is available, leveraging large amounts of data from another modality. © 2019 ESANN (***). All rights reserved.

关键词： Emotion Recognition

Synthesizing personality-dependent body postures using generative adversarial networks 31

学校读者我要写书评

暂无评论

Synthesizing personality-dependent body postures using gener...

31st Benelux Conference on Artificial Intelligence and the 28th Belgian Dutch Conference on Machine Learning, BNAIC/BENELEARN 2019

作者： Calsius, Frederik Asteriadis, Stylianos Department of Data Science and Knowledge Engineering Maastricht University Netherlands

In Personality Computing, one of the major goals is to estimate the personality of an individual by making use of computational techniques. Among the existing models that classify personality traits, the Big-5 factor model is probably the most popular, due to the fact that it provides a compact and complete set of traits describing human personalities. This paper presents an adversarial method that allows the generation of body postures exhibiting the characteristics of a chosen personality trait. The Big-5 and a broader model are analyzed and, in particular, we propose and analyze a technique for generating silhouettes with different levels of extroversion, as well as the aspect of a broader model corresponding to how over (or under) constrained a person is. The proposed approach can be applied in domains such as automatic character animation, marketing, and the broader field of Affective Computing. © 2019 for this paper by its authors.

关键词： Generative adversarial networks

Complex Network for Complex Problems: A comparative study of CNN and Complex-valued CNN

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Chatterjee, Soumick Tummala, Pavan Speck, Oliver Nürnberger, Andreas Faculty of Computer Science Otto von Guericke University Magdeburg Germany Data and Knowledge Engineering Group Otto von Guericke University Magdeburg Germany Biomedical Magnetic Resonance Otto von Guericke University Magdeburg Germany German Center for Neurodegenerative Disease Magdeburg Germany Center for Behavioral Brain Sciences Magdeburg Germany

Neural networks, especially convolutional neural networks (CNN), are one of the most common tools these days used in computer vision. Most of these networks work with real-valued data using real-valued features. Complex-valued convolutional neural networks (CV-CNN) can preserve the algebraic structure of complex-valued input data and have the potential to learn more complex relationships between the input and the ground-truth. Although some comparisons of CNNs and CV-CNNs for different tasks have been performed in the past, a large-scale investigation comparing different models operating on different tasks has not been conducted. Furthermore, because complex features contain both real and imaginary components, CV-CNNs have double the number of trainable parameters as real-valued CNNs in terms of the actual number of trainable parameters. Whether or not the improvements in performance with CV-CNN observed in the past have been because of the complex features or just because of having double the number of trainable parameters has not yet been explored. This paper presents a comparative study of CNN, CNNx2 (CNN with double the number of trainable parameters as the CNN), and CV-CNN. The experiments were performed using seven models for two different tasks - brain tumour classification and segmentation in brain MRIs. The results have revealed that the CV-CNN models outperformed the CNN and CNNx2 models. Copyright © 2023, The Authors. All rights reserved.

关键词： Image segmentation

A new steganography without embedding based on adversarial training 20

学校读者我要写书评

暂无评论

A new steganography without embedding based on adversarial t...

2020 ACM Turing Celebration Conference - China, ACM TURC 2020

作者： Jiang, Wenjie Hu, Donghui Yu, Cong Li, Meng Zhao, Zhong-Qiu Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Ministry of Education and College of Computer Science and Information Engineering !!!Hefei University of Technology Hefei China College of Computer Science and Information Engineering Hefei University of Technology Hefei230601 China

ISBN: (纸本)9781450375344

Steganography is an art to hide information in the carriers to prevent from being detected, while steganalysis is the opposite art to detect the presence of the hidden information. With the development of deep learning, several state-of-the-art steganography and steganalysis based on deep learning techniques have been proposed to improve hiding or detection capabilities. Generative Adversarial Networks (GANs) based steganography directly uses the minimax game between the generator and discriminator, to automatically generate steganography algorithms resisting being detected by powerful steganalysis. The steganography without embedding (SWE) based on GANs, where the generated cover images themselves are stego ones carrying secret information has shown its state-of-the-art steganography performance. However, SWE based on GANs has serious weaknesses, such as low information recovery accuracy, low steganography capacity and poor natural showing. To solve these problems, this paper proposes a new SWE based on adversarial training, with carefully designed generator, discriminator and extractor, as well as their loss functions and optimized training mode. The proposed method can achieve a very high information recovery accuracy (100% in some cases), and at the same time improve the steganography capacity and image quality. © 2020 ACM.

关键词： Steganography