检索结果-内蒙古大学图书馆

23rd IEEE International Conference on Machine Learning and Applications, ICMLA 2024

作者： Adigun, Olaoluwa Kosko, Bart Signal and Image Processing Institute Department of Electrical and Computer Engineering Los AngelesCA90089-2564 United States

ISBN: (纸本)9798350374889

We introduce new soft diamond regularizers that both improve synaptic sparsity and maintain classification accuracy in deep neural networks. These parametrized regularizers outperform the state-of-the-art hard-diamond Laplacian regularizer of Lasso regression and classification. They use thick-tailed symmetric alpha-stable (Sa S) bell-curve synaptic weight priors that are not Gaussian and so have thicker tails. The geometry of the diamond-shaped constraint set varies from a circle to a star depending on the tail thickness and dispersion of the prior probability density function. Training directly with these priors is computationally intensive because almost all Sa S probability densities lack a closed form. A precomputed lookup table removed this computational bottleneck. We tested the new soft diamond regularizers with deep neural classifiers on the three datasets CIFAR-10, CIFAR-100, and Caltech-256. The regularizers improved the accuracy of the classifiers. The improvements included 4.57% on CIFAR-10, 4.27% on CIFAR-100, and 6.69% on Caltech-256. They also outperformed L2 regularizers on all the test cases. Soft diamond regularizers also outperformed L1 lasso or Laplace regularizers because they better increased sparsity while improving classification accuracy. Soft-diamond priors substantially improved accuracy on CIFAR-10 when combined with dropout, batch, or data-augmentation regularization. © 2024 IEEE.

关键词： Probability density function

来源：评论

学校读者我要写书评

暂无评论

Bidirectional Backpropagation Autoencoding Networks for image Compression and Denoising 22

Bidirectional Backpropagation Autoencoding Networks for Imag...

引用

22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023

作者： Adigun, Olaoluwa Kosko, Bart Signal and Image Processing Institute Department of Electrical and Computer Engineering Los AngelesCA90089-2564 United States

ISBN: (纸本)9798350345346

A bidirectional autoencoder learns or approximates an identity mapping as it trains a single network with a version of the new bidirectional backpropagation algorithm. Ordinary unidirectional autoencoders find many uses in image processing and in large language models. But they use separate networks for encoding and decoding. Bidirectional auto encoders use the same synaptic weights for encoding and decoding. The forward pass encodes while the backward pass decodes. Bidirectional auto encoders improved network performance and significantly reduced memory usage and used fewer parameters. Simulations compared unidirectional with bidirectional autoencoders for image compression and de noising. The models trained on the MNIST handwritten-digit and CIFAR-IO image datasets. The performance measures were the peak signal-to-noise ratio and the index of structural similarity. Bidirectional autoencoders outperformed unidirectional autoencoders and still reduced the number of trainable synaptic parameters by about 50%. © 2023 IEEE.

关键词： autoencoders bidirectional au-toencoders Bidirectional backpropagation bidirectional networks large language models variational autoencoders

来源：评论

学校读者我要写书评

暂无评论

Training Deep Neural Classifiers with Soft Diamond Regularizers

Training Deep Neural Classifiers with Soft Diamond Regulariz...

引用

International Conference on Machine Learning and Applications (ICMLA)

作者： Olaoluwa Adigun Bart Kosko Department of Electrical and Computer Engineering Signal and Image Processing Institute Los Angeles California

ISBN: (数字)9798350374889

ISBN: (纸本)9798350374896

We introduce new soft diamond regularizers that both improve synaptic sparsity and maintain classification accuracy in deep neural networks. These parametrized regularizers outperform the state-of-the-art hard-diamond Laplacian regularizer of Lasso regression and classification. They use thick-tailed symmetric alpha-stable $(\mathcal{S}\alpha \mathcal{S})$ bell-curve synaptic weight priors that are not Gaussian and so have thicker tails. The geometry of the diamond-shaped constraint set varies from a circle to a star depending on the tail thickness and dispersion of the prior probability density function. Training directly with these priors is computationally intensive because almost all $\mathcal{S}\alpha \mathcal{S}$ probability densities lack a closed form. A precomputed lookup table removed this computational bottleneck. We tested the new soft diamond regularizers with deep neural classifiers on the three datasets CIFAR-10, CIFAR-100, and Caltech-256. The regularizers improved the accuracy of the classifiers. The improvements included 4.57% on CIFAR-10, 4.27% on CIFAR-100, and 6.69% on Caltech-256. They also outperformed $L_{2}$ regularizers on all the test cases. Soft diamond regularizers also outperformed $L_{1}$ lasso or Laplace regularizers because they better increased sparsity while improving classification accuracy. Soft-diamond priors substantially improved accuracy on CIFAR-10 when combined with dropout, batch, or data-augmentation regularization.

关键词： Training Accuracy Sparse approximation Stars Tail Machine learning Probability density function Diamond Table lookup Residual neural networks

来源：评论

学校读者我要写书评

暂无评论

Controlled Causal Hallucinations Can Estimate Phantom Nodes in Multiexpert Mixtures of Fuzzy Cognitive Maps

arXiv

引用

arXiv 2024年

作者： Panda, Akash Kumar Kosko, Bart Signal and Image Processing Institute Department of Electrical and Computer Engineering University of Southern California United States

An adaptive multiexpert mixture of feedback causal models can approximate missing or phantom nodes in large-scale causal models. The result gives a scalable form of big knowledge. The mixed model approximates a sampled dynamical system by approximating its main limit-cycle equilibria. Each expert first draws a fuzzy cognitive map (FCM) with at least one missing causal node or variable. FCMs are directed signed partial-causality cyclic graphs. They mix naturally through convex combination to produce a new causal feedback FCM. Supervised learning helps each expert FCM estimate its phantom node by comparing the FCM's partial equilibrium with the complete multi-node equilibrium. Such phantom-node estimation allows partial control over these causal hallucinations and helps approximate the future trajectory of the dynamical system. But the approximation can be computationally heavy. Mixing the tuned expert FCMs gives a practical way to find several phantom nodes and thereby better approximate the feedback system's true equilibrium behavior. Copyright © 2024, The Authors. All rights reserved.

关键词： Phantoms

来源：评论

学校读者我要写书评

暂无评论

Iterative Gaussian-Laplacian Pyramid Network for Hyperspectral image Classification

引用

IEEE Transactions on Geoscience and Remote Sensing 2024年 62卷 1-22页

作者： Chang, Chein-I Liang, Chia-Chen Hu, Peter Fuming Information and Technology College Dalian116026 China University of Maryland Remote Sensing Signal and Image Processing Laboratory Department of Computer Science and Electrical Engineering BaltimoreMD21250 United States National Cheng Kung University Department of Electrical Engineering Tainan70101 Taiwan University of Maryland School of Medicine R Adams Cowley Shock Trauma Center Shock Trauma Anesthesia Organized Research Center Department of Anesthesia BaltimoreMD21201 United States

Gaussian pyramid (GP) is a commonly used image coding technique that encodes an image as a pyramid that is stacked by a set of images with Gaussian window-reduced sizes and multiple spatial resolutions. Associated with GP, a Laplacian pyramid (LP) can be also constructed to represent differential images between images in two consecutive layers of GP. Such resulting Gaussian-Laplacian pyramid (GLP) performs data compression in a lossless and lossy manner. A convolutional neural network (CNN) consists of a series of layers concatenated in a feedforward manner where each layer has a convolutional sublayer (CL) and a pooling sublayer (PL). Interestingly, each layer implemented by CL and PL in a CNN can be realized by a single layer in GP in the sense that CL and PL can be carried out by a low-pass Gaussian filter operated as a Gaussian kernel in a single layer of GP. This article develops a new approach to hyperspectral image classification (HSIC), called the GLP network (GLPN), which uses not only GP to realize CNN but also LP to capture differential information between two consecutive layers that CNN cannot. Furthermore, by incorporating an iterative process into GLPN, we can derive an iterative GLPN (IGLPN) that can be considered a companion of a recently developed iterative random training sampling CNN (IRTS-CNN) by replacing CNN with GLPN. Since GLPN can realize CNN in a better way, it is expected that IGLPN will perform better than IRTS-CNN and also significantly reduce computational efficiency compared to IRTS-CNN. © 1980-2012 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Band Sampling of Hyperspectral Anomaly Detection in Effective Anomaly Space

引用

IEEE Transactions on Geoscience and Remote Sensing 2024年 62卷 1-29页

作者： Chang, Chein-I Lin, Chien-Yu Hu, Peter Fuming Information and Technology College Dalian116026 China University of Maryland Remote Sensing Signal and Image Processing Laboratory Department of Computer Science and Electrical Engineering BaltimoreMD21250 United States National Cheng Kung University Department of Electrical Engineering Tainan70101 Taiwan University of Maryland School of Medicine R Adams Cowley Shock Trauma Center Shock Trauma Anesthesia Organized Research Center Department of Anesthesia BaltimoreMD21201 United States

This article investigates four issues, background (BKG) suppression (BS), anomaly detectability, noise effect, and interband correlation reduction (IBCR), which have significant impacts on its performance. Despite that a recently developed effective anomaly space (EAS) was designed to use data sphering (DS) to remove the second-order data statistics characterized by BKG, enhance anomaly detectability, and reduce noise effect, it does not address the IBCR issue. To cope with this issue, this article introduces band sampling (BSam) into EAS to reduce IBCR and further suppress BKG more effectively. By implementing EAS in conjunction with BSam (EAS-BSam), these four issues can be resolved altogether for any arbitrary anomaly detector. It first modifies iterative spectral-spatial hyperspectral anomaly detection (ISSHAD) to develop a new variant of ISSHAD, called iterative spectral-spatial maximal map (ISSMax), and then generalizes ISSMax to EAS-ISSMax, which further enhances anomaly detectability and noise removal. Finally, EAS-BSam is implemented to reduce IBCR. As a result, combining EAS, BSam, and ISSMax yields four versions: EAS-BSam, EAS-ISSMax, BSam-SSMAX, and EAS-BSam-SSMax. Such integration presents a great challenge because all these four versions are derived from different aspects, iterative spectral-spatial feedback process, compressive sensing, and low-rank and sparse matrix decomposition. Experiments demonstrate that EAS-BSam and EAS-BSam-SSMax show their superiority to ISSHAD and many current existing hyperspectral anomaly detection (HAD) methods. © 1980-2012 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Bidirectional Backpropagation Autoencoding Networks for image Compression and Denoising

Bidirectional Backpropagation Autoencoding Networks for Imag...

引用

International Conference on Machine Learning and Applications (ICMLA)

作者： Olaoluwa Adigun Bart Kosko Department of Electrical and Computer Engineering Signal and Image Processing Institute Los Angeles California

关键词：

来源：评论

学校读者我要写书评

暂无评论

Training Deep Neural Classifiers with Soft Diamond Regularizers

arXiv

引用

arXiv 2024年

作者： Adigun, Olaoluwa Kosko, Bart Signal and Image Processing Institute Department of Electrical and Computer Engineering Los AngelesCA90089-2564 United States

We introduce new soft diamond regularizers that both improve synaptic sparsity and maintain classification accuracy in deep neural networks. These parametrized regularizers outperform the state-of-the-art hard-diamond Laplacian regularizer of Lasso regression and classification. They use thick-tailed symmetric alpha-stable (SαS) bell-curve synaptic weight priors that are not Gaussian and so have thicker tails. The geometry of the diamond-shaped constraint set varies from a circle to a star depending on the tail thickness and dispersion of the prior probability density function. Training directly with these priors is computationally intensive because almost all SαS probability densities lack a closed form. A precomputed look-up table removed this computational bottleneck. We tested the new soft diamond regularizers with deep neural classifiers on the three datasets CIFAR-10, CIFAR-100, and Caltech-256. The regularizers improved the accuracy of the classifiers. The improvements included 4.57% on CIFAR-10, 4.27% on CIFAR-100, and 6.69% on Caltech-256. They also outperformed L2 regularizers on all the test cases. Soft diamond regularizers also outperformed L1 lasso or Laplace regularizers because they better increased sparsity while improving classification accuracy. Soft-diamond priors substantially improved accuracy on CIFAR-10 when combined with dropout, batch, or data-augmentation regularization. Copyright © 2024, The Authors. All rights reserved.

关键词： Probability density function

来源：评论

学校读者我要写书评

暂无评论

Shannon-like Interpolation with Spectral Priors and Weighted Hilbert Spaces: Beyond the Nyquist Rate

arXiv

引用

arXiv 2024年

作者： Haldar, Justin P. Signal and Image Processing Institute Ming Hsieh Department of Electrical and Computer Engineering University of Southern California Los AngelesCA90089 United States

In this work, we draw connections between the classical Shannon interpolation of bandlimited deterministic signals and the literature on estimating continuous-time random processes from their samples (known in various communities under different names, such as Wiener-Kolmogorov filtering, Gaussian process regression, and kriging). This leads to the realization that Shannon interpolation can be interpreted as implicitly expecting that the unknown signal has uniform spectral density within its bandwidth. However, in many practical applications, we often expect more energy at some frequencies than at others. This leads us to propose novel Shannon-like interpolators that are optimal with respect to appropriately-constructed weighted Hilbert spaces, where weighting enables us to accommodate prior information about nonuniform spectral density. Although our new interpolants are derived for data obtained with any sampling rate, we observe that they are particularly useful for interpolating sub-Nyquist data. In addition to theory, we also discuss aspects of practical implementation and show illustrative examples to demonstrate the potential benefits of the approach. Copyright © 2024, The Authors. All rights reserved.

关键词： Wiener filtering

来源：评论

学校读者我要写书评

暂无评论

Deeper Bidirectional Neural Networks with Generalized Non-Vanishing Hidden Neurons

Deeper Bidirectional Neural Networks with Generalized Non-Va...

引用

International Conference on Machine Learning and Applications (ICMLA)

作者： Olaoluwa Adigun Bart Kosko Department of Electrical and Computer Engineering Signal and Image Processing Institute Los Angeles California

The new NoVa hidden neurons have outperformed ReLU hidden neurons in deep classifiers on some large image test sets. The NoVa or nonvanishing logistic neuron additively perturbs the sigmoidal activation function so that its derivative is not zero. This helps avoid or delay the problem of vanishing gradients. We here extend the NoVa to the generalized perturbed logistic neuron and compare it to ReLU and several other hidden neurons on large image test sets that include CIFAR-100 and Caltech-256. Generalized NoVa classifiers allow deeper networks with better classification on the large datasets. This deep benefit holds for ordinary unidirectional backpropagation. It also holds for the more efficient bidirectional backpropagation that trains in both the forward and backward directions.

关键词： Backpropagation Training Neurons Machine learning Delays Biological neural networks Logistics

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：