Journal: IEEE Transactions on Neural Networks and Learning Systems

Abbreviation

IEEE Trans. Neural Netw. Learn. Syst.

Publisher

IEEE

Journal Volumes

ISSN

2162-237X
2162-2388

Description

Filters

2012 - 2019112020 - 202517
Reset filters

Search Results

Publications 1 - 10 of 28
  • Attentive Learning Facilitates Generalization of Neural Networks
    Item type: Journal Article
    Lei, Shiye; He, Fengxiang; Chen, Haowen; et al. (2025)
    IEEE Transactions on Neural Networks and Learning Systems
    This article studies the generalization of neural networks (NNs) by examining how a network changes when trained on a training sample with or without out-of-distribution (OoD) examples. If the network's predictions are less influenced by fitting OoD examples, then the network learns attentively from the clean training set. A new notion, dataset-distraction stability, is proposed to measure the influence. Extensive CIFAR-10/100 experiments on the different VGG, ResNet, WideResNet, ViT architectures, and optimizers show a negative correlation between the dataset-distraction stability and generalizability. With the distraction stability, we decompose the learning process on the training set $\mathcal{S}$ into multiple learning processes on the subsets of $\mathcal{S}$ drawn from simpler distributions, i.e., distributions of smaller intrinsic dimensions (IDs), and furthermore, a tighter generalization bound is derived. Through attentive learning, miraculous generalization in deep learning can be explained and novel algorithms can also be designed.
  • Learning to Predict Sequences of Human Visual Fixations
    Item type: Journal Article
    Jiang, Ming; Boix, Xavier; Roig, Gemma; et al. (2016)
    IEEE Transactions on Neural Networks and Learning Systems
  • Learning Generative Models Using Denoising Density Estimators
    Item type: Journal Article
    Bigdeli, Siavash A.; Lin, Geng; Dunbar, L. Andrea; et al. (2024)
    IEEE Transactions on Neural Networks and Learning Systems
    Learning probabilistic models that can estimate the density of a given set of samples, and generate samples from that density, is one of the fundamental challenges in unsupervised machine learning. We introduce a new generative model based on denoising density estimators (DDEs), which are scalar functions parametrized by neural networks, that are efficiently trained to represent kernel density estimators of the data. Leveraging DDEs, our main contribution is a novel technique to obtain generative models by minimizing the Kullback-Leibler (KL)-divergence directly. We prove that our algorithm for obtaining generative models is guaranteed to converge consistently to the correct solution. Our approach does not require specific network architecture as in normalizing flows (NFs), nor use ordinary differential equation (ODE) solvers as in continuous NFs. Experimental results demonstrate substantial improvement in density estimation and competitive performance in generative model training.
  • Robust Learning-Based Control for Uncertain Nonlinear Systems With Validation on a Soft Robot
    Item type: Journal Article
    Han, Minghao; Wong, Kiwan; Euler-Rolle, Jacob; et al. (2025)
    IEEE Transactions on Neural Networks and Learning Systems
    Existing modeling and control methods for real-world systems typically deal with uncertainty and nonlinearity on a case-by-case basis. We present a universal and robust control framework for the general class of uncertain nonlinear systems. Our data-driven deep stochastic Koopman operator (DeSKO) model and robust learning control framework guarantee robust stability. DeSKO learns the uncertainty of dynamical systems by inferring a distribution of observables. The inferred distribution is used in our robust and stabilizing closed-loop controller for dynamical systems. We also develop a model predictive control framework with integral action to compensate for run-time parametric uncertainty, such as manipulating unknown objects. Modeling and control experiments in simulation show that our presented framework is more robust and scalable for robotic systems than state-of-the-art controllers using deep Koopman operators and reinforcement learning (RL) methods. We demonstrate that our method resists previously unseen uncertainties, such as external disturbances, at a magnitude of up to five times the maximum control input. Furthermore, we test our DeSKO-based control framework on a real-world soft robotic arm. It shows that our framework outperforms model-based controllers that have full knowledge of the model parameters, and the controller can conduct object pick-and-place tasks without further training. Our approach opens up new possibilities in robustly managing internal or external uncertainty while controlling high-dimensional nonlinear systems in a learning framework. This approach serves as a foundation to greatly simplify high-level control and decision-making for robots.
  • AttentionGAN: Unpaired Image-to-Image Translation Using Attention-Guided Generative Adversarial Networks
    Item type: Journal Article
    Tang, Hao; Liu, Hong; Xu, Dan; et al. (2023)
    IEEE Transactions on Neural Networks and Learning Systems
    State-of-the-art methods in the image-to-image translation are capable of learning a mapping from a source domain to a target domain with unpaired image data. Though the existing methods have achieved promising results, they still produce visual artifacts, being able to translate low-level information but not high-level semantics of input images. One possible reason is that generators do not have the ability to perceive the most discriminative parts between the source and target domains, thus making the generated images low quality. In this article, we propose a new Attention-Guided Generative Adversarial Networks (AttentionGAN) for the unpaired image-to-image translation task. AttentionGAN can identify the most discriminative foreground objects and minimize the change of the background. The attention-guided generators in AttentionGAN are able to produce attention masks, and then fuse the generation output with the attention masks to obtain high-quality target images. Accordingly, we also design a novel attention-guided discriminator which only considers attended regions. Extensive experiments are conducted on several generative tasks with eight public datasets, demonstrating that the proposed method is effective to generate sharper and more realistic images compared with existing competitive models. The code is available at https://github.com/Ha0Tang/AttentionGAN.
  • Reservoir Computing Universality with Stochastic Inputs
    Item type: Journal Article
    Gonon, Lukas; Ortega, Juan-Pablo (2020)
    IEEE Transactions on Neural Networks and Learning Systems
  • Asynchronous Event-Based Binocular Stereo Matching
    Item type: Journal Article
    Rogister, Paul; Benosman, Ryad; Ieng, Sio-Hoi; et al. (2012)
    IEEE Transactions on Neural Networks and Learning Systems
  • Visual Recognition by Learning from Web Data via Weakly Supervised Domain Generalization
    Item type: Journal Article
    Niu, Li; Li, Wen; Xu, Dong; et al. (2017)
    IEEE Transactions on Neural Networks and Learning Systems
  • Jointly Learning Structured Analysis Discriminative Dictionary and Analysis Multiclass Classifier
    Item type: Journal Article
    Zhang, Zhao; Jiang, Weiming; Qin, Jie; et al. (2018)
    IEEE Transactions on Neural Networks and Learning Systems
  • Challenges and Opportunities in Deep Reinforcement Learning With Graph Neural Networks: A Comprehensive Review of Algorithms and Applications
    Item type: Review Article
    Munikoti, Sai; Agarwal, Deepesh; Das, Laya; et al. (2024)
    IEEE Transactions on Neural Networks and Learning Systems
    Deep reinforcement learning (DRL) has empowered a variety of artificial intelligence fields, including pattern recognition, robotics, recommendation systems, and gaming. Similarly, graph neural networks (GNNs) have also demonstrated their superior performance in supervised learning for graphstructured data. In recent times, the fusion of GNN with DRL for graph-structured environments has attracted a lot of attention. This article provides a comprehensive review of these hybrid works. These works can be classified into two categories: 1) algorithmic contributions, where DRL and GNN complement each other with an objective of addressing each other's shortcomings and 2) application-specific contributions that leverage a combined GNN-DRL formulation to address problems specific to different applications. This fusion effectively addresses various complex problems in engineering and life sciences. Based on the review, we further analyze the applicability and benefits of fusing these two domains, especially in terms of increasing generalizability and reducing computational complexity. Finally, the key challenges in integrating DRL and GNN, and potential future research directions are highlighted, which will be of interest to the broader machine learning community.
Publications 1 - 10 of 28