Sousa, Iam Palatnik deVellasco, Marley M. B. R.Silva, Eduardo Costa da
12页
查看更多>>摘要：A novel evolutionary approach for Explainable Artificial Intelligence is presented: the "Evolved Expla-nations "model (EvEx). This methodology combines Local Interpretable Model Agnostic Explanations (LIME) with Multi-Objective Genetic Algorithms to allow for automated segmentation parameter tuning in image classification tasks. In this case, the dataset studied is Patch-Camelyon, comprised of patches from pathology whole slide images. A publicly available Convolutional Neural Network (CNN) was trained on this dataset to provide a binary classification for presence/absence of lymph node metastatic tissue. In turn, the classifications are explained by means of evolving segmentations, seeking to optimize three evaluation goals simultaneously. The final explanation is computed as the mean of all explanations generated by Pareto front individuals, evolved by the developed genetic algorithm. To enhance reproducibility and traceability of the explanations, each of them was generated from several different seeds, randomly chosen. The observed results show remarkable agreement between different seeds. Despite the stochastic nature of LIME explanations, regions of high explanation weights proved to have good agreement in the heat maps, as computed by pixel-wise relative standard deviations. The found heat maps coincide with expert medical segmentations, which demonstrates that this methodology can find high quality explanations (according to the evaluation metrics), with the novel advantage of automated parameter fine tuning. These results give additional insight into the inner workings of neural network black box decision making for medical data.(c) 2021 Elsevier Ltd. All rights reserved.
查看更多>>摘要：This paper considers the exponential synchronization issue for variable-order fractional complex dynamical networks (FCDNs) with short memory and derivative couplings via the impulsive control scheme, where dynamical nodes are modeled to be discontinuous. Firstly, the mathematics model with respect to variable-order fractional systems with short memory is established under the impulsive controller, in which the impulse strength is not only determined by the impulse control gain, but also the order of the control systems. Secondly, the exponential stability criterion for variable-order fractional systems with short memory is developed. Thirdly, the hybrid controller, which consists of the impulsive coupling controller and the discontinuous feedback controller, is designed to realize the synchronization objective. In addition, by constructing Lyapunov functional and applying inequality analysis techniques, the synchronization conditions are achieved in terms of linear matrix inequalities (LMIs). Finally, two simulation examples are performed to verify the effectiveness of the developed synchronization scheme and the theoretical outcomes. (C) 2021 Elsevier Ltd. All rights reserved.
Li, JingjingLiu, YijunDong, XianlingSaripan, M. Iqbal...
14页
查看更多>>摘要：This study aims to explore an effective method to evaluate spatial cognitive ability, which can effectively extract and classify the feature of EEG signals collected from subjects participating in the virtual reality (VR) environment; and evaluate the training effect objectively and quantitatively to ensure the objectivity and accuracy of spatial cognition evaluation, according to the classification results. Therefore, a multi-dimensional conditional mutual information (MCMI) method is proposed, which could calculate the coupling strength of two channels considering the influence of other channels. The coupled characteristics of the multi-frequency combination were transformed into multi spectral images, and the image data were classified employing the convolutional neural networks (CNN) model. The experimental results showed that the multi-spectral image transform features based on MCMI are better in classification than other methods, and among the classification results of six band combinations, the best classification accuracy of Beta1-Beta2-Gamma combination is 98.3%. The MCMI characteristics on the Beta1-Beta2-Gamma band combination can be a biological marker for the evaluation of spatial cognition. The proposed feature extraction method based on MCMI provides a new perspective for spatial cognitive ability assessment and analysis. (C)& nbsp;2021 Elsevier Ltd. All rights reserved.
查看更多>>摘要：Fora class of quaternion-valued neural networks (QVNNs) with discrete and distributed time delays, its finite-time synchronization (FTSYN) is addressed in this paper. Instead of decomposition, a direct analytical method named two-step analysis is proposed. That method can always be used to study FTSYN, under either 1-norm or 2-norm of quaternion. Compared with the decomposing method, the two-step method is also suitable for models that are not easily decomposed. Furthermore, a switching controller based on the two-step method is proposed. In addition, two criteria are given to realize the FTSYN of QVNNs. At last, three numerical examples illustrate the feasibility, effectiveness and practicability of our method.(c) 2021 Elsevier Ltd. All rights reserved.
查看更多>>摘要：Recent studies have shown that the choice of activation function can significantly affect the performance of deep learning networks. However, the benefits of novel activation functions have been inconsistent and task dependent, and therefore the rectified linear unit (ReLU) is still the most commonly used. This paper proposes a technique for customizing activation functions automatically, resulting in reliable improvements in performance. Evolutionary search is used to discover the general form of the function, and gradient descent to optimize its parameters for different parts of the network and over the learning process. Experiments with four different neural network architectures on the CIFAR-10 and CIFAR-100 image classification datasets show that this approach is effective. It discovers both general activation functions and specialized functions for different architectures, consistently improving accuracy over ReLU and other activation functions by significant margins. The approach can therefore be used as an automated optimization step in applying deep learning to new tasks. (c) 2022 Elsevier Ltd. All rights reserved.
查看更多>>摘要：This paper concentrates on trade off analysis between fixed-time stabilization and energy consumption for a type of nonlinear neural networks (NNs). By constructing a compound switching controller and utilizing inequality techniques, a sufficient condition is proposed to ensure the fixed-time stabilization. Then, an estimate of the upper bound of the energy consumed by the controller in the control process is given. Furthermore, the quantitative analysis of the trade-off between the control time and energy consumption is studied. This article reveals that appropriate control parameters can balance the above two indicators to achieve an optimal control state. Finally, the presented theoretical results are verified by two numerical examples. (C)& nbsp;2022 Published by Elsevier Ltd.
查看更多>>摘要：Voice conversion has made great progress in the past few years under the studio-quality test scenario in terms of speech quality and speaker similarity. However, in real applications, test speech from source speaker or target speaker can be corrupted by various environment noises, which seriously degrade the speech quality and speaker similarity. In this paper, we propose a novel encoder-decoder based noise-robust voice conversion framework, which consists of a speaker encoder, a content encoder, a decoder, and two domain adversarial neural networks. Specifically, we integrate disentangling speaker and content representation technique with domain adversarial training technique. Domain adversarial training makes speaker representations and content representations extracted by speaker encoder and content encoder from clean speech and noisy speech in the same space, respectively. In this way, the learned speaker and content representations are noise-invariant. Therefore, the two noise-invariant representations can be taken as input by the decoder to predict the clean converted spectrum. The experimental results demonstrate that our proposed method can synthesize clean converted speech under noisy test scenarios, where the source speech and target speech can be corrupted by seen or unseen noise types during the training process. Additionally, both speech quality and speaker similarity are improved.(c) 2022 Elsevier Ltd. All rights reserved.
查看更多>>摘要：This article mainly dedicates on the issue of finite-time stabilization of complex-valued neural networks with proportional delays and inertial terms via directly constructing Lyapunov functions without separating the original complex-valued neural networks into two real-valued subsystems equivalently. First of all, in order to facilitate the analysis of the second-order derivative caused by the inertial term, two intermediate variables are introduced to transfer complex-valued inertial neural networks (CVINNs) into the first-order differential equation form. Then, under the finite-time stability theory, some new criteria with less conservativeness are established to ensure the finite-time stabilizability of CVINNs by a newly designed complex-valued feedback controller. In addition, for reducing expenses of the control, an adaptive control strategy is also proposed to achieve the finite time stabilization of CVINNs. At last, numerical examples are given to demonstrate the validity of the derived results.(C) 2022 Elsevier Ltd. All rights reserved.
Evans, Benjamin D.Malhotra, GauravBowers, Jeffrey S.
15页
查看更多>>摘要：Deep Convolutional Neural Networks (DNNs) have achieved superhuman accuracy on standard image classification benchmarks. Their success has reignited significant interest in their use as models of the primate visual system, bolstered by claims of their architectural and representational similarities. However, closer scrutiny of these models suggests that they rely on various forms of shortcut learning to achieve their impressive performance, such as using texture rather than shape information. Such superficial solutions to image recognition have been shown to make DNNs brittle in the face of more challenging tests such as noise-perturbed or out-of-distribution images, casting doubt on their similarity to their biological counterparts. In the present work, we demonstrate that adding fixed biological filter banks, in particular banks of Gabor filters, helps to constrain the networks to avoid reliance on shortcuts, making them develop more structured internal representations and more tolerance to noise. Importantly, they also gained around 20-35% improved accuracy when generalising to our novel out-of-distribution test image sets over standard end-to-end trained architectures. We take these findings to suggest that these properties of the primate visual system should be incorporated into DNNs to make them more able to cope with real-world vision and better capture some of the more impressive aspects of human visual perception such as generalisation. (C)& nbsp;2021 Elsevier Ltd. All rights reserved.& nbsp;
NSTL
Elsevier