Related papers: Improving Fuzzy Rule Classifier with Brain Storm O…

Bayesian optimization (BO) has gained attention as an efficient algorithm for black-box optimization of expensive-to-evaluate systems, where the BO algorithm iteratively queries the system and suggests new trials based on a probabilistic…

For improving the efficiency and the reliability of the opportunistic routing algorithm, in this paper, we propose the cross-layer and reliable opportunistic routing algorithm (CBRT) for Mobile Ad Hoc Networks, which introduces the improved…

Time-series data classification is central to the analysis and control of autonomous systems, such as robots and self-driving cars. Temporal logic-based learning algorithms have been proposed recently as classifiers of such data. However,…

The decision-making process significantly influences the predictions of machine learning models. This is especially important in rule-based systems such as Learning Fuzzy-Classifier Systems (LFCSs) where the selection and application of…

Model explainability is crucial for human users to be able to interpret how a proposed classifier assigns labels to data based on its feature values. We study generalized linear models constructed using sets of feature value rules, which…

Deep learning requires regularization mechanisms to reduce overfitting and improve generalization. We address this problem by a new regularization method based on distributional robust optimization. The key idea is to modify the…

A method of a fusion of fuzzy inference and policy gradient reinforcement learning has been proposed that directly learns, as maximizes the expected value of the reward per episode, parameters in a policy function represented by fuzzy rules…

The state-of-the-art online learning models generally conduct a single online gradient descent when a new sample arrives and thus suffer from suboptimal model weights. To this end, we introduce an online broad learning system framework with…

Gravitational Search Algorithm (GSA) and Particle Swarm Optimization (PSO) are nature-inspired, swarm-based optimization algorithms respectively. Though they have been widely used for single-objective optimization since their inception,…

An enhanced approach for network monitoring is to create a network monitoring tool that has artificial intelligence characteristics. There are a number of approaches available. One such approach is by the use of a combination of rule based,…

A method of simultaneously optimizing both the structure of neural networks and the connection weights in a single training loop can reduce the enormous computational cost of neural architecture search. We focus on the probabilistic…

Deep learning has been successfully applied to many classification problems including underwater challenges. However, a long-standing issue with deep learning is the need for large and consistently labeled datasets. Although current…

This work investigates the use of mixed-norm regularization for sensor selection in Event-Related Potential (ERP) based Brain-Computer Interfaces (BCI). The classification problem is cast as a discriminative optimization framework where…

Scaling deep neural network (DNN) training to more devices can reduce time-to-solution. However, it is impractical for users with limited computing resources. FOSI, as a hybrid order optimizer, converges faster than conventional optimizers…

To improve the robustness of deep classifiers against adversarial perturbations, many approaches have been proposed, such as designing new architectures with better robustness properties (e.g., Lipschitz-capped networks), or modifying the…

Automatic classification of diabetic retinopathy from retinal images has been widely studied using deep neural networks with impressive results. However, there is a clinical need for estimation of the uncertainty in the classifications, a…

Learning an explainable classifier often results in low accuracy model or ends up with a huge rule set, while learning a deep model is usually more capable of handling noisy data at scale, but with the cost of hard to explain the result and…

Swarm optimization algorithms are widely used for feature selection before data mining and machine learning applications. The metaheuristic nature-inspired feature selection approaches are used for single-objective optimization tasks,…

Standard objective functions used during the training of neural-network-based predictive models do not consider clinical criteria, leading to models that are not necessarily clinically acceptable. In this study, we look at this problem from…

Despite the enormous success of machine learning models in various applications, most of these models lack resilience to (even small) perturbations in their input data. Hence, new methods to robustify machine learning models seem very…