Search Results

Generative art is a domain in which artistic output is created via a procedure or heuristic that may result in digital and/or physical results. A generative artist will typically act as a domain expert by specifying the algorithms that will form ...

A meta-evolutionary framework called Differential Evolution Ensemble Designer (DEED) has been proposed in this paper to automate the design of DE ensemble algorithms. Given the design components of DE ensembles and a set of optimization problems, ...

• An automated ensemble differential evolution (DE) designer named DEED is presented.
• A meta-evolutionary approach to automatically choose ensemble DE design components.
• Grammatical evolution forms the meta-evolutionary engine in ...

Selecting and optimizing Convolutional Neural Networks (CNNs) has become a very complex task given the number of associated optimizable parameters, as well as the fact that the arrangement of the layers present in a CNN directly influences its ...

• An evolutionary framework that optimizes CNN with no need for an expert is introduced.
• Although there are different grammar-based approaches (with different context-free grammars) proposed in the literature, to the best of our ...

The design of complex and deep neural networks is often performed by identifying and combining building blocks and progressively selecting the most promising combination. Neuroevolution automates this process by employing evolutionary algorithms ...

• Novel grammar-based multi-objective algorithm for designing Deep Convolutional Neural Networks.
• Development of an efficient context-free grammar for encoding skip-connections.
• Elegant representation of network structures through ...

A significant goal of modern universities is to provide high-quality education to their students and reduce their failure rates. The early recognition of low-performance students that would potentially lead them to increase their duration of ...

• Proactive support strategies can reduce student dropouts.
• Creating new features can increase neural networks’ generalization ability.
• Using a multi-core CPU can speed up the algorithm’s evolutionary process.

One-Class Classification (OCC) corresponds to a subclass of unsupervised Machine Learning (ML) that is valuable when labeled data is non-existent. In this paper, we present AutoOC, a computationally efficient Grammatical Evolution (GE) approach ...

• AutoOC uses a Grammatical Evolution to find lightweight One-Class (OC) classifiers.
• AutoOC is multi-objective, optimizing predictive performance and training time.
• Two AutoOC variants are studied: a Neuroevolution and an Automated ...

Grammar is a key input in grammar-based genetic programming. Grammar design not only influences performance, but also program size. However, grammar design and the choice of productions often require expert input as no automatic approach exists. ...

Text classification is one of the Natural Language Processing (NLP) tasks. Its objective is to label textual elements, such as phrases, queries, paragraphs, and documents. In NLP, several approaches have achieved promising results ...

• Application of a grammar-based evolutionary approach to the design of DNNs.
• ...

A feature construction method that incorporates a grammatical guided procedure is presented here to predict the monthly mortality rate of the COVID-19 pandemic. Three distinct use cases were obtained from publicly available data and three ...

In recent years, the adoption of deep Convolutional Neural Networks (CNNs) has stood out in solving computer vision tasks, such as image classification. Researchers have proposed several architectures with varying sizes, complexities, ...

• An evolutional framework that optimizes CNNs with no need of an expert is introduced.

Diabetes mellitus is a metabolic disease involving high blood glucose levels that can lead to serious medical consequences. Hence, for diabetic patients the prediction of future glucose levels is essential in the management of the disease. Most ...

• Models are devised to lower severe errors in predicting glucose in diabetic patients.
• Glucose forecasting models are assessed by combining clinical and numerical metrics.
• PRED-EGA methodology is used to evaluate the clinical ...

COVID-19 raised the need for automatic medical diagnosis, to increase the physicians’ efficiency in managing the pandemic. Among all the techniques for evaluating the status of the lungs of a patient with COVID-19, lung ultrasound (LUS)...

• We propose deep networks and decision trees to automatically score COVID-19 patients.

Deep Learning (DL) allowed the field of Multi-Agent Reinforcement Learning (MARL) to make significant advances, speeding-up the progress in the field. However, agents trained by means of DL in MARL settings have an important drawback: their ...

A Meta-evolutionary Selection of Constituents in Ensemble DE (MeSCEDE) framework is proposed in this paper to automate the design of high-level multi-population ensemble Differential Evolution (DE) algorithms. The automated design of high-level ...

• Automated design of ensemble differential evolution (DE) algorithm is presented.
• The proposed approach is Meta-evolutionary Selection of Constituents in Ensemble DE.
• The approach uses grammatical evolution as the meta evolutionary ...

Display Omitted

• A two-phase optimization system for solving classification problems.
• Combining Auto-ML pipelines to improve overall performance.
• Intelligent selection of ensemble methods.
• Best results delivered by double-fault measure and 20 ...

Automatic Machine Learning (Auto-ML) tools enable the automatic solution of real-world problems through machine learning techniques. These tools tend to be more time consuming than standard machine learning libraries, therefore, exploiting all ...

Deep Learning has been very successful in automating the feature engineering process, widely applied for various tasks, such as speech recognition, classification, segmentation of images, time-series forecasting, among others. Deep neural networks ...

Recent machine learning studies present accurate results generating prediction models to identify refactoring operations for a program. However, such works are limited to prediction, i.e., they learn refactoring operations strictly as applied by ...

A novel approach to induce Fuzzy Pattern Trees using Grammatical Evolution is presented in this paper. This new method, called Fuzzy Grammatical Evolution, is applied to a set of benchmark classification problems. Experimental results show that ...

Research efforts in the improvement of artificial neural networks have provided significant enhancements in learning ability, either through manual improvement by researchers or through automated design by other artificial intelligence techniques, ...

Selection hyper-heuristics have been used successfully to solve hard optimization problems. These techniques choose a heuristic or a group of heuristics to create a solution and/or improve it. In a prior study, we proposed an approach that changes ...