Reliable deployment of machine learning models such as neural networks continues to be challenging due to several limitations.
In this paper, we investigate the effect of different variation operators in a complex domain, that of multi-network heterogeneous neural models.
Neuroevolutionary algorithms, automatic searches of neural network structures by means of evolutionary techniques, are computationally costly procedures.
Despite the remarkable performance and generalization levels of deep learning models in a wide range of artificial intelligence tasks, it has been demonstrated that these models can be easily fooled by the addition of imperceptible yet malicious perturbations to natural inputs.
In this paper we investigate to which extent the distortion metrics proposed in the literature for audio adversarial examples, and which are commonly applied to evaluate the effectiveness of methods for generating these attacks, are a reliable measure of the human perception of the perturbations.
Adversarial examples are inputs intentionally perturbed with the aim of forcing a machine learning model to produce a wrong prediction, while the changes are not easily detectable by a human.
Gaussian Process is a state-of-the-art technique for regression and classification that heavily relies on a kernel function.
Our results show that the algorithm can outperform Gaussian Processes with traditional kernels for some of the sentiment analysis tasks considered.
Multi-task learning, as it is understood nowadays, consists of using one single model to carry out several similar tasks.
In the past, evolutionary algorithms (EAs) that use probabilistic modeling of the best solutions incorporated latent or hidden vari- ables to the models as a more accurate way to represent the search distributions.
To illustrate this claim, we present a contrasted analysis of formalisms, questions, and results produced in FDAs and gray-box optimization.
Missing data has a ubiquitous presence in real-life applications of machine learning techniques.
In this paper we investigate for the first time the use of Evolutionary Algorithms (EAs) on Ising spin glass instances defined on the Chimera topology.
Evolutionary algorithms based on modeling the statistical dependencies (interactions) between the variables have been proposed to solve a wide range of complex problems.
Topological quantum computing is an alternative framework for avoiding the quantum decoherence problem in quantum computation.