"The graph-based classifier denoted as Optimum-Path Forest has a supervised version which only depends on a distance measure to create arcs between the graph's nodes and further assemble them into trees."

"An alternative to traditional classifiers is the parameter-less Optimum-Path Forest, which uses a graph-based methodology and a distance metric to create arcs between nodes and hence trees, responsible for conquering the nodes, defining their labels and shaping the forests."

"An action recognition task is characterized by an observation of a complete sequence of movements performed by a human followed by its classification."

"If we are trying to identify persons from their handwritten, do sex, age, or any physical trait matters, or it might be more relevant to analyze their hand's pressure, tilt, and acceleration while writing?"

"The discriminative part of a Generative Adversarial Network estimates the probability of a fake sample being a real sample, while its generative part produces fake samples."

"Generative Adversarial Networks are composed of both discriminative and generative networks, commonly known as discriminators and generators."

"A more feasible approach stands for optimization procedures, where parameters are optimized according to an objective function instead of being joined in all possible combinations."

"One significant challenge regarding deep neural networks regards their struggle in achieving low generalization errors."

"Feature selection has been used to enhance data clustering, supervised classification, regression, and recommendation tasks."

“Deep Learning architectures have been widely fostered throughout the last years, being used in a wide range of applications, such as object recognition, image reconstruction, and signal processing.“

“Numerous attempts have been engaged in order to lessen the overfitting problem in classification tasks, such as early-stopping training or even introducing regularization methods such as soft-weight sharing, L1, and L2, among others.”

"Siamese Networks, often called twin networks, consist of a pair of neural networks that share their weights and aims at computing similarity functions."

"Most of literature works focus on only optimizing the model’s hyperparameters (learning rate, number of units, momentum, weight decay, dropout) instead of optimizing its parameters (layers’ weights and biases)."

“Restricted Boltzmann Machines are stochastic networks that deals with probabilities and physical concepts, such as entropy and energy.”

“Machine Learning and Deep Learning are highly susceptible to the data that it is feed with, being only reasonable when the dataset is accurately modeled, representing the real possibilities of the problem.”

Meu nome é Gustavo de Rosa e sou doutorando em Ciência da Computação. O foco é aplicar o Aprendizado Adversarial ao Processamento de Linguagem Natural, fomentando o estudo da geração e identificação de textos artificiais e combatendo as fake news. #ExistePesquisanoBR

"Meta-heuristics algorithms, usually referred to as nature-inspired, or even to swarm- or evolutionary-based algorithms, gained great attention in the last years, attempting to solve optimization problems in a more appealing way than traditional methods."

"An algorithm that has received spotlights is the Restricted Boltzmann Machine (RBM), which is an energy-based architecture that attempts to model the data distribution, relying upon physical and probabilistic concepts."

"Even with the fostering of Machine Learning techniques, there are still many debatable problems on how to produce accurate representations of the real world."

"Traditional augmentation methods, such as cropping, flipping, and padding, are commonly used to enhance neural networks' training, yet they only scratch the surface of data augmentation policies."