Buscar recursos académicos

Rectified activation units (rectifiers) are essential for state-of-the-art neural networks. In this work, we study rectifier neural networks for image classification from two aspects. First, we propose a Parametric Recti...

Covers supervised learning (prediction) to unsupervised learning. This book contains topics including neural networks, support vector machines, classification trees and boosting

A major assumption in many machine learning and data mining algorithms is that the training and future data must be in the same feature space and have the same distribution. However, in many real-world applications, this...

We present Momentum Contrast (MoCo) for unsupervised visual representation learning. From a perspective on contrastive learning as dictionary look-up, we build a dynamic dictionary with a queue and a moving-averaged enco...

Many classification systems rely on clustering techniques in which a collection of training examples is provided as an input, and a number of clusters c1,...cm modelling some concept C results as an output, such that ev...

Function estimation/approximation is viewed from the perspective of numerical optimization in function space, rather than parameter space. A connection is made between stagewise additive expansions and steepest-descent m...

Very deep convolutional networks have been central to the largest advances in image recognition performance in recent years. One example is the Inception architecture that has been shown to achieve very good performance ...

"The use of Brain-Computer Interfaces can provide substantial improvements to the quality of life of patients with diseases such as severe Amyotrophic lateral sclerosis that cause Locked-in syndrome, by creating new aven...

LIBSVM is a library for Support Vector Machines (SVMs). We have been actively developing this package since the year 2000. The goal is to help users to easily apply SVM to their applications. LIBSVM has gained wide popul...

"Falls pose a significant health risk to older adults, often resulting in serious injuries and reduced independence. This study explored two machine learning approaches for detecting falls using data from wearable sensor...

This dataset comprises physiological signals recorded via a wearable device (Empatica E4) during structured acute stress induction and both aerobic and anaerobic exercise sessions. Collected metrics include blood volume ...

Deep learning has revolutionized many machine learning tasks in recent years, ranging from image classification and video processing to speech recognition and natural language understanding. The data in these tasks are t...

"The rapid proliferation of deepfake videos poses a growing threat to the integrity of digital information and public discourse. Traditional detection methods, often based on convolutional neural networks or artifact-spe...

A training algorithm that maximizes the margin between the training patterns and the decision boundary is presented. The technique is applicable to a wide variety of the classification functions, including Perceptrons, p...

The ability of learning networks to generalize can be greatly enhanced by providing constraints from the task domain. This paper demonstrates how such constraints can be integrated into a backpropagation network through ...

In the first part of this paper, a regular recurrent neural network (RNN) is extended to a bidirectional recurrent neural network (BRNN). The BRNN can be trained without the limitation of using input information just up ...

The caret package, short for classification and regression training, contains numerous tools for developing predictive models using the rich set of models available in R. The package focuses on simplifying model training...

En la actualidad es importante detectar a tiempo la depresión, con el fin de llevar un tratamiento oportuno y mejorar la calidad de vida de las personas, este proceso de evaluación o detección requiere el uso de herra...

An essential textbook for any student or researcher in biology needing to design experiments, sample programs or analyse the resulting data. The text begins with a revision of estimation and hypothesis testing methods, c...

We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVR...

MOTIVATION: Biological sequence data is accumulating rapidly, motivating the development of improved high-throughput methods for sequence classification. RESULTS: UBLAST and USEARCH are new algorithms enabling sensitive ...

Existing deep convolutional neural networks (CNNs) require a fixed-size (e.g., 224 × 224) input image. This requirement is "artificial" and may reduce the recognition accuracy for the images or sub-images of an arbitrar...

While it is nearly effortless for humans to quickly assess the perceptual similarity between two images, the underlying processes are thought to be quite complex. Despite this, the most widely used perceptual metrics tod...

Convolutional networks are powerful visual models that yield hierarchies of features. We show that convolutional networks by themselves, trained end-to-end, pixels-to-pixels, improve on the previous best result in semant...