Buscar recursos académicos

Materias / palabras clave: Computer science; Deep learning; Artificial intelligence; Abstraction; Representation (politics); Layer (electronics); Object (grammar); Backpropagation; Convolutional neural network; Feature learning; Pattern recognitio...

Materias / palabras clave: Artificial intelligence; Deep learning; Computer science; Artificial neural network; Backpropagation; Reinforcement learning; Machine learning; Deep neural networks; Unsupervised learning; Recurrent neural network; Encod...

Deep convolutional neural networks have performed remarkably well on many Computer Vision tasks. However, these networks are heavily reliant on big data to avoid overfitting. Overfitting refers to the phenomenon when a n...

We present an interpretation of Inception modules in convolutional neural networks as being an intermediate step in-between regular convolution and the depthwise separable convolution operation (a depthwise convolution f...

Materias / palabras clave: Deep learning; Artificial intelligence; Computer science; Segmentation; Field (mathematics); Convolutional neural network; State of art; Image segmentation; Open research; Machine learning; Image (mathematics); Data scie...

"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...

Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers...

In this work, we revisit the global average pooling layer proposed in [13], and shed light on how it explicitly enables the convolutional neural network (CNN) to have remarkable localization ability despite being trained...

In this work we address the task of semantic image segmentation with Deep Learning and make three main contributions that are experimentally shown to have substantial practical merit. First, we highlight convolution with...

Materias / palabras clave: Reinforcement learning; Computer science; Artificial intelligence; Variety (cybernetics); Deep learning; Control (management); Perception; Human–computer interaction; Machine learning; Neuroscience; Biology

We show how to use "complementary priors" to eliminate the explaining-away effects that make inference difficult in densely connected belief nets that have many hidden layers. Using complementary priors, we derive a fast...

The success of machine learning algorithms generally depends on data representation, and we hypothesize that this is because different representations can entangle and hide more or less the different explanatory factors ...

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...

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...

Multilayer neural networks trained with the back-propagation algorithm constitute the best example of a successful gradient based learning technique. Given an appropriate network architecture, gradient-based learning alg...

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...

Materias / palabras clave: Convolutional neural network; Skin cancer; Artificial intelligence; Deep learning; Medicine; Computer science; Biopsy; Skin biopsy; Deep neural networks; Cancer; Pattern recognition (psychology); Dermatology

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...

Materias / palabras clave: Monte Carlo tree search; Computer science; Champion; Artificial neural network; Reinforcement learning; Artificial intelligence; Game tree; Value (mathematics); Search algorithm; Tree (set theory); Deep neural networks; ...

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 ...

"Gravitatonal waves, the seed of the 2015 Nobel’s prize are the cause of several complex celestial phenomena that is non-observable for the naked eye. Their identification, classification and study is s(ll a handmade w...

Caffe provides multimedia scientists and practitioners with a clean and modifiable framework for state-of-the-art deep learning algorithms and a collection of reference models. The framework is a BSD-licensed C++ library...

Generative adversarial networks are a kind of artificial intelligence algorithm designed to solve the generative modeling problem. The goal of a generative model is to study a collection of training examples and learn th...

We propose a technique for producing `visual explanations' for decisions from a large class of Convolutional Neural Network (CNN)-based models, making them more transparent. Our approach - Gradient-weighted Class Activat...