Search academic resources

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

Subjects / keywords: Neural networks (Computer science); Machine learning; Electronic books

Embark on a profound journey within the realms of the human psyche with 'Deep Learning: Unlocking Our Emotions.' This captivating book delves into the intricate landscapes of our emotions, unraveling the complex tapestry...

Predicting face attributes in the wild is challenging due to complex face variations. We propose a novel deep learning framework for attribute prediction in the wild. It cascades two CNNs, LNet and ANet, which are fine-t...

Subjects / keywords: Artificial intelligence; Deep learning; Computer science; Artificial neural network; Backpropagation; Reinforcement learning; Machine learning; Deep neural networks; Unsupervised learning; Recurrent neural network; Encod...

La inteligencia artificial es un amplio y diverso campo de la computación dedicado al desarrollo de algoritmos, sistemas y técnicas que permitan a las máquinas aprender y mejorar sus capacidades de razonamiento, perce...

Automático (Machine Learning). El objetivo del machine learning es que los sistemas informáticos sean capaces de aprender a partir de los datos, emulando de esta manera las capacidades humanas. El Aprendizaje Profundo ...

La inteligencia artificial permite la innovación y el cambio en todos los aspectos de la vida moderna. La mayoría de los avances actuales se basan en Deep Learning, un área de conocimiento muy madura que permite a las...

Los avances continuos en la visión artificial permiten resolver problemas de distinta índole, como pueden ser la conducción autónoma, el reconocimiento biométrico, la detección de defectos industriales o la interac...

Subjects / keywords: Computer science; Artificial intelligence; Videography; Toolbox; Transfer of learning; Tracking (education); Computer vision; Pose; A priori and a posteriori; Deep learning; Artificial neural network; Animal behavior

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...

Importance: Deep learning is a family of computational methods that allow an algorithm to program itself by learning from a large set of examples that demonstrate the desired behavior, removing the need to specify rules ...

In the last few years, the deep learning (DL) computing paradigm has been deemed the Gold Standard in the machine learning (ML) community. Moreover, it has gradually become the most widely used computational approach in ...

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...

Subjects / keywords: 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...

Point cloud is an important type of geometric data structure. Due to its irregular format, most researchers transform such data to regular 3D voxel grids or collections of images. This, however, renders data unnecessaril...

Subjects / keywords: Computer science; Segmentation; Artificial intelligence; Rendering (computer graphics); Image segmentation; Key (lock); Deep learning; Field (mathematics); Segmentation-based object categorization; Scale-space segmentati...

Remarkable progress has been made in image recognition, primarily due to the availability of large-scale annotated datasets and deep convolutional neural networks (CNNs). CNNs enable learning data-driven, highly represen...

The popular Q-learning algorithm is known to overestimate action values under certain conditions. It was not previously known whether, in practice, such overestimations are common, whether they harm performance, and whet...

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...

Subjects / keywords: Deep learning; Artificial intelligence; Computer science

The discriminative model learning for image denoising has been recently attracting considerable attentions due to its favorable denoising performance. In this paper, we take one step forward by investigating the construc...

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