Feature (linguistics)
View article: On a Method to Measure Supervised Multiclass Model’s Interpretability: Application to Degradation Diagnosis (Short Paper)
On a Method to Measure Supervised Multiclass Model’s Interpretability: Application to Degradation Diagnosis (Short Paper) Open
In an industrial maintenance context, degradation diagnosis is the problem of determining the current level of degradation of operating machines based on measurements. With the emergence of Machine Learning techniques, such a problem can n…
View article
A Unified Approach to Interpreting Model Predictions Open
Understanding why a model makes a certain prediction can be as crucial as the prediction's accuracy in many applications. However, the highest accuracy for large modern datasets is often achieved by complex models that even experts struggl…
View article
Dynamic Graph CNN for Learning on Point Clouds Open
Point clouds provide a flexible geometric representation suitable for countless applications in computer graphics; they also comprise the raw output of most 3D data acquisition devices. While hand-designed features on point clouds have lon…
View article
A survey of transfer learning Open
Machine learning and data mining techniques have been used in numerous real-world applications. An assumption of traditional machine learning methodologies is the training data and testing data are taken from the same domain, such that the…
View article
Using Embeddings to Improve Named Entity Recognition Classification with Graphs Open
Richer information has potential to improve performance of NLP (Natural Language Processing) tasks such as Named Entity Recognition. A linear sequence of words can be enriched with the sentence structure, as well as their syntactic structu…
View article
Reading digits in natural images with unsupervised feature learning Open
Detecting and reading text from natural images is a hard computer vision task that is central to a variety of emerging applications. Related problems like document character recognition have been widely studied by computer vision and machi…
View article
Inductive Representation Learning on Large Graphs Open
Low-dimensional embeddings of nodes in large graphs have proved extremely useful in a variety of prediction tasks, from content recommendation to identifying protein functions. However, most existing approaches require that all nodes in th…
View article
Deep Learning in Medical Image Analysis Open
This review covers computer-assisted analysis of images in the field of medical imaging. Recent advances in machine learning, especially with regard to deep learning, are helping to identify, classify, and quantify patterns in medical imag…
View article
UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation Open
The state-of-the-art models for medical image segmentation are variants of U-Net and fully convolutional networks (FCN). Despite their success, these models have two limitations: (1) their optimal depth is apriori unknown, requiring extens…
View article
SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition Open
We present SpecAugment, a simple data augmentation method for speech\nrecognition. SpecAugment is applied directly to the feature inputs of a neural\nnetwork (i.e., filter bank coefficients). The augmentation policy consists of\nwarping th…
View article
Wide & Deep Learning for Recommender Systems Open
Generalized linear models with nonlinear feature transformations are widely used for large-scale regression and classification problems with sparse inputs. Memorization of feature interactions through a wide set of cross-product feature tr…
View article
Algorithms for hyper-parameter optimization Open
Several recent advances to the state of the art in image classification benchmarks have come from better configurations of existing techniques rather than novel ap-proaches to feature learning. Traditionally, hyper-parameter optimization h…
View article
Grad-CAM++: Generalized Gradient-Based Visual Explanations for Deep Convolutional Networks Open
Over the last decade, Convolutional Neural Network (CNN) models have been\nhighly successful in solving complex vision problems. However, these deep\nmodels are perceived as "black box" methods considering the lack of\nunderstanding of the…
View article
Deep Learning for Generic Object Detection: A Survey Open
Object detection, one of the most fundamental and challenging problems in computer vision, seeks to locate object instances from a large number of predefined categories in natural images. Deep learning techniques have emerged as a powerful…
View article
Learning Important Features Through Propagating Activation Differences Open
The purported "black box" nature of neural networks is a barrier to adoption in applications where interpretability is essential. Here we present DeepLIFT (Deep Learning Important FeaTures), a method for decomposing the output prediction o…
View article
Squeeze-and-Excitation Networks Open
The central building block of convolutional neural networks (CNNs) is the convolution operator, which enables networks to construct informative features by fusing both spatial and channel-wise information within local receptive fields at e…
View article
A Review of Yolo Algorithm Developments Open
Object detection techniques are the foundation for the artificial intelligence field. This research paper gives a brief overview of the You Only Look Once (YOLO) algorithm and its subsequent advanced versions. Through the analysis, we reac…
View article
Self-Attention Generative Adversarial Networks Open
In this paper, we propose the Self-Attention Generative Adversarial Network (SAGAN) which allows attention-driven, long-range dependency modeling for image generation tasks. Traditional convolutional GANs generate high-resolution details a…
View article
All-optical machine learning using diffractive deep neural networks Open
All-optical deep learning Deep learning uses multilayered artificial neural networks to learn digitally from large datasets. It then performs advanced identification and classification tasks. To date, these multilayered neural networks hav…
View article
Large-Vessel Stroke as a Presenting Feature of Covid-19 in the Young Open
Covid-19 CasesTo rapidly communicate information on the global clinical effort against Covid-19, the Journal has initiated a series of case reports that offer important teaching points or novel findings.The case reports should be viewed as…
View article
DeepFM: A Factorization-Machine based Neural Network for CTR Prediction Open
Learning sophisticated feature interactions behind user behaviors is critical in maximizing CTR for recommender systems. Despite great progress, existing methods seem to have a strong bias towards low- or high-order interactions, or requir…
View article
Feature Selection Open
Feature selection, as a data preprocessing strategy, has been proven to be effective and efficient in preparing data (especially high-dimensional data) for various data-mining and machine-learning problems. The objectives of feature select…
View article
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space Open
Few prior works study deep learning on point sets. PointNet by Qi et al. is a pioneer in this direction. However, by design PointNet does not capture local structures induced by the metric space points live in, limiting its ability to reco…
View article
An Overview of Overfitting and its Solutions Open
Overfitting is a fundamental issue in supervised machine learning which prevents us from perfectly generalizing the models to well fit observed data on training data, as well as unseen data on testing set. Because of the presence of noise,…
View article
Wide Residual Networks Open
Deep residual networks were shown to be able to scale up to thousands of layers and still have improving performance. However, each fraction of a percent of improved accuracy costs nearly doubling the number of layers, and so training very…
View article
Unsupervised Learning of Visual Features by Contrasting Cluster Assignments Open
Unsupervised image representations have significantly reduced the gap with supervised pretraining, notably with the recent achievements of contrastive learning methods. These contrastive methods typically work online and rely on a large nu…
View article
Densely Connected Convolutional Networks Open
Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output. In this paper, we emb…
View article
Deformable DETR: Deformable Transformers for End-to-End Object Detection Open
DETR has been recently proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance. However, it suffers from slow convergence and limited feature spatial resolution, due to the …
View article
Deep Ordinal Regression Network for Monocular Depth Estimation Open
Monocular depth estimation, which plays a crucial role in understanding 3D scene geometry, is an ill-posed problem. Recent methods have gained significant improvement by exploring image-level information and hierarchical features from deep…
View article
Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks Open
Although deep neural networks (DNNs) have achieved great success in many\ntasks, they can often be fooled by \\emph{adversarial examples} that are\ngenerated by adding small but purposeful distortions to natural examples.\nPrevious studies…