Search results for "feature learning"
showing 10 items of 16 documents
Discovering web services in social web service repositories using deep variational autoencoders
2020
Abstract Web Service registries have progressively evolved to social networks-like software repositories. Users cooperate to produce an ever-growing, rich source of Web APIs upon which new value-added Web applications can be built. Such users often interact in order to follow, comment on, consume and compose services published by other users. In this context, Web Service discovery is a core functionality of modern registries as needed Web Services must be discovered before being consumed or composed. Many efforts to provide effective keyword-based service discovery mechanisms are based on Information Retrieval techniques as services are described using structured or unstructured textdocumen…
A Neural Network model for the Evaluation of Text Complexity in Italian Language: a Representation Point of View
2018
Abstract The goal of a text simplification system (TS) is to create a new text suited to the characteristics of a reader, with the final goal of making it more understandable.The building of an Automatic Text Simplification System (ATS) cannot be separated from a correct evaluation of the text complexity. In fact the ATS must be capable of understanding if a text should be simplified for the target reader or not. In a previous work we have presented a model capable of classifying Italian sentences based on their complexity level. Our model is a Long Short Term Memory (LSTM) Neural Network capable of learning the features of easy-to-read and complex-to-read sentences autonomously from a anno…
Unsupervised deep feature extraction of hyperspectral images
2014
This paper presents an effective unsupervised sparse feature learning algorithm to train deep convolutional networks on hyperspectral images. Deep convolutional hierarchical representations are learned and then used for pixel classification. Features in lower layers present less abstract representations of data, while higher layers represent more abstract and complex characteristics. We successfully illustrate the performance of the extracted representations in a challenging AVIRIS hyperspectral image classification problem, compared to standard dimensionality reduction methods like principal component analysis (PCA) and its kernel counterpart (kPCA). The proposed method largely outperforms…
Autoencoders and Data Fusion Based Hybrid Health Indicator for Detecting Bearing and Stator Winding Faults in Electric Motors
2018
The main objective of a condition monitoring programs is to track the health status of critical components of a machine. In this paper, a hybrid health indicator is proposed to monitor the health status of bearings and stator winding of a motor. The proposed method is based on a feature learning from deep autoencoders and data fusion. The features can be learned by autoencoders using individual current and vibration signals, and then learning features are fused to make final health indicators. The experimental data from a permanent magnet synchronous motor is used to validate the proposed method. Promising results in detecting faults and severities of the stator and bearing faults at differ…
A Curvature Based Method for Blind Mesh Visual Quality Assessment Using a General Regression Neural Network
2016
International audience; No-reference quality assessment is a challenging issue due to the non-existence of any information related to the reference and the unknown distortion type. The main goal is to design a computational method to objectively predict the human perceived quality of a distorted mesh and deal with the practical situation when the reference is not available. In this work, we design a no reference method that relies on the general regression neural network (GRNN). Our network is trained using the mean curvature which is an important perceptual feature representing the visual aspect of a 3D mesh. Relatively to the human subjective scores, the trained network successfully asses…
Learning Improved Feature Rankings through Decremental Input Pruning for Support Vector Based Drug Activity Prediction
2010
The use of certain machine learning and pattern recognition tools for automated pharmacological drug design has been recently introduced. Different families of learning algorithms and Support Vector Machines in particular have been applied to the task of associating observed chemical properties and pharmacological activities to certain kinds of representations of the candidate compounds. The purpose of this work, is to select an appropriate feature ordering from a large set of molecular descriptors usually used in the domain of Drug Activity Characterization. To this end, a new input pruning method is introduced and assessed with respect to commonly used feature ranking algorithms.
Convolutional Neural Networks for the Identification of Regions of Interest in PET Scans: A Study of Representation Learning for Diagnosing Alzheimer…
2017
When diagnosing patients suffering from dementia based on imaging data like PET scans, the identification of suitable predictive regions of interest (ROIs) is of great importance. We present a case study of 3-D Convolutional Neural Networks (CNNs) for the detection of ROIs in this context, just using voxel data, without any knowledge given a priori. Our results on data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) suggest that the predictive performance of the method is on par with that of state-of-the-art methods, with the additional benefit of potential insights into affected brain regions.
CostNet: An End-to-End Framework for Goal-Directed Reinforcement Learning
2020
Reinforcement Learning (RL) is a general framework concerned with an agent that seeks to maximize rewards in an environment. The learning typically happens through trial and error using explorative methods, such as \(\epsilon \)-greedy. There are two approaches, model-based and model-free reinforcement learning, that show concrete results in several disciplines. Model-based RL learns a model of the environment for learning the policy while model-free approaches are fully explorative and exploitative without considering the underlying environment dynamics. Model-free RL works conceptually well in simulated environments, and empirical evidence suggests that trial and error lead to a near-opti…
CNN based Gearbox Fault Diagnosis and Interpretation of Learning Features
2021
Machine learning based fault diagnosis schemes have been intensively proposed to deal with faults diagnosis of rotating machineries such as gearboxes, bearings, and electric motors. However, most of the machine learning algorithms used in fault diagnosis are pattern recognition tools, which can classify given data into two or more classes. The underlined physical phenomena in fault diagnosis are not directly interpretable in machine learning schemes, thus it is usually called black/gray box models. In this study, convolutional neural networks (CNN) machine learning algorithm is proposed to classify gearbox faults, and the learning features of the CNN filters are visualized to understand the…
A convolutional neural network framework for blind mesh visual quality assessment
2017
In this paper, we propose a new method for blind mesh visual quality assessment using a deep learning approach. To do this, we first extract visual representative features by computing locally curvature and dihedral angles from each distorted mesh. Then, we determine from these features a set of 2D patches which are learned to a convolutional neural network (CNN). The network consists of two convolutional layers with two max-pooling layers. Then, a multilayer perceptron (MLP) with two fully connected layers is integrated to summarize the learned representation into an output node. With this network structure, feature learning and regression are used to predict the quality score of a given d…