scholarly journals Logic Tensor Networks for Semantic Image Interpretation

2017 ◽  
Author(s):  
Ivan Donadello ◽  
Luciano Serafini ◽  
Artur d'Avila Garcez
Keyword(s):  
Neural Networks ◽  
Image Interpretation ◽  
Background Knowledge ◽  
Learning System ◽  
Training Data ◽  
Reasoning Under Uncertainty ◽  
Tensor Networks ◽  
Logical Constraints ◽  
Bounding Boxes ◽  
Efficient Learning

Semantic Image Interpretation (SII) is the task of extracting structured semantic descriptions from images. It is widely agreed that the combined use of visual data and background knowledge is of great importance for SII. Recently, Statistical Relational Learning (SRL) approaches have been developed for reasoning under uncertainty and learning in the presence of data and rich knowledge. Logic Tensor Networks (LTNs) are a SRL framework which integrates neural networks with first-order fuzzy logic to allow (i) efficient learning from noisy data in the presence of logical constraints, and (ii) reasoning with logical formulas describing general properties of the data. In this paper, we develop and apply LTNs to two of the main tasks of SII, namely, the classification of an image's bounding boxes and the detection of the relevant part-of relations between objects. To the best of our knowledge, this is the first successful application of SRL to such SII tasks. The proposed approach is evaluated on a standard image processing benchmark. Experiments show that background knowledge in the form of logical constraints can improve the performance of purely data-driven approaches, including the state-of-the-art Fast Region-based Convolutional Neural Networks (Fast R-CNN). Moreover, we show that the use of logical background knowledge adds robustness to the learning system when errors are present in the labels of the training data.

scholarly journals Improvement of E-learning Based via Learning Management Systems (LMS) Using Artificial Neural Networks

2019 ◽  
pp. 1-9
Author(s):  
Khaled . M. G Noama ◽  
Ahmed Khalid ◽  
Arafat A. Muharram ◽  
Ibrahim A. Ahmed
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Real Data ◽  
Feedforward Neural Network ◽  
Learning System ◽  
Training Data ◽  
Factors Affecting ◽  
Virtual Class ◽  
Innovative Learning ◽  
E Learning

E-Learning nowadays is one of the learning system which uses the latest technologies in the field of innovative learning, it has been an extension of traditional education. The effectiveness of E-Learning lies in achievement of education and improving the student's performance and its reflection on the demands of students by discovering the weaknesses and strengths of the factors affecting distance learning. In this research we have used the multilayered neural networks (feedforward neural network) with an input of five neurons which represent the five criteria (virtual class presence, Discussion during semester, Solving Quiz, Mid-term examination, Assignment), hidden layer has two neurons and the output layers have one neuron. to estimate the performance of the students attending an E-Learning course, feedforward neural network was  applied to real data )400 student records (80%) are used for training data and the remaining 100 records (20%) are used as test data, performance = 0.0699), to  predict the performance of  the students   that reflect their real grades.

scholarly journals ALMI—A Generic Active Learning System for Computational Object Classification in Marine Observation Images

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1134
Author(s):  
Torben Möller ◽  
Tim W. Nattkemper
Keyword(s):  
Time Series ◽  
Active Learning ◽  
A Priori ◽  
Image Interpretation ◽  
Reference Method ◽  
Quantitative Information ◽  
Learning System ◽  
Training Data ◽  
Data Set ◽  
Feature Representations

In recent years, an increasing number of cabled Fixed Underwater Observatories (FUOs) have been deployed, many of them equipped with digital cameras recording high-resolution digital image time series for a given period. The manual extraction of quantitative information from these data regarding resident species is necessary to link the image time series information to data from other sensors but requires computational support to overcome the bottleneck problem in manual analysis. As a priori knowledge about the objects of interest in the images is almost never available, computational methods are required that are not dependent on the posterior availability of a large training data set of annotated images. In this paper, we propose a new strategy for collecting and using training data for machine learning-based observatory image interpretation much more efficiently. The method combines the training efficiency of a special active learning procedure with the advantages of deep learning feature representations. The method is tested on two highly disparate data sets. In our experiments, we can show that the proposed method ALMI achieves on one data set a classification accuracy A > 90% with less than N = 258 data samples and A > 80% after N = 150 iterations, i.e., training samples, on the other data set outperforming the reference method regarding accuracy and training data required.

An Efficient Learning of Neural Networks to Acquire Inverse Kinematics Model

2020 ◽  
pp. 203-232
Author(s):  
Fusaomi Nagata ◽  
Maki K. Habib ◽  
Keigo Watanabe
Keyword(s):  
Neural Networks ◽  
Inverse Kinematics ◽  
Industrial Robot ◽  
Training Data ◽  
Serial Link ◽  
Data Set ◽  
Effective Learning ◽  
The Neural Networks ◽  
Efficient Learning ◽  
Time Required

In this chapter, effective learning approach of inverse kinematics using neural networks with efficient weights update ability has been presented for a serial link structure and industrial robot. Generally, in making neural networks learn a relation among multi inputs and outputs, a desired training data set prepared in advance is used. The training data set consists of multiple pairs of input and output vectors. The input layer receives each input vector for forward computation, and it is compared with the yielded vector from the output layer. The time required for the learning process of the neural networks depends on the number of total weights in the neural networks and that of the input-output pairs in the training data set.

scholarly journals Deep Learning on Low-Resource Datasets

2018 ◽  
Author(s):  
Veronica Morfi ◽  
Dan Stowell
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Deep Neural Networks ◽  
Learning System ◽  
Training Data ◽  
Quality Performance ◽  
Training Performance ◽  
Low Resource ◽  
Advantages And Disadvantages

In training a deep learning system to perform audio transcription, two practical problems may arise. Firstly, most datasets are weakly labelled, having only a list of events present in each recording without any temporal information for training. Secondly, deep neural networks need a very large amount of labelled training data to achieve good quality performance, yet in practice it is difficult to collect enough samples for most classes of interest. In this paper, we propose factorising the final task of audio transcription into multiple intermediate tasks in order to improve the training performance when dealing with this kind of low-resource datasets. We evaluate three data-efficient approaches of training a stacked convolutional and recurrent neural network for the intermediate tasks. Our results show that different methods of training have different advantages and disadvantages.

scholarly journals Exploring the Knowledge Embedded in Class Visualizations and Their Application in Dataset and Extreme Model Compression

2021 ◽  
Vol 11 (20) ◽  
pp. 9374
Author(s):  
José Ricardo Abreu-Pederzini  ◽  
Guillermo Arturo Martínez-Mascorro ◽  
José Carlos Ortíz-Bayliss ◽  
Hugo Terashima-Marín
Keyword(s):  
Neural Networks ◽  
Computer Vision ◽  
Artificial Neural Networks ◽  
Language Processing ◽  
Training Data ◽  
Visual Aids ◽  
Model Compression ◽  
Extreme Model ◽  
Artificial Neural ◽  
Efficient Learning

Artificial neural networks are efficient learning algorithms that are considered to be universal approximators for solving numerous real-world problems in areas such as computer vision, language processing, or reinforcement learning. To approximate any given function, neural networks train a large number of parameters—up to millions, or even billions in some cases. The large number of parameters and hidden layers in neural networks make them hard to interpret, which is why they are often referred to as black boxes. In the quest to make artificial neural networks interpretable in the field of computer vision, feature visualization stands out as one of the most developed and promising research directions. While feature visualizations are a valuable tool to gain insights about the underlying function learned by the network, they are still considered to be simple visual aids requiring human interpretation. In this paper, we propose that feature visualizations—class visualizations in particular—are analogous to mental imagery in humans, resembling the experience of seeing or perceiving the actual training data. Therefore, we propose that class visualizations contain embedded knowledge that can be exploited in a more automated manner. We present a series of experiments that shed light on the nature of class visualizations and demonstrate that class visualizations can be considered a conceptual compression of the data used to train the underlying model. Finally, we show that class visualizations can be regarded as convolutional filters and experimentally show their potential for extreme model compression purposes.

Operational Determination of the Activated Sludge Process Using Neural Networks

1992 ◽  
Vol 26 (9-11) ◽  
pp. 2461-2464 ◽  
Author(s):  
R. D. Tyagi ◽  
Y. G. Du
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Steady State ◽  
Activated Sludge ◽  
Feedforward Neural Network ◽  
Training Data ◽  
Activated Sludge Process

A steady-statemathematical model of an activated sludgeprocess with a secondary settler was developed. With a limited number of training data samples obtained from the simulation at steady state, a feedforward neural network was established which exhibits an excellent capability for the operational prediction and determination.

scholarly journals Improving Semi-Supervised Learning for Audio Classification with FixMatch

Electronics ◽  
2021 ◽  
Vol 10 (15) ◽  
pp. 1807
Author(s):  
Sascha Grollmisch ◽  
Estefanía Cano
Keyword(s):  
Neural Networks ◽  
Supervised Learning ◽  
Transfer Learning ◽  
Data Transfer ◽  
State Of The Art ◽  
Training Data ◽  
Audio Classification ◽  
Image Domain ◽  
Full Dataset ◽  
Audio Data

Including unlabeled data in the training process of neural networks using Semi-Supervised Learning (SSL) has shown impressive results in the image domain, where state-of-the-art results were obtained with only a fraction of the labeled data. The commonality between recent SSL methods is that they strongly rely on the augmentation of unannotated data. This is vastly unexplored for audio data. In this work, SSL using the state-of-the-art FixMatch approach is evaluated on three audio classification tasks, including music, industrial sounds, and acoustic scenes. The performance of FixMatch is compared to Convolutional Neural Networks (CNN) trained from scratch, Transfer Learning, and SSL using the Mean Teacher approach. Additionally, a simple yet effective approach for selecting suitable augmentation methods for FixMatch is introduced. FixMatch with the proposed modifications always outperformed Mean Teacher and the CNNs trained from scratch. For the industrial sounds and music datasets, the CNN baseline performance using the full dataset was reached with less than 5% of the initial training data, demonstrating the potential of recent SSL methods for audio data. Transfer Learning outperformed FixMatch only for the most challenging dataset from acoustic scene classification, showing that there is still room for improvement.

scholarly journals Experiments with Neural Networks in the Identification and Control of a Magnetic Levitation System Using a Low-Cost Platform

2021 ◽  
Vol 11 (6) ◽  
pp. 2535
Author(s):  
Bruno E. Silva ◽  
Ramiro S. Barbosa
Keyword(s):  
Neural Networks ◽  
Neural Control ◽  
Magnetic Levitation ◽  
Low Cost ◽  
Training Data ◽  
Neural Controllers ◽  
Levitation System ◽  
Internal Model Controller ◽  
Magnetic Levitation System ◽  
And Performance

In this article, we designed and implemented neural controllers to control a nonlinear and unstable magnetic levitation system composed of an electromagnet and a magnetic disk. The objective was to evaluate the implementation and performance of neural control algorithms in a low-cost hardware. In a first phase, we designed two classical controllers with the objective to provide the training data for the neural controllers. After, we identified several neural models of the levitation system using Nonlinear AutoRegressive eXogenous (NARX)-type neural networks that were used to emulate the forward dynamics of the system. Finally, we designed and implemented three neural control structures: the inverse controller, the internal model controller, and the model reference controller for the control of the levitation system. The neural controllers were tested on a low-cost Arduino control platform through MATLAB/Simulink. The experimental results proved the good performance of the neural controllers.

Sign in / Sign up

Export Citation Format

Share Document