scholarly journals Neural Networks Fusion for Regression Problems

2012 ◽  
pp. 511-516 ◽  
Author(s):  
Ali Shamsoddini ◽  
John C. Trinder
Keyword(s):  
Neural Networks ◽  
Regression Problems

Hidden representations in deep neural networks: Part 2. Regression problems

2020 ◽  
Vol 139 ◽  
pp. 106895 ◽  
Author(s):  
Laya Das ◽  
Abhishek Sivaram ◽  
Venkat Venkatasubramanian
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Regression Problems

scholarly journals Multi-Task Learning for Multi-Dimensional Regression: Application to Luminescence Sensing

2019 ◽  
Vol 9 (22) ◽  
pp. 4748 ◽  
Author(s):  
Umberto Michelucci ◽  
Francesca Venturini
Keyword(s):  
Neural Networks ◽  
Functional Dependence ◽  
Feed Forward ◽  
Multiple Parameters ◽  
Task Learning ◽  
Non Linear ◽  
Input Dataset ◽  
Feed Forward Neural Networks ◽  
Regression Problems ◽  
Multiple Variables

The classical approach to non-linear regression in physics is to take a mathematical model describing the functional dependence of the dependent variable from a set of independent variables, and then using non-linear fitting algorithms, extract the parameters used in the modeling. Particularly challenging are real systems, characterized by several additional influencing factors related to specific components, like electronics or optical parts. In such cases, to make the model reproduce the data, empirically determined terms are built in the models to compensate for the difficulty of modeling things that are, by construction, difficult to model. A new approach to solve this issue is to use neural networks, particularly feed-forward architectures with a sufficient number of hidden layers and an appropriate number of output neurons, each responsible for predicting the desired variables. Unfortunately, feed-forward neural networks (FFNNs) usually perform less efficiently when applied to multi-dimensional regression problems, that is when they are required to predict simultaneously multiple variables that depend from the input dataset in fundamentally different ways. To address this problem, we propose multi-task learning (MTL) architectures. These are characterized by multiple branches of task-specific layers, which have as input the output of a common set of layers. To demonstrate the power of this approach for multi-dimensional regression, the method is applied to luminescence sensing. Here, the MTL architecture allows predicting multiple parameters, the oxygen concentration and temperature, from a single set of measurements.

scholarly journals Fuzzy Neural Networks based on Fuzzy Logic Neurons Regularized by Resampling Techniques and Regularization Theory for Regression Problems

2018 ◽  
pp. 114-133
Author(s):  
Paulo Vitor de Campos Souza
Keyword(s):  
Neural Networks ◽  
Fuzzy Logic ◽  
Learning Algorithm ◽  
Fuzzy Neural Networks ◽  
Compact Set ◽  
Regularization Theory ◽  
Promising Alternative ◽  
Fuzzy Neural ◽  
Regression Problems ◽  
Learning Machine

This paper presents a novel learning algorithm for fuzzy logic neuron based on neural networks and fuzzy systems able to generate accurate and transparent models. The learning algorithm is based on ideas from Extreme Learning Machine [36], to achieve a low time complexity, and regularization theory, resulting in sparse and accurate models. A compact set of incomplete fuzzy rules can be extracted from the resulting network topology. Experiments considering regression problems are detailed. Results suggest the proposed approach as a promising alternative for pattern recognition with a good accuracy and some level of interpretability.

scholarly journals Economic classification and regression problems and neural networks

2011 ◽  
Vol 57 (No. 3) ◽  
pp. 150-157 ◽  
Author(s):  
A. Veselý
Keyword(s):  
Neural Networks ◽  
Network Models ◽  
Neural Network Models ◽  
Economic Agents ◽  
Share Prices ◽  
Currency Exchange ◽  
Currency Exchange Rates ◽  
Software Packages ◽  
The Neural Network ◽  
Regression Problems

Artificial neural networks provide powerful models for solving many economic classifications, as well as regression problems. For example, they were successfully used for the discrimination between healthy economic agents and those prone to bankruptcy, for the inflation-deflation forecasting, for the currency exchange rates prediction, or for the prediction of share prices. At present, the neural models are part of the majority of standard statistical software packages. This paper discusses the basic principles, which the neural network models are based on, and sum up the important principles that must be respected in order that their utilization in practice is efficient.  

scholarly journals Complementary neural networks for regression problems

2009 ◽  
Author(s):  
Pawalai Kraipeerapun ◽  
Sathit Nakkrasae ◽  
Somkid Amornsamankul ◽  
Chun Che Fung
Keyword(s):  
Neural Networks ◽  
Regression Problems

scholarly journals Fuzzy Neural Networks based on Fuzzy Logic Neurons Regularized by Resampling Techniques and Regularization Theory for Regression Problems

2018 ◽  
Vol 21 (62) ◽  
pp. 114 ◽  
Author(s):  
Paulo Vitor De Campos Souza ◽  
Augusto Junio Guimaraes ◽  
Vanessa Souza Ararújo ◽  
Thiago Silva Rezende ◽  
Vinicius Jonathan Silva Araújo
Keyword(s):  
Neural Networks ◽  
Fuzzy Logic ◽  
Learning Algorithm ◽  
Fuzzy Neural Networks ◽  
Compact Set ◽  
Regularization Theory ◽  
Promising Alternative ◽  
Fuzzy Neural ◽  
Regression Problems ◽  
Learning Machine

This paper presents a novel learning algorithm for fuzzy logic neuron based on neural networks and fuzzy systems able to generate accurate and transparent models. The learning algorithm is based on ideas from Extreme Learning Machine [36], to achieve a low time complexity, and regularization theory, resulting in sparse and accurate models. A compact set of incomplete fuzzy rules can be extracted from the resulting network topology. Experiments considering regression problems are detailed. Results suggest the proposed approach as a promising alternative for pattern recognition with a good accuracy and some level of interpretability.

Sign in / Sign up

Export Citation Format

Share Document