Neural Network Explainable AI Based on Paraconsistent Analysis: An Extension

This paper explores the use of paraconsistent analysis for assessing neural networks from an explainable AI perspective. This is an early exploration paper aiming to understand whether paraconsistent analysis can be applied for understanding neural networks and whether it is worth further develop the subject in future research. The answers to these two questions are affirmative. Paraconsistent analysis provides insightful prediction visualisation through a mature formal framework that provides proper support for reasoning. The significant potential envisioned is the that paraconsistent analysis will be used for guiding neural network development projects, despite the performance issues. This paper provides two explorations. The first was a baseline experiment based on MNIST for establishing the link between paraconsistency and neural networks. The second experiment aimed to detect violence in audio files to verify whether the paraconsistent framework scales to industry level problems. The conclusion shown by this early assessment is that further research on this subject is worthful, and may eventually result in a significant contribution to the field.

Download Full-text

Forecasting Stock Returns with Artificial Neural Networks

Neural Networks in Business Forecasting ◽

10.4018/978-1-59140-176-6.ch003 ◽

2011 ◽

pp. 47-79 ◽

Cited By ~ 5

Author(s):

Suraphan Thawornwong ◽

David Enke

Keyword(s):

Neural Network ◽

Neural Networks ◽

Artificial Neural Network ◽

Artificial Neural Networks ◽

Stock Returns ◽

Future Research ◽

Network Architectures ◽

Network Applications ◽

Artificial Neural ◽

Neural Network Applications

During the last few years there has been growing literature on applications of artificial neural networks to business and financial domains. In fact, a great deal of attention has been placed in the area of stock return forecasting. This is due to the fact that once artificial neural network applications are successful, monetary rewards will be substantial. Many studies have reported promising results in successfully applying various types of artificial neural network architectures for predicting stock returns. This chapter reviews and discusses various neural network research methodologies used in 45 journal articles that attempted to forecast stock returns. Modeling techniques and suggestions from the literature are also compiled and addressed. The results show that artificial neural networks are an emerging and promising computational technology that will continue to be a challenging tool for future research.

Download Full-text

Untangling Neural Nets

American Political Science Review ◽

10.1017/s0003055404001200 ◽

2004 ◽

Vol 98 (2) ◽

pp. 371-378 ◽

Cited By ~ 39

Author(s):

SCOTT DE MARCHI ◽

CHRISTOPHER GELPI ◽

JEFFREY D. GRYNAVISKI

Keyword(s):

Neural Network ◽

Neural Networks ◽

Logit Model ◽

Model Building ◽

Neural Nets ◽

Security Studies ◽

Future Research ◽

Linear Discriminant ◽

Nonparametric Approach ◽

Traditional Approaches

Beck, King, and Zeng (2000) offer both a sweeping critique of the quantitative security studies field and a bold new direction for future research. Despite important strengths in their work, we take issue with three aspects of their research: (1) the substance of the logit model they compare to their neural network, (2) the standards they use for assessing forecasts, and (3) the theoretical and model-building implications of the nonparametric approach represented by neural networks. We replicate and extend their analysis by estimating a more complete logit model and comparing it both to a neural network and to a linear discriminant analysis. Our work reveals that neural networks do not perform substantially better than either the logit or the linear discriminant estimators. Given this result, we argue that more traditional approaches should be relied upon due to their enhanced ability to test hypotheses.

Download Full-text

Neural Networks as Classification Mechanisms of Complex Human Activities

International Journal of Artificial Intelligence Tools ◽

10.1142/s0218213020500116 ◽

2020 ◽

Vol 29 (05) ◽

pp. 2050011

Author(s):

Anargyros Angeleas ◽

Nikolaos Bourbakis

Keyword(s):

Neural Network ◽

Neural Networks ◽

Convolutional Neural Network ◽

Short Term Memory ◽

Neural Nets ◽

Quality Of Data ◽

Short Term ◽

Video Frames ◽

Data Engineering ◽

Formal Framework

Within this paper, we present two neural nets for view-independent complex human activity recognition (HAR) from video frames. For our study here, we reduce the number of frames produced by a video sequence given that we can identify activities from a sparsely sampled sequence of body poses, and, at the same time, we are able to reduce the processing complexity and response while hardly affecting the accuracy, precision, and recall. To do so, we use a formal framework to ensure the quality of data collection and data preprocessing. We utilize neural networks for the classification of single and complex body activities. More specifically, we consider the sequence of body poses as a time-series problem given that they can provide state-of-the-art results on challenging recognition tasks with little data engineering. Deep Learning in the form of Convolutional Neural Network (CNN), Long Short-Term Neural Network (LSTM), and a one-dimensional Convolutional Neural Network Long Short-Term Memory model (CNN-LSTM) are used as benchmarks to classify the activity.

Download Full-text

Automated Whale Blow Detection in Infrared Video

Advances in Environmental Engineering and Green Technologies - Computer Vision and Pattern Recognition in Environmental Informatics ◽

10.4018/978-1-4666-9435-4.ch004 ◽

2015 ◽

pp. 58-78

Author(s):

Varun Santhaseelan ◽

Vijayan K. Asari

Keyword(s):

Neural Network ◽

Neural Networks ◽

Infrared Camera ◽

Future Research ◽

Multi Layer Perceptron ◽

Three Solutions ◽

The Third ◽

Manual Intervention ◽

Infrared Video ◽

Spatio Temporal

In this chapter, solutions to the problem of whale blow detection in infrared video are presented. The solutions are considered to be assistive technology that could help whale researchers to sift through hours or days of video without manual intervention. Video is captured from an elevated position along the shoreline using an infrared camera. The presence of whales is inferred from the presence of blows detected in the video. In this chapter, three solutions are proposed for this problem. The first algorithm makes use of a neural network (multi-layer perceptron) for classification, the second uses fractal features and the third solution is using convolutional neural networks. The central idea of all the algorithms is to attempt and model the spatio-temporal characteristics of a whale blow accurately using appropriate mathematical models. We provide a detailed description and analysis of the proposed solutions, the challenges and some possible directions for future research.

Download Full-text

Control Systems in Manufacturing

4th Flexible Assembly Conference ◽

10.1115/detc1994-0365 ◽

1994 ◽

Author(s):

Mruthyunjaya S. Telagi ◽

Athamaram H. Soni

Keyword(s):

Neural Network ◽

Neural Networks ◽

Fuzzy Logic ◽

Control Systems ◽

Research Trends ◽

Future Research ◽

Cerebellar Model Articulation Controller ◽

Manufacturing Environment ◽

The Future ◽

Planar Robot

Abstract This paper reviews different control methodologies applied in manufacturing environment. Since comparatively newer control methodologies like — Neural networks, Fuzzy logic, and Cerebellar model articulation controller have gained more research interests in recent years, they have been dealt in more detail. With this, we have presented application of neural network for endeffector positioning of three degree planar robot and results have been evaluated. Finally the future research trends in these areas have been discussed.

Download Full-text

Neural Network Identifiability for a Family of Sigmoidal Nonlinearities

Constructive Approximation ◽

10.1007/s00365-021-09544-3 ◽

2021 ◽

Author(s):

Verner Vlačić ◽

Helmut Bölcskei

Keyword(s):

Neural Network ◽

Neural Networks ◽

Network Architecture ◽

Uniform Norm ◽

Feed Forward Neural Network ◽

The Subject ◽

Hidden Layer ◽

Arbitrary Precision ◽

Necessary And Sufficient ◽

Fully Connected

AbstractThis paper addresses the following question of neural network identifiability: Does the input–output map realized by a feed-forward neural network with respect to a given nonlinearity uniquely specify the network architecture, weights, and biases? The existing literature on the subject (Sussman in Neural Netw 5(4):589–593, 1992; Albertini et al. in Artificial neural networks for speech and vision, 1993; Fefferman in Rev Mat Iberoam 10(3):507–555, 1994) suggests that the answer should be yes, up to certain symmetries induced by the nonlinearity, and provided that the networks under consideration satisfy certain “genericity conditions.” The results in Sussman (1992) and Albertini et al. (1993) apply to networks with a single hidden layer and in Fefferman (1994) the networks need to be fully connected. In an effort to answer the identifiability question in greater generality, we derive necessary genericity conditions for the identifiability of neural networks of arbitrary depth and connectivity with an arbitrary nonlinearity. Moreover, we construct a family of nonlinearities for which these genericity conditions are minimal, i.e., both necessary and sufficient. This family is large enough to approximate many commonly encountered nonlinearities to within arbitrary precision in the uniform norm.

Download Full-text

THE IMPACT OF THE LEARNING-BY-EXPORTING EFFECTS ON BUSINESS MODELS: LITERATURE REVIEW AND FUTURE RESEARCH DIRECTIONS

Strategic decisions and risk management ◽

10.17747/2618-947x-2019-3-262-273 ◽

2019 ◽

Vol 10 (3) ◽

pp. 262-273

Author(s):

G. S. Hovakimyan ◽

G. G. Nalbandyan

Keyword(s):

Significant Contribution ◽

Business Models ◽

Future Research ◽

Research Directions ◽

Self Selection ◽

Learning By Exporting ◽

Future Research Directions ◽

The Subject ◽

The Impact ◽

The Relationship

This review makes a significant contribution to the study of the “learning-by-exporting” effect. The article offers a detailed overview of the various views and studies on the subject. The work helps to review the evolution in the field of learning-by-exporting research through bibliometric analysis. Thirdly, this paper focuses on the most cited publications, as well as on the work of the last two or three years. Also, this article discusses the relationship between the learning-by-exporting and the self-selection hypothesis.

Download Full-text

The Representation Theory of Neural Networks

Mathematics ◽

10.3390/math9243216 ◽

2021 ◽

Vol 9 (24) ◽

pp. 3216

Author(s):

Marco Armenta ◽

Pierre-Marc Jodoin

Keyword(s):

Neural Network ◽

Neural Networks ◽

Representation Theory ◽

Oriented Graph ◽

Mathematical Object ◽

Mathematical Representation ◽

Future Research ◽

Quiver Representation ◽

Quiver Representations ◽

The Neural Network

In this work, we show that neural networks can be represented via the mathematical theory of quiver representations. More specifically, we prove that a neural network is a quiver representation with activation functions, a mathematical object that we represent using a network quiver. Furthermore, we show that network quivers gently adapt to common neural network concepts such as fully connected layers, convolution operations, residual connections, batch normalization, pooling operations and even randomly wired neural networks. We show that this mathematical representation is by no means an approximation of what neural networks are as it exactly matches reality. This interpretation is algebraic and can be studied with algebraic methods. We also provide a quiver representation model to understand how a neural network creates representations from the data. We show that a neural network saves the data as quiver representations, and maps it to a geometrical space called the moduli space, which is given in terms of the underlying oriented graph of the network, i.e., its quiver. This results as a consequence of our defined objects and of understanding how the neural network computes a prediction in a combinatorial and algebraic way. Overall, representing neural networks through the quiver representation theory leads to 9 consequences and 4 inquiries for future research that we believe are of great interest to better understand what neural networks are and how they work.

Download Full-text

Using intelligent technologies for tourism

Problems of Innovation and Investment Development ◽

10.33813/2224-1213.24.2021.9 ◽

2021 ◽

pp. 96-105

Author(s):

Nataliia Lytvyn ◽

Svitlana Panchenko

Keyword(s):

Neural Network ◽

Artificial Intelligence ◽

Neural Networks ◽

Knowledge Management ◽

Research Methodology ◽

Network Technology ◽

Inaccurate Information ◽

Tourism Product ◽

The Subject ◽

Neural Network Technology

The purpose of the article is to explore the essence and features of using intelligent technologies in tourism and to develop proposals for their implementation. The subject of research – intelligent technologies in tourism, the technology of forming the “profile” of the tourist. The research methodology consists in the application of methods of analysis, synthesis, comparison, generalization, forecasting, as well as in the use of systematic, activity approaches. The article presents the technology of forming the “profile” of the tourist. It is established that it is necessary to create a world of tourist models, the “profile” of the tourist, as it is a matter of formalizing such poorly structured concepts as “impressions”, “intentions”, etc., it is necessary to use artificial intelligence technologies, in particular neural networks. The scientific novelty is that this article proves the effectiveness of the use of intelligent technologies to create a model of the tourist, his “profile” using neural networks. Conclusions. Effective using of information from various sources in the field of tourism is an important and difficult task. Managers are often forced to make decisions based on partial, incomplete and inaccurate information. The article considers knowledge management in a rapidly changing environment for the task of promoting a tourism product. Neural network technology allows for the effective formation of the “tourist profile” and use all the information in available databases. Key words: tourism, intelligent technologies for tourism, neural networks, tourist profile, tourist product.

Download Full-text