| |
|
|
|
|
|
|
|
|
1. |
Record Nr. |
UNISA996466210403316 |
|
|
Titolo |
Artificial Intelligence and Soft Computing [[electronic resource] ] : 16th International Conference, ICAISC 2017, Zakopane, Poland, June 11-15, 2017, Proceedings, Part I / / edited by Leszek Rutkowski, Marcin Korytkowski, Rafał Scherer, Ryszard Tadeusiewicz, Lotfi A. Zadeh, Jacek M. Zurada |
|
|
|
|
|
|
|
Pubbl/distr/stampa |
|
|
Cham : , : Springer International Publishing : , : Imprint : Springer, , 2017 |
|
|
|
|
|
|
|
|
|
ISBN |
|
|
|
|
|
|
Edizione |
[1st ed. 2017.] |
|
|
|
|
|
Descrizione fisica |
|
1 online resource (XXIV, 776 p. 293 illus.) |
|
|
|
|
|
|
Collana |
|
Lecture Notes in Artificial Intelligence ; ; 10245 |
|
|
|
|
|
|
Disciplina |
|
|
|
|
|
|
Soggetti |
|
Artificial intelligence |
Optical data processing |
Algorithms |
Logic design |
Data mining |
Special purpose computers |
Artificial Intelligence |
Computer Imaging, Vision, Pattern Recognition and Graphics |
Algorithm Analysis and Problem Complexity |
Logic Design |
Data Mining and Knowledge Discovery |
Special Purpose and Application-Based Systems |
|
|
|
|
|
|
|
|
Lingua di pubblicazione |
|
|
|
|
|
|
Formato |
Materiale a stampa |
|
|
|
|
|
Livello bibliografico |
Monografia |
|
|
|
|
|
Nota di contenuto |
|
Intro -- Preface -- Organization -- Contents - Part I -- Contents - Part II -- Neural Networks and Their Applications -- Author Profiling with Classification Restricted Boltzmann Machines -- 1 Introduction -- 2 Author Profile Dimensions -- 3 Restricted Boltzmann Machines -- 4 Probabilities and Gradients -- 4.1 Discriminative Training -- 4.2 Generative Training -- 5 Evaluation Datasets -- 6 Experiments and Results -- 6.1 Overall Results -- 7 Conclusions -- References -- |
|
|
|
|
|
|
|
|
|
Parallel Implementation of the Givens Rotations in the Neural Network Learning Algorithm -- 1 Introduction -- 2 Givens Elimination Step -- 3 Givens QR Decomposition -- 4 QR Decomposition in Neural Network Weights Update -- 5 Parallel Implementation -- 6 Simulation Results -- 7 Conclusion -- References -- Parallel Levenberg-Marquardt Algorithm Without Error Backpropagation -- 1 Introduction -- 2 Parallel Realisation -- 2.1 Calculating the Weight Derivatives Without Error Backpropagation -- 2.2 Calculating the A Matrix and the Gradient Vector -- 2.3 The QR Decomposition Based on the Householser Reflections -- 3 Computational Results -- 4 Conclusions -- References -- Spectral Analysis of CNN for Tomato Disease Identification -- Abstract -- 1 Introduction -- 2 Related Works -- 3 Spectral Analysis of CNN for Tomato Disease -- 3.1 Deep Visualization of CNN -- 3.2 Color Sensitivity of RGB Images -- 3.3 Sensitivity to Color with Different Wavelength Values -- 3.3.1 Visible Spectrum of Images -- 4 Experimental Results -- 4.1 Dataset Description -- 4.2 CNN Activations and Features Visualization -- 4.2.1 Activations of Neurons -- 4.2.2 RGB Color Sensitivity -- 4.2.3 Feature Maps -- 5 Conclusion and Future Work -- Acknowledgments -- References -- From Homogeneous Network to Neural Nets with Fractional Derivative Mechanism -- 1 Introduction -- 2 Weight Distribution with Fractional Calculus. |
3 Fractional Derivative Inside Neuron Transfer Function -- 4 The Fractional Mechanism Within 2D Homogeneous Network -- 5 Conclusion -- References -- Neurons Can Sort Data Efficiently -- 1 Introduction -- 2 Models of Neurons, Receptors, and the Senses -- 2.1 Sensory Fields and Sensors -- 2.2 Extreme, Sensory and Object Neurons -- 3 Simplistic Sequential Neural Associative Sorting -- 4 Conclusions and Remarks -- References -- Avoiding Over-Detection: Towards Combined Object Detection and Counting -- 1 Introduction -- 2 Related Work -- 2.1 Deep Learning Methods for Object Detection -- 2.2 Deep Learning Methods for Cell Detection -- 3 Method -- 3.1 Loss Function -- 3.2 Model Architecture -- 4 Results -- 5 Conclusion -- References -- Echo State Networks Simulation of SIR Distributed Control -- 1 Introduction -- 2 Echo State Networks -- 3 SIR Model with Delay and Spatial Diffusions -- 3.1 Distributed Optimal Control Problem -- 4 Discretisation and Adaptive Critic Neural Networks Solution of the Distributed Optimal Control -- 4.1 Numerical Simulation -- 5 Conclusion -- References -- The Study of Architecture MLP with Linear Neurons in Order to Eliminate the ``vanishing Gradient'' Problem -- 1 Introduction -- 2 Nonlinearity capabilities of deep neural networks -- 3 Approach for Resolving Vanishing Gradient Problem -- 4 Experimental Results -- 5 Conclusions -- References -- Convergence and Rates of Convergence of Recursive Radial Basis Functions Networks in Function Learning and Classification -- 1 Introduction -- 2 Nonlinear Function Learning -- 3 Recursive Classification Rules -- 4 Consistency and Rates of Convergence -- 4.1 Convergence Results -- 4.2 Outlines of Proofs -- 5 Conclusions -- References -- Solar Event Classification Using Deep Convolutional Neural Networks -- 1 Introduction -- 2 Background -- 2.1 Convolutional Neural Networks. |
2.2 Solar Event Classification -- 3 Methods -- 3.1 Data -- 3.2 CNN Architectures -- 4 Experiments -- 4.1 Experimental Setup -- 4.2 Evaluation of the Models -- 4.3 Comparison with Conventional Methods -- 5 Conclusions -- References -- Sequence Learning in Unsupervised and Supervised Vector Quantization Using Hankel Matrices -- 1 Introduction -- 2 Hankel Matrices - Mathematical Description and Properties -- 2.1 General Definition of Hankel Matrices -- 2.2 Dissimilarity Measures for Hankel Matrices -- 3 Unsupervised and Supervised Neural Vector Quantization for Hankel matrices -- 3.1 |
|
|
|
|
|
|
|
Unsupervised Neural Vector Quantization -- 3.2 Supervised Neural Vector Quantization -- 3.3 Hankel Matrices and Neural Vector Quantization -- 4 Existing Application Scenarios and New Perspectives for DNA Sequence Analysis -- 5 Conclusion -- References -- Discrete Cosine Transformation as Alternative to Other Methods of Computational Intelligence for Function Approximation -- 1 Introduction -- 2 Discrete Cosine Transform -- 3 Reduction of the System Size with DCT -- 4 Converting Randomly Distributed Patterns into a Regular Grid -- 5 Comparison of Selected Methods -- 6 Conclusions -- References -- Improvement of RBF Training by Removing of Selected Pattern -- 1 Introduction -- 2 Reduction of the Number of Training Patterns -- 2.1 Error Correction Algorithm -- 2.2 Proposed Methodologies -- 3 Experimental Results -- 3.1 Peaks Function -- 3.2 Rastrigin Function -- 3.3 Schaffer Function -- 4 Conclusions -- References -- Exploring the Solution Space of the Euclidean Traveling Salesman Problem Using a Kohonen SOM Neural Network -- 1 Introduction -- 2 Short Formulation of the ETSP Problem -- 3 The Kohonen SOM Algorithm for Solving ETSP -- 3.1 SOM Learning -- 4 Exploring ETSP Solution Space -- 4.1 Starting Solutions. |
4.2 Computing the Tour Corresponding to the Actual Neuron's Locations -- 4.3 Algorithm -- 5 Simulation Study Using TSPLIB Examples -- 5.1 Pbc3038 Problem (TSPLIB) -- 5.2 pbc1173 Problem (TSPLIB) -- 5.3 bier127 Problem TSPLIB -- 6 Comments and Conclusions -- References -- Resolution Invariant Neural Classifiers for Dermoscopy Images of Melanoma -- 1 Introduction -- 1.1 Medical Background -- 1.2 Wavelets -- 1.3 Melanoma CAD with ANN -- 1.4 Motivation -- 2 Data Analysis -- 2.1 Signal Processing -- 2.2 Wavelet Features -- 2.3 Machine Learning -- 3 Results and Discussion -- References -- Application of Stacked Autoencoders to P300 Experimental Data -- 1 Introduction -- 1.1 P300 Brain-Computer Interfaces -- 1.2 Aims of this Paper -- 2 Theoretical Background -- 2.1 Deep Learning Models -- 2.2 Stacked Autoencoders -- 3 Experimental Design -- 3.1 Measurement -- 3.2 Guess the Number Application for On-line and Off-line BCI Classification -- 4 P300 Detection -- 4.1 Preprocessing and Feature Extraction -- 4.2 Classification -- 5 Results -- 6 Discussion and Future Work -- References -- NARX Neural Network for Prediction of Refresh Timeout in PIM--DM Multicast Routing -- 1 Introduction -- 2 PIM--DM -- 3 PIM--DM Protocol Overview -- 4 PIM--DM Protocol State -- 5 Refresh Timeout -- 6 Nonlinear Autoregressive Network for Prediction of Refresh Timeout -- 7 Simulation Results -- 8 Conclusions -- References -- Evolving Node Transfer Functions in Deep Neural Networks for Pattern Recognition -- 1 Introduction -- 2 Evolution of Deep Neural Networks -- 3 Pattern Recognition Benchmarks -- 3.1 Brodatz Textures -- 3.2 Handwritten Digits -- 3.3 COIL-100 -- 4 Experimental Setting -- 4.1 Initial Architecture of the Deep Neural Network -- 4.2 Node Transfer Functions -- 4.3 Representation of the Deep Evolutionary Neural Network -- 4.4 Search Operators -- 5 Results -- 6 Conclusions. |
References -- A Neural Network Circuit Development via Software-Based Learning and Circuit-Based Fine Tuning -- Abstract -- 1 Introduction -- 2 Memristor-Based Neural Network -- 2.1 The Memristor Bridge Synapse -- 2.2 Memristor-Based Neural Networks -- 3 Proposed Hybrid Learning: Hardware Friendly Error-Backpropagation and Circuit-Based Complementary ... -- 3.1 Random Weight Change Algorithm for Circuit-Based Learning -- 3.2 Hybrid Learning: Software-Based Confined Learning and Circuit-Based Complementary Learning with ... -- 4 Simulation Results -- 5 Conclusions -- References -- Fuzzy Systems and Their Applications -- A Comparative Study of Two |
|
|
|
|
|
|
|
|
|
Novel Approaches to the Rule-Base Evidential Reasoning -- 1 Introduction -- 2 Preliminaries -- 2.1 The Basics of DST -- 2.2 The Basics of A-IFS -- 2.3 Interpretation of A-IFS in the Framework of DST -- 3 Two New Approaches to the Rule-Based Evidential Reasoning: Comparative Study -- 4 Conclusion -- References -- STRIPS in Some Temporal-Preferential Extension -- 1 Introduction -- 1.1 The Paper Motivation and Objectives -- 1.2 The Paper Organization -- 2 Terminological Background of the Paper Analysis -- 2.1 STRIPS -- in the Original Nilsson's Depiction -- 2.2 Fuzzy Temporal Constraints and Preferences Based on Them -- 3 Fuzzy Temporal Constraints and Global Preferences in STRIPS -- 4 TP-STRIPS in Use -- 5 Towards a Generalization and Closing Remarks -- References -- Geometrical Interpretation of Impact of One Set on Another Set -- 1 Introduction -- 2 Matching of Fuzzy Sets -- 3 Matching of Multisets -- 4 Conclusions -- References -- A Method for Nonlinear Fuzzy Modelling Using Population Based Algorithm with Flexibly Selectable Operators -- 1 Introduction -- 2 Description of Proposed Method -- 2.1 Description of Neuro-Fuzzy System Used for Nonlinear Modeling -- 2.2 Encoding of the Individuals. |
2.3 Evaluation of the Individuals. |
|
|
|
|
|
|
Sommario/riassunto |
|
The two-volume set LNAI 10245 and LNAI 10246 constitutes the refereed proceedings of the 16th International Conference on Artificial Intelligence and Soft Computing, ICAISC 2017, held in Zakopane, Poland in June 2017. The 133 revised full papers presented were carefully reviewed and selected from 274 submissions. The papers included in the first volume are organized in the following five parts: neural networks and their applications; fuzzy systems and their applications; evolutionary algorithms and their applications; computer vision, image and speech analysis; and bioinformatics, biometrics and medical applications. |
|
|
|
|
|
|
|
| |