Zeszyty czasopisma

Tom 12 (2022): Zeszyt 3 (July 2022)

Tom 12 (2022): Zeszyt 2 (April 2022)

Tom 12 (2022): Zeszyt 1 (January 2022)

Tom 11 (2021): Zeszyt 4 (October 2021)

Tom 11 (2021): Zeszyt 3 (July 2021)

Tom 11 (2021): Zeszyt 2 (April 2021)

Tom 11 (2021): Zeszyt 1 (January 2021)

Tom 10 (2020): Zeszyt 4 (October 2020)

Tom 10 (2020): Zeszyt 3 (July 2020)

Tom 10 (2020): Zeszyt 2 (April 2020)

Tom 10 (2020): Zeszyt 1 (January 2020)

Tom 9 (2019): Zeszyt 4 (October 2019)

Tom 9 (2019): Zeszyt 3 (July 2019)

Tom 9 (2019): Zeszyt 2 (April 2019)

Tom 9 (2019): Zeszyt 1 (January 2019)

Tom 8 (2018): Zeszyt 4 (October 2018)

Tom 8 (2018): Zeszyt 3 (July 2018)

Tom 8 (2018): Zeszyt 2 (April 2018)

Tom 8 (2018): Zeszyt 1 (January 2018)

Tom 7 (2017): Zeszyt 4 (October 2017)

Tom 7 (2017): Zeszyt 3 (July 2017)

Tom 7 (2017): Zeszyt 2 (April 2017)

Tom 7 (2017): Zeszyt 1 (January 2017)

Tom 6 (2016): Zeszyt 4 (October 2016)

Tom 6 (2016): Zeszyt 3 (July 2016)

Tom 6 (2016): Zeszyt 2 (April 2016)

Tom 6 (2016): Zeszyt 1 (January 2016)

Tom 5 (2015): Zeszyt 4 (October 2015)

Tom 5 (2015): Zeszyt 3 (July 2015)

Tom 5 (2015): Zeszyt 2 (April 2015)

Tom 5 (2015): Zeszyt 1 (January 2015)

Tom 4 (2014): Zeszyt 4 (October 2014)

Tom 4 (2014): Zeszyt 3 (July 2014)

Tom 4 (2014): Zeszyt 2 (April 2014)

Tom 4 (2014): Zeszyt 1 (January 2014)

Tom 3 (2013): Zeszyt 4 (October 2013)

Tom 3 (2013): Zeszyt 3 (July 2013)

Tom 3 (2013): Zeszyt 2 (April 2013)

Tom 3 (2013): Zeszyt 1 (January 2013)

Informacje o czasopiśmie
Format
Czasopismo
eISSN
2449-6499
Pierwsze wydanie
30 Dec 2014
Częstotliwość wydawania
4 razy w roku
Języki
Angielski

Wyszukiwanie

Tom 7 (2017): Zeszyt 4 (October 2017)

Informacje o czasopiśmie
Format
Czasopismo
eISSN
2449-6499
Pierwsze wydanie
30 Dec 2014
Częstotliwość wydawania
4 razy w roku
Języki
Angielski

Wyszukiwanie

5 Artykułów
Otwarty dostęp

An English Neural Network that Learns Texts, Finds Hidden Knowledge, and Answers Questions

Data publikacji: 03 May 2017
Zakres stron: 229 - 242

Abstrakt

Abstract

In this paper, a novel neural network is proposed, which can automatically learn and recall contents from texts, and answer questions about the contents in either a large corpus or a short piece of text. The proposed neural network combines parse trees, semantic networks, and inference models. It contains layers corresponding to sentences, clauses, phrases, words and synonym sets. The neurons in the phrase-layer and the word-layer are labeled with their part-of-speeches and their semantic roles. The proposed neural network is automatically organized to represent the contents in a given text. Its carefully designed structure and algorithms make it able to take advantage of the labels and neurons of synonym sets to build the relationship between the sentences about similar things. The experiments show that the proposed neural network with the labels and the synonym sets has the better performance than the others that do not have the labels or the synonym sets while the other parts and the algorithms are the same. The proposed neural network also shows its ability to tolerate noise, to answer factoid questions, and to solve single-choice questions in an exercise book for non-native English learners in the experiments.

Słowa kluczowe

  • natural language processing
  • neural network
  • question answering
  • natural language understanding
Otwarty dostęp

A Machine Learning Approach for the Segmentation of Driving Maneuvers and its Application in Autonomous Parking

Data publikacji: 03 May 2017
Zakres stron: 243 - 255

Abstrakt

Abstract

A classification system for the segmentation of driving maneuvers and its validation in autonomous parking using a small-scale vehicle are presented in this work. The classifiers are designed to detect points that are crucial for the path-planning task, thus enabling the implementation of efficient autonomous parking maneuvers. The training data set is generated by simulations using appropriate vehicle-dynamics models and the resulting classifiers are validated with the small-scale autonomous vehicle. To achieve both a high classification performance and a classification system that can be implemented on a microcontroller with limited computational resources, a two-stage design process is applied. In a first step an ensemble classifier, the Random Forest (RF) algorithm, is constructed and based on the RF-kernel a General Radial Basis Function (GRBF) classifier is generated. The GRBF-classifier is integrated into the small-scale autonomous vehicle leading to excellent performance in parallel-, cross- and oblique-parking maneuvers. The work shows that segmentation using classifies and open-loop control are an efficient approach in autonomous driving for the implementation of driving maneuvers.

Słowa kluczowe

  • autonomous parking
  • ensemble learning
  • maneuver segmentation
Otwarty dostęp

Pseudo-Orthogonalization of Memory Patterns for Complex-Valued and Quaternionic Associative Memories

Data publikacji: 03 May 2017
Zakres stron: 257 - 264

Abstrakt

Abstract

Hebbian learning rule is well known as a memory storing scheme for associative memory models. This scheme is simple and fast, however, its performance gets decreased when memory patterns are not orthogonal each other. Pseudo-orthogonalization is a decorrelating method for memory patterns which uses XNOR masking between the memory patterns and randomly generated patterns. By a combination of this method and Hebbian learning rule, storage capacity of associative memory concerning non-orthogonal patterns is improved without high computational cost. The memory patterns can also be retrieved based on a simulated annealing method by using an external stimulus pattern. By utilizing complex numbers and quaternions, we can extend the pseudo-orthogonalization for complex-valued and quaternionic Hopfield neural networks. In this paper, the extended pseudo-orthogonalization methods for associative memories based on complex numbers and quaternions are examined from the viewpoint of correlations in memory patterns. We show that the method has stable recall performance on highly correlated memory patterns compared to the conventional real-valued method.

Słowa kluczowe

  • Hopfield neural network
  • pseudo-orthogonalization
  • complex numbers
  • quaternions
Otwarty dostęp

Characterization of Symbolic Rules Embedded in Deep DIMLP Networks: A Challenge to Transparency of Deep Learning

Data publikacji: 03 May 2017
Zakres stron: 265 - 286

Abstrakt

Abstract

Rule extraction from neural networks is a fervent research topic. In the last 20 years many authors presented a number of techniques showing how to extract symbolic rules from Multi Layer Perceptrons (MLPs). Nevertheless, very few were related to ensembles of neural networks and even less for networks trained by deep learning. On several datasets we performed rule extraction from ensembles of Discretized Interpretable Multi Layer Perceptrons (DIMLP), and DIMLPs trained by deep learning. The results obtained on the Thyroid dataset and the Wisconsin Breast Cancer dataset show that the predictive accuracy of the extracted rules compare very favorably with respect to state of the art results. Finally, in the last classification problem on digit recognition, generated rules from the MNIST dataset can be viewed as discriminatory features in particular digit areas. Qualitatively, with respect to rule complexity in terms of number of generated rules and number of antecedents per rule, deep DIMLPs and DIMLPs trained by arcing give similar results on a binary classification problem involving digits 5 and 8. On the whole MNIST problem we showed that it is possible to determine the feature detectors created by neural networks and also that the complexity of the extracted rulesets can be well balanced between accuracy and interpretability.

Słowa kluczowe

  • ensembles
  • Deep Learning
  • rule extraction
  • feature detectors
Otwarty dostęp

An Integrative Approach to Analyze Eeg Signals and Human Brain Dynamics in Different Cognitive States

Data publikacji: 03 May 2017
Zakres stron: 287 - 299

Abstrakt

Abstract

Electroencephalograph (EEG) data provide insight into the interconnections and relationships between various cognitive states and their corresponding brain dynamics, by demonstrating dynamic connections between brain regions at different frequency bands. While sensory input tends to stimulate neural activity in different frequency bands, peaceful states of being and self-induced meditation tend to produce activity in the mid-range (Alpha). These studies were conducted with the aim of: (a) testing different equipment in order to assess two (2) different EEG technologies together with their benefits and limitations and (b) having an initial impression of different brain states associated with different experimental modalities and tasks, by analyzing the spatial and temporal power spectrum and applying our movie making methodology to engage in qualitative exploration via the art of encephalography. This study complements our previous study of measuring multichannel EEG brain dynamics using MINDO48 equipment associated with three experimental modalities measured both in the laboratory and the natural environment. Together with Hilbert analysis, we conjecture, the results will provide us with the tools to engage in more complex brain dynamics and mental states, such as Meditation, Mathematical Audio Lectures, Music Induced Meditation, and Mental Arithmetic Exercises. This paper focuses on open eye and closed eye conditions, as well as meditation states in laboratory conditions. We assess similarities and differences between experimental modalities and their associated brain states as well as differences between the different tools for analysis and equipment.

Słowa kluczowe

  • cognition
  • EEG
  • analytic amplitude
  • analytic phase
  • Hilbert transform
  • visual cortex
  • consciousness
  • meditation
  • emotions
  • awareness
  • intentionality
  • spiritual values
5 Artykułów
Otwarty dostęp

An English Neural Network that Learns Texts, Finds Hidden Knowledge, and Answers Questions

Data publikacji: 03 May 2017
Zakres stron: 229 - 242

Abstrakt

Abstract

In this paper, a novel neural network is proposed, which can automatically learn and recall contents from texts, and answer questions about the contents in either a large corpus or a short piece of text. The proposed neural network combines parse trees, semantic networks, and inference models. It contains layers corresponding to sentences, clauses, phrases, words and synonym sets. The neurons in the phrase-layer and the word-layer are labeled with their part-of-speeches and their semantic roles. The proposed neural network is automatically organized to represent the contents in a given text. Its carefully designed structure and algorithms make it able to take advantage of the labels and neurons of synonym sets to build the relationship between the sentences about similar things. The experiments show that the proposed neural network with the labels and the synonym sets has the better performance than the others that do not have the labels or the synonym sets while the other parts and the algorithms are the same. The proposed neural network also shows its ability to tolerate noise, to answer factoid questions, and to solve single-choice questions in an exercise book for non-native English learners in the experiments.

Słowa kluczowe

  • natural language processing
  • neural network
  • question answering
  • natural language understanding
Otwarty dostęp

A Machine Learning Approach for the Segmentation of Driving Maneuvers and its Application in Autonomous Parking

Data publikacji: 03 May 2017
Zakres stron: 243 - 255

Abstrakt

Abstract

A classification system for the segmentation of driving maneuvers and its validation in autonomous parking using a small-scale vehicle are presented in this work. The classifiers are designed to detect points that are crucial for the path-planning task, thus enabling the implementation of efficient autonomous parking maneuvers. The training data set is generated by simulations using appropriate vehicle-dynamics models and the resulting classifiers are validated with the small-scale autonomous vehicle. To achieve both a high classification performance and a classification system that can be implemented on a microcontroller with limited computational resources, a two-stage design process is applied. In a first step an ensemble classifier, the Random Forest (RF) algorithm, is constructed and based on the RF-kernel a General Radial Basis Function (GRBF) classifier is generated. The GRBF-classifier is integrated into the small-scale autonomous vehicle leading to excellent performance in parallel-, cross- and oblique-parking maneuvers. The work shows that segmentation using classifies and open-loop control are an efficient approach in autonomous driving for the implementation of driving maneuvers.

Słowa kluczowe

  • autonomous parking
  • ensemble learning
  • maneuver segmentation
Otwarty dostęp

Pseudo-Orthogonalization of Memory Patterns for Complex-Valued and Quaternionic Associative Memories

Data publikacji: 03 May 2017
Zakres stron: 257 - 264

Abstrakt

Abstract

Hebbian learning rule is well known as a memory storing scheme for associative memory models. This scheme is simple and fast, however, its performance gets decreased when memory patterns are not orthogonal each other. Pseudo-orthogonalization is a decorrelating method for memory patterns which uses XNOR masking between the memory patterns and randomly generated patterns. By a combination of this method and Hebbian learning rule, storage capacity of associative memory concerning non-orthogonal patterns is improved without high computational cost. The memory patterns can also be retrieved based on a simulated annealing method by using an external stimulus pattern. By utilizing complex numbers and quaternions, we can extend the pseudo-orthogonalization for complex-valued and quaternionic Hopfield neural networks. In this paper, the extended pseudo-orthogonalization methods for associative memories based on complex numbers and quaternions are examined from the viewpoint of correlations in memory patterns. We show that the method has stable recall performance on highly correlated memory patterns compared to the conventional real-valued method.

Słowa kluczowe

  • Hopfield neural network
  • pseudo-orthogonalization
  • complex numbers
  • quaternions
Otwarty dostęp

Characterization of Symbolic Rules Embedded in Deep DIMLP Networks: A Challenge to Transparency of Deep Learning

Data publikacji: 03 May 2017
Zakres stron: 265 - 286

Abstrakt

Abstract

Rule extraction from neural networks is a fervent research topic. In the last 20 years many authors presented a number of techniques showing how to extract symbolic rules from Multi Layer Perceptrons (MLPs). Nevertheless, very few were related to ensembles of neural networks and even less for networks trained by deep learning. On several datasets we performed rule extraction from ensembles of Discretized Interpretable Multi Layer Perceptrons (DIMLP), and DIMLPs trained by deep learning. The results obtained on the Thyroid dataset and the Wisconsin Breast Cancer dataset show that the predictive accuracy of the extracted rules compare very favorably with respect to state of the art results. Finally, in the last classification problem on digit recognition, generated rules from the MNIST dataset can be viewed as discriminatory features in particular digit areas. Qualitatively, with respect to rule complexity in terms of number of generated rules and number of antecedents per rule, deep DIMLPs and DIMLPs trained by arcing give similar results on a binary classification problem involving digits 5 and 8. On the whole MNIST problem we showed that it is possible to determine the feature detectors created by neural networks and also that the complexity of the extracted rulesets can be well balanced between accuracy and interpretability.

Słowa kluczowe

  • ensembles
  • Deep Learning
  • rule extraction
  • feature detectors
Otwarty dostęp

An Integrative Approach to Analyze Eeg Signals and Human Brain Dynamics in Different Cognitive States

Data publikacji: 03 May 2017
Zakres stron: 287 - 299

Abstrakt

Abstract

Electroencephalograph (EEG) data provide insight into the interconnections and relationships between various cognitive states and their corresponding brain dynamics, by demonstrating dynamic connections between brain regions at different frequency bands. While sensory input tends to stimulate neural activity in different frequency bands, peaceful states of being and self-induced meditation tend to produce activity in the mid-range (Alpha). These studies were conducted with the aim of: (a) testing different equipment in order to assess two (2) different EEG technologies together with their benefits and limitations and (b) having an initial impression of different brain states associated with different experimental modalities and tasks, by analyzing the spatial and temporal power spectrum and applying our movie making methodology to engage in qualitative exploration via the art of encephalography. This study complements our previous study of measuring multichannel EEG brain dynamics using MINDO48 equipment associated with three experimental modalities measured both in the laboratory and the natural environment. Together with Hilbert analysis, we conjecture, the results will provide us with the tools to engage in more complex brain dynamics and mental states, such as Meditation, Mathematical Audio Lectures, Music Induced Meditation, and Mental Arithmetic Exercises. This paper focuses on open eye and closed eye conditions, as well as meditation states in laboratory conditions. We assess similarities and differences between experimental modalities and their associated brain states as well as differences between the different tools for analysis and equipment.

Słowa kluczowe

  • cognition
  • EEG
  • analytic amplitude
  • analytic phase
  • Hilbert transform
  • visual cortex
  • consciousness
  • meditation
  • emotions
  • awareness
  • intentionality
  • spiritual values

Zaplanuj zdalną konferencję ze Sciendo