SciTePress - Affiliation Profile

Research.Publish.Connect.

Title:
ISBN:
Year:
Acronym:
Subject:

Advanced Search Proceedings Search

If you're looking for an exact phrase use quotation marks on text fields.

Title:
Author:
Affiliation:
Subject:

Advanced Search Papers Search

If you're looking for an exact phrase use quotation marks on text fields.

Name:
Affiliation:
Country:
Conference:
Subject:

Advanced Search Authors Search

If you're looking for an exact phrase use quotation marks on text fields.

Name:
Country:
Subject:

Advanced Search Affiliations Search

If you're looking for an exact phrase use quotation marks on text fields.

Proceedings

Proceedings Search

Title:
ISBN:
Year:
Acronym:
Subject:

Advanced Search Proceedings Search

If you're looking for an exact phrase use quotation marks on text fields.

Papers

Papers Search

Title:
Author:
Affiliation:
Subject:

Advanced Search Papers Search

If you're looking for an exact phrase use quotation marks on text fields.

Authors

Authors Search

Name:
Affiliation:
Country:
Conference:
Subject:

Advanced Search Authors Search

If you're looking for an exact phrase use quotation marks on text fields.

Advanced Search

Affiliation

Select a Subject
Refine Ontology Subject

FernUniversität in Hagen, Germany

Context (please use complete words only)

Field

Sort by

23 Papers

On the Robustness of Convolutional Neural Networks Regarding Transformed Input Images

Topics: Deep Learning; Convolutional Neural Networks

Authors: Frederik Timme , Jochen Kerdels and Gabriele Peters

Affiliation: Chair of Human-Computer Interaction, Faculty of Mathematics and Computer Science, University of Hagen, Universitätsstraße 47, 58097 Hagen, Germany

Digital Object Identifier: 10.5220/0010107203960403

Proceedings of NCTA 2020, ISBN: 978-989-758-475-6

Quick Abstract

Convolutional Neural Networks (CNNs) have become the dominant and arguably most successful approach for the task of image classification since the release of AlexNet in 2012. Despite their excellent performance, CNNs continue to suffer from a still poorly understood lack of robustness when confronted with adversarial attacks or particular forms of handcrafted datasets. Here we investigate how the recognition performance of three widely used CNN architectures (AlexNet, VGG19 and ResNeXt) changes in response to certain input data transformations. 10,000 images from the ILSVRC2012s validation dataset were systematically manipulated by means of common transformations (translation, rotation, color change, background replacement) as well as methods like image collages and jigsaw-like puzzles. Both the effect of single and combined transformations are investigated. Our results show that three of these input image manipulations (rotation, collage, and puzzle) can cause a significant drop in classification accuracy in all evaluated architectures. In general, the more recent VGG19 and ResNeXt displayed a higher robustness than AlexNet in our experiments indicating that some progress has been made to harden the CNN approach against malicious or unforeseen input.

Challenging the Intuition about Memory and Computation in Theories of Cognition

Topics: Computational Neuroscience; Higher Level Artificial Neural Network Based Intelligent Systems

Authors: Jochen Kerdels and Gabriele Peters

Affiliation: FernUniversität in Hagen, University of Hagen, Human-Computer Interaction, Faculty of Mathematics and Computer Science, Universitätsstrasse 1, D-58097 Hagen and Germany

Digital Object Identifier: 10.5220/0008493605220527

Proceedings of NCTA 2019/IJCCI, ISBN: 978-989-758-384-1

Quick Abstract

In this position paper we argue that the concepts of memory and computation as they are commonly used in theories of cognition are strongly influenced by our intuitive understanding of the corresponding concepts in contemporary computer systems, leading to an implicit loss of biological plausibility. To support our argument we provide an alternative perspective on memory and computation that allows a closer comparison of the capabilities of computer programs running on computer systems and neurobiological systems showing that computer programs exhibit a computational flexibility that is difficult to reconcile with neurobiological constraints. We end this paper by offering a neurobiologically plausible perspective on memory that views memory as a dynamic, distributed process that is an intrinsic part of a neurobiological network that integrates information, e.g., sensory information.

Related Ontology Subjects/Areas/Topics (18)

Artificial Intelligence	Higher Level Artificial Neural Network Based Intelligent Systems	Pattern Recognition
Biomedical Engineering	Human-Computer Interaction	Physiological Computing Systems
Biomedical Signal Processing	Methodologies and Methods	Sensor Networks
Computational Intelligence	Neural Networks	Signal Processing
Computational Neuroscience	Neurocomputing	Soft Computing
Health Engineering and Technology Applications	Neurotechnology, Electronics and Informatics	Theory and Methods

A Grid Cell Inspired Model of Cortical Column Function

Topics: Computational Neuroscience; Self-Organization and Emergence; Neurocomputational Formulations; Neurodynamic Approaches and Solutions

Authors: Jochen Kerdels and Gabriele Peters

Affiliation: FernUniversitt in Hagen – University of Hagen, Human-Computer Interaction, Faculty of Mathematics and Computer Science, Universitätsstrasse 1 , D-58097 Hagen and Germany

Digital Object Identifier: 10.5220/0006931502040210

Proceedings of IJCCI 2018, ISBN: 978-989-758-327-8

Quick Abstract

The cortex of mammals has a distinct, low-level structure consisting of six horizontal layers that are vertically connected by local groups of about 80 to 100 neurons forming so-called minicolumns. A well-known and widely discussed hypothesis suggests that this regular structure may indicate that there could be a common computational principle that governs the diverse functions performed by the cortex. However, no generally accepted theory regarding such a common principle has been presented so far. In this position paper we provide a novel perspective on a possible function of cortical columns. Based on our previous efforts to model the behaviour of entorhinal grid cells we argue that a single cortical column can function as an independent, autoassociative memory cell (AMC) that utilizes a sparse distributed encoding. We demonstrate the basic operation of this AMC by a first set of preliminary simulation results.

Related Ontology Subjects/Areas/Topics (18)

Artificial Intelligence	Human-Computer Interaction	Physiological Computing Systems
Biomedical Engineering	Methodologies and Methods	Self-Organization and Emergence
Biomedical Signal Processing	Neural Networks	Sensor Networks
Computational Intelligence	Neurocomputing	Signal Processing
Computational Neuroscience	Neurotechnology, Electronics and Informatics	Soft Computing
Health Engineering and Technology Applications	Pattern Recognition	Theory and Methods

Self-Learning 3D Object Classification

Topics: Learning in Process Automation and Control; Object Recognition/Tracking

Authors: Jens Garstka and Gabriele Peters

Affiliation: FernUniversitt in Hagen - University of Hagen, Germany

Digital Object Identifier: 10.5220/0006649905110519

Proceedings of ICPRAM 2018, ISBN: 978-989-758-276-9

Quick Abstract

We present a self-learning approach to object classification from 3D point clouds. Existing 3D feature descriptors have been utilized successfully for 3D point cloud classification. But there is not a single best descriptor for any situation. We extend a well-tried 3D object classification pipeline based on local 3D feature descriptors by a reinforcement learning approach that learns strategies to select point cloud descriptors depending on qualities of the point cloud to be classified. The reinforcement learning framework learns autonomously a strategy to select feature descriptors from a provided set of descriptors and to apply them successively for an optimal classification result. Extensive experiments on more than 200.000 3D point clouds yielded higher classification rates with partly more reliable results than a single descriptor setting. Furthermore, our approach proved to be able to preserve classification strategies that have been learned so far while integrating additional descriptors in an ongoing classification process.

Entorhinal Grid Cells May Facilitate Pattern Separation in the Hippocampus

Topic: Computational Neuroscience

Authors: Jochen Kerdels and Gabriele Peters

Affiliation: University of Hagen, Germany

Digital Object Identifier: 10.5220/0006514601410148

Proceedings of IJCCI 2017, ISBN: 978-989-758-274-5

Quick Abstract

The dentate gyrus (DG) in the hippocampus of the mammalian brain is known to exhibit strong pattern separation. However, how this pattern separation arises in the DG is not well understood. Here we offer a novel hypothesis regarding this problem by demonstrating that pattern separation can already be performed by entorhinal grid cells, which are located just one synapse upstream of the DG. For our simulations we utilize a recently introduced grid cell model that interprets the behavior of grid cells as just one instance of a general information processing scheme. The obtained results challenge the established view that pattern separation occurs primarily in the DG, and they uncover a common misconception regarding the specificity of ensemble activity in grid cells.

Related Ontology Subjects/Areas/Topics (17)

Artificial Intelligence	Human-Computer Interaction	Physiological Computing Systems
Biomedical Engineering	Methodologies and Methods	Sensor Networks
Biomedical Signal Processing	Neural Networks	Signal Processing
Computational Intelligence	Neurocomputing	Soft Computing
Computational Neuroscience	Neurotechnology, Electronics and Informatics	Theory and Methods
Health Engineering and Technology Applications	Pattern Recognition

Evaluation of Local 3-D Point Cloud Descriptors in Terms of Suitability for Object Classification

Topic: Vision, Recognition and Reconstruction

Authors: Jens Garstka and Gabriele Peters

Affiliation: Faculty of Mathematics and Computer Science and University of Hagen, Germany

Digital Object Identifier: 10.5220/0006011505400547

Proceedings of ICINCO 2016, ISBN: 978-989-758-198-4

Quick Abstract

This paper investigates existing methods for local 3-D feature description with special regards to their suitability for object classification based on 3-D point cloud data. We choose five approved descriptors, namely Spin Images, Point Feature Histogram, Fast Point Feature Histogram, Signature of Histograms of Orientations, and Unique Shape Context and evaluate them with a commonly used classification pipeline on a large scale 3-D object dataset comprising more than 200000 different point clouds. Of particular interest are the details of the choice of all parameters associated with the classification pipeline. The point clouds are classified by using support vector machines. Fast Point Feature Histogram proves to be the best descriptor for the method of object classification used in this evaluation.

Related Ontology Subjects/Areas/Topics (3)

Informatics in Control, Automation and Robotics

Robotics and Automation

Vision, Recognition and Reconstruction

Modelling the Grid-like Encoding of Visual Space in Primates

Topics: Computational Neuroscience; Neuroinformatics and Bioinformatics; Self-Organization and Emergence

Authors: Jochen Kerdels and Gabriele Peters

Affiliation: University of Hagen, Germany

Digital Object Identifier: 10.5220/0006045500420049

Proceedings of NCTA 2016/IJCCI, ISBN: 978-989-758-201-1

Quick Abstract

Several regions of the mammalian brain contain neurons that exhibit grid-like firing patterns. The most prominent example of such neurons are grid cells in the entorhinal cortex (EC) whose activity correlates with the animal's location. Correspondingly, contemporary models of grid cells interpret this firing behavior as a specialized, functional part within a system for orientation and navigation. However, Killian et al. report on neurons in the primate EC that show similar, grid-like firing patterns but encode gaze-positions in the field of view instead of locations in the environment. We hypothesized that the phenomenon of grid-like firing patterns may not be restricted to navigational tasks and may be related to a more general, underlying information processing scheme. To explore this idea, we developed a grid cell model based on the recursive growing neural gas (RGNG) algorithm that expresses this notion. Here we show that our grid cell model can -- in contrast to established grid cell models -- also describe the observations of Killian et al. and we outline the general conditions under which we would expect neurons to exhibit grid-like activity patterns in response to input signals independent of a presumed, functional task of the neurons.

Related Ontology Subjects/Areas/Topics (19)

Artificial Intelligence	Methodologies and Methods	Physiological Computing Systems
Biomedical Engineering	Neural Networks	Self-Organization and Emergence
Biomedical Signal Processing	Neurocomputing	Sensor Networks
Computational Intelligence	Neuroinformatics and Bioinformatics	Signal Processing
Computational Neuroscience	Neurotechnology, Electronics and Informatics	Soft Computing
Health Engineering and Technology Applications	Pattern Recognition	Theory and Methods
Human-Computer Interaction

Noise Resilience of an RGNG-based Grid Cell Model

Topics: Computational Neuroscience; Neuroinformatics and Bioinformatics; Self-Organization and Emergence

Authors: Jochen Kerdels and Gabriele Peters

Affiliation: University of Hagen, Germany

Digital Object Identifier: 10.5220/0006045400330041

Proceedings of NCTA 2016/IJCCI, ISBN: 978-989-758-201-1

Quick Abstract

Grid cells are neurons in the entorhinal cortex of mammals that are known for their peculiar, grid-like firing patterns. We developed a generic computational model that describes the behavior of neurons with such firing patterns in terms of a competitive, self-organized learning process. Here we investigate how this process can cope with increasing amounts of noise in its input signal. We demonstrate, that the firing patterns of simulated neurons are mostly unaffected with regard to their structure even if high levels of noise are present in the input. In contrast, the maximum activity of the corresponding neurons decreases significantly with increasing levels of noise. Based on these results we predict that real grid cells can retain their triangular firing patterns in the presence of noise, but may exhibit a noticeable decrease in their peak firing rates.

Related Ontology Subjects/Areas/Topics (19)

Artificial Intelligence	Methodologies and Methods	Physiological Computing Systems
Biomedical Engineering	Neural Networks	Self-Organization and Emergence
Biomedical Signal Processing	Neurocomputing	Sensor Networks
Computational Intelligence	Neuroinformatics and Bioinformatics	Signal Processing
Computational Neuroscience	Neurotechnology, Electronics and Informatics	Soft Computing
Health Engineering and Technology Applications	Pattern Recognition	Theory and Methods
Human-Computer Interaction

Adaptive 3-D Object Classification with Reinforcement Learning

Topic: Vision, Recognition and Reconstruction

Authors: Jens Garstka and Gabriele Peters

Affiliation: University of Hagen, Germany

Digital Object Identifier: 10.5220/0005563803810385

Proceedings of ICINCO 2015, ISBN: 978-989-758-123-6

Quick Abstract

We propose an adaptive approach to 3-D object classification. In this approach appropriate 3-D feature descriptor algorithms for 3-D point clouds are selected via reinforcement learning depending on properties of the objects to be classified. This approach is supposed to be able to learn strategies for an advantageous selection of 3-D point cloud descriptor algorithms in an autonomous and adaptive way, and thus is supposed to yield higher object classification rates in unfamiliar environments than any of the single algorithms alone. In addition, we expect our approach to be able to adapt to subsequently added 3-D feature descriptor algorithms as well as to autonomously learn new object categories when encountered in the environment without further user assistance. We describe the 3-D object classification pipeline based on local 3-D features and its integration into the reinforcement learning environment.

Related Ontology Subjects/Areas/Topics (3)

Informatics in Control, Automation and Robotics

Robotics and Automation

Vision, Recognition and Reconstruction

Fast and Robust Keypoint Detection in Unstructured 3-D Point Clouds

Topics: Vision, Recognition and Reconstruction; Mobile Robots and Autonomous Systems; Perception and Awareness; Virtual Environment, Virtual and Augmented Reality

Authors: Jens Garstka and Gabriele Peters

Affiliation: University of Hagen, Germany

Digital Object Identifier: 10.5220/0005569501310140

Proceedings of ICINCO 2015, ISBN: 978-989-758-123-6

Quick Abstract

In robot perception, as well as in other areas of 3-D computer vision, keypoint detection is the first major step for an efficient and accurate 3-D perception of the environment. Thus, a fast and robust algorithm for an automatic identification of keypoints in unstructured 3-D point clouds is essential. The presented algorithm is designed to be highly parallelizable and can be implemented on modern GPUs for fast execution. The computation is based on a convolution of a voxel based representation of the point cloud and a voxelized integral volume. The generation of the voxel-based representation neither requires additional surface information or normals nor needs to approximate them. The proposed approach is robust against noise up to the mean distance between the 3-D points. In addition, the algorithm provides moderate scale invariance, i. e., it can approximate keypoints for lower resolution versions of the input point cloud. This is particularly useful, if keypoints are supposed to be used with any local 3-D point cloud descriptor to recognize or classify point clouds at different scales. We evaluate our approach in a direct comparison with state-of-the-art keypoint detection algorithms in terms of repeatability and computation time.

Related Ontology Subjects/Areas/Topics (6)

Informatics in Control, Automation and Robotics		Perception and Awareness		Virtual Environment, Virtual and Augmented Reality
Mobile Robots and Autonomous Systems		Robotics and Automation		Vision, Recognition and Reconstruction