Dalarna University's logo and link to the university's website

du.sePublications
Change search
Link to record
Permanent link

Direct link
Hintze, Arend, ProfessorORCID iD iconorcid.org/0000-0002-4872-1961
Publications (10 of 67) Show all publications
Bohm, C., Hintze, A. & Schossau, J. (2023). A Simple Sparsity Function to Promote Evolutionary Search. In: ALIFE 2023: Ghost in the Machine: Proceedings of the 2023 Artificial Life Conference. Paper presented at 2023 Artificial Life Conference (pp. 368-376).
Open this publication in new window or tab >>A Simple Sparsity Function to Promote Evolutionary Search
2023 (English)In: ALIFE 2023: Ghost in the Machine: Proceedings of the 2023 Artificial Life Conference, 2023, p. 368-376Conference paper, Published paper (Refereed)
National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:du-47521 (URN)10.1162/isal_a_00655 (DOI)
Conference
2023 Artificial Life Conference
Available from: 2023-12-18 Created: 2023-12-18 Last updated: 2023-12-18Bibliographically approved
Rosenthal, M., Richter, D. J., Hübner, F., Staudacher, J. & Hintze, A. (2023). APGG version 1.1. 2-A Modular C++ Framework for Asymmetric Public Goods Games. Zenodo
Open this publication in new window or tab >>APGG version 1.1. 2-A Modular C++ Framework for Asymmetric Public Goods Games
Show others...
2023 (English)Other (Other academic)
Place, publisher, year, pages
Zenodo, 2023
National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:du-47524 (URN)10.5281/zenodo.8334926 (DOI)
Note

Zenodo Software archive corresponding to peer-reviewed publication

Available from: 2023-12-19 Created: 2023-12-19 Last updated: 2023-12-19Bibliographically approved
Rosenthal, M., Richter, D. J., Hübner, F., Staudacher, J. & Hintze, A. (2023). APGG-A Modular C++ Framework for Asymmetric Public Goods Games. Journal of Open Source Software, 8(89), Article ID 4944.
Open this publication in new window or tab >>APGG-A Modular C++ Framework for Asymmetric Public Goods Games
Show others...
2023 (English)In: Journal of Open Source Software, E-ISSN 2475-9066, Vol. 8, no 89, article id 4944Article in journal (Refereed) Published
Abstract [en]

The Asymmetric Public Goods Game (APGG) C++ framework offers an easy to use environmentto study game theoretical questions. Specifically, it is designed to address questions in thedomain of asymmetric public goods games. The modular architecture allows for a vast amountof scenarios and setups for experimenting with different public goods games, using easy tochange parameters. Users can experiment with well mixed and structured populations aswell as with symmetric and asymmetric payoffs. APGG also features group level payoffs andindividual payoffs, and different evolutionary selection mechanisms (Miller et al., 1995) andreplication schemes. Results are automatically saved in semantic and descriptive structuresand can be easily visualized with the included Python scripts. This paper aims to explain thefunctionality and the structure of the framework, to show the workflow that APGG follows, topresent the different modules that are available, and to show how APGG can be used to runexperiments with public goods games on example scenarios.

National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:du-47523 (URN)10.21105/joss.04944 (DOI)
Available from: 2023-12-19 Created: 2023-12-19 Last updated: 2023-12-19Bibliographically approved
Saleh, R., Fleyeh, H., Alam, M. & Hintze, A. (2023). Assessing the color status and daylight chromaticity of road signs through machine learning approaches. IATSS Research, 47(3), 305-317
Open this publication in new window or tab >>Assessing the color status and daylight chromaticity of road signs through machine learning approaches
2023 (English)In: IATSS Research, ISSN 0386-1112, Vol. 47, no 3, p. 305-317Article in journal (Refereed) Published
Abstract [en]

The color of road signs is a critical aspect of road safety, as it helps drivers quickly and accurately identify and respond to these signs. Properly colored road signs improve visibility during the day and make it easier for drivers to make informed decisions while driving. In order to ensure the safety and efficiency of road traffic, it is essential to maintain the appropriate color level of road signs. The objective of this study was to analyze the color status and daylight chromaticity of in-use road signs using supervised machine learning models, and to explore the correlation between road sign's age and daylight chromaticity. Three algorithms were employed: Random Forest (RF), Support Vector Machine (SVM), and Artificial Neural Network (ANN). The data used in this study was collected from road signs that were in-use on roads in Sweden. The study employed classification models to assess the color status (accepted or rejected) of the road signs based on minimum acceptable color levels according to standards, and regression models to predict the daylight chromaticity values. The correlation between road sign's age and daylight chromaticity was explored through regression analysis. Daylight chromaticity describes the color quality of road signs in daylight, that is expressed in terms of X and Y chromaticity coordinates. The study revealed a linear relationship between the road sign's age and daylight chromaticity for blue, green, red, and white sheeting, but not for yellow. The lifespan of red signs was estimated to be around 12 years, much shorter than the estimated lifespans of yellow, green, blue, and white sheeting, which are 35, 42, 45, and 75 years, respectively. The supervised machine learning models successfully assessed the color status of the road signs and predicted the daylight chromaticity values using the three algorithms. The results of this study showed that the ANN classification and ANN regression models achieved high accuracy of 81% and R2 of 97%, respectively. The RF and SVM models also performed well, with accuracy values of 74% and 79% and R2 ranging from 59% to 92%. The findings demonstrate the potential of machine learning to effectively predict the status and daylight chromaticity of road signs and their impact on road safety in the Swedish context. © 2023 International Association of Traffic and Safety Sciences

Keywords
Classification, Daylight chromaticity, Machine learning algorithms, Prediction, Regression, Road signs, Accident prevention, Color, Forecasting, Forestry, Learning algorithms, Learning systems, Motor transportation, Regression analysis, Roads and streets, Support vector machines, Color levels, Machine learning models, Random forests, Regression modelling, Road safety, Supervised machine learning, Neural networks
National Category
Transport Systems and Logistics Computer and Information Sciences
Identifiers
urn:nbn:se:du-46627 (URN)10.1016/j.iatssr.2023.06.003 (DOI)001048708900001 ()2-s2.0-85164276006 (Scopus ID)
Available from: 2023-08-04 Created: 2023-08-04 Last updated: 2023-09-01Bibliographically approved
Hintze, A. (2023). ChatGPT believes it is conscious.
Open this publication in new window or tab >>ChatGPT believes it is conscious
2023 (English)Manuscript (preprint) (Other academic)
National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:du-47517 (URN)10.48550/arXiv.2304.12898 (DOI)
Available from: 2023-12-19 Created: 2023-12-19 Last updated: 2023-12-19Bibliographically approved
Hintze, A. & Adami, C. (2023). Detecting Information Relays in Deep Neural Networks. Entropy, 25(3), Article ID 401.
Open this publication in new window or tab >>Detecting Information Relays in Deep Neural Networks
2023 (English)In: Entropy, E-ISSN 1099-4300, Vol. 25, no 3, article id 401Article in journal (Refereed) Published
Abstract [en]

Deep learning of artificial neural networks (ANNs) is creating highly functional processes that are, unfortunately, nearly as hard to interpret as their biological counterparts. Identification of functional modules in natural brains plays an important role in cognitive and neuroscience alike, and can be carried out using a wide range of technologies such as fMRI, EEG/ERP, MEG, or calcium imaging. However, we do not have such robust methods at our disposal when it comes to understanding functional modules in artificial neural networks. Ideally, understanding which parts of an artificial neural network perform what function might help us to address a number of vexing problems in ANN research, such as catastrophic forgetting and overfitting. Furthermore, revealing a network's modularity could improve our trust in them by making these black boxes more transparent. Here, we introduce a new information-theoretic concept that proves useful in understanding and analyzing a network's functional modularity: the relay information IR. The relay information measures how much information groups of neurons that participate in a particular function (modules) relay from inputs to outputs. Combined with a greedy search algorithm, relay information can be used to identify computational modules in neural networks. We also show that the functionality of modules correlates with the amount of relay information they carry.

Keywords
deep learning, information theory, relay
National Category
Computer Sciences
Identifiers
urn:nbn:se:du-45828 (URN)10.3390/e25030401 (DOI)000960036200001 ()36981289 (PubMedID)2-s2.0-85152710571 (Scopus ID)
Available from: 2023-04-04 Created: 2023-04-04 Last updated: 2023-04-25Bibliographically approved
Mehra, P. & Hintze, A. (2023). Evolution of Pleiotropy and Epistasis in a Gene Regulatory Network. In: ALIFE 2023. Ghost in The Machine. Proceedings of the Artificial Life Conference 2023: . Paper presented at 2023 Artificial Life Conference (pp. 685-687). MIT Press
Open this publication in new window or tab >>Evolution of Pleiotropy and Epistasis in a Gene Regulatory Network
2023 (English)In: ALIFE 2023. Ghost in The Machine. Proceedings of the Artificial Life Conference 2023, MIT Press, 2023, p. 685-687Conference paper, Published paper (Refereed)
Place, publisher, year, edition, pages
MIT Press, 2023
National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:du-47522 (URN)10.1162/isal_a_00604 (DOI)
Conference
2023 Artificial Life Conference
Available from: 2023-12-18 Created: 2023-12-18 Last updated: 2023-12-18Bibliographically approved
Halabi, R., Hintze, A. & Ortiz, A. (2023). Multi-resolution Time-frequency Spectral Derivative Spike Detection for Episode Onset Detection using Passively Collected Sensor Data.
Open this publication in new window or tab >>Multi-resolution Time-frequency Spectral Derivative Spike Detection for Episode Onset Detection using Passively Collected Sensor Data
2023 (English)Manuscript (preprint) (Other academic)
National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:du-47519 (URN)
Available from: 2023-12-19 Created: 2023-12-19 Last updated: 2023-12-19Bibliographically approved
Sardar, N., Khan, S., Hintze, A. & Mehra, P. (2023). Robustness of Sparsely Distributed Representations to Adversarial Attacks in Deep Neural Networks. Entropy, 25(6), Article ID 933.
Open this publication in new window or tab >>Robustness of Sparsely Distributed Representations to Adversarial Attacks in Deep Neural Networks
2023 (English)In: Entropy, E-ISSN 1099-4300, Vol. 25, no 6, article id 933Article in journal (Refereed) Published
Abstract [en]

Deep learning models have achieved an impressive performance in a variety of tasks, but they often suffer from overfitting and are vulnerable to adversarial attacks. Previous research has shown that dropout regularization is an effective technique that can improve model generalization and robustness. In this study, we investigate the impact of dropout regularization on the ability of neural networks to withstand adversarial attacks, as well as the degree of "functional smearing" between individual neurons in the network. Functional smearing in this context describes the phenomenon that a neuron or hidden state is involved in multiple functions at the same time. Our findings confirm that dropout regularization can enhance a network's resistance to adversarial attacks, and this effect is only observable within a specific range of dropout probabilities. Furthermore, our study reveals that dropout regularization significantly increases the distribution of functional smearing across a wide range of dropout rates. However, it is the fraction of networks with lower levels of functional smearing that exhibit greater resilience against adversarial attacks. This suggests that, even though dropout improves robustness to fooling, one should instead try to decrease functional smearing.

Keywords
adversarial attacks, artificial neural networks, dropout, fast gradient sign method, information relay, information smearedness
National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:du-46366 (URN)10.3390/e25060933 (DOI)001017335800001 ()37372277 (PubMedID)2-s2.0-85163826427 (Scopus ID)
Available from: 2023-07-04 Created: 2023-07-04 Last updated: 2023-08-04Bibliographically approved
Schossau, J. & Hintze, A. (2023). Towards a Theory of Mind for Artificial Intelligence Agents. In: ALIFE 2023. Ghost in the MAchine. Proceedings of the Artificial Life Conference 2023: . Paper presented at Artificial Life Conference 2023 (pp. 147-156). MIT Press
Open this publication in new window or tab >>Towards a Theory of Mind for Artificial Intelligence Agents
2023 (English)In: ALIFE 2023. Ghost in the MAchine. Proceedings of the Artificial Life Conference 2023, MIT Press, 2023, p. 147-156Conference paper, Published paper (Refereed)
Place, publisher, year, edition, pages
MIT Press, 2023
National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:du-47520 (URN)10.1162/isal_a_00605 (DOI)
Conference
Artificial Life Conference 2023
Available from: 2023-12-18 Created: 2023-12-18 Last updated: 2023-12-18Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0002-4872-1961

Search in DiVA

Show all publications