liu.seSearch for publications in DiVA
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Stress in Artificial Neural Networks: An explorative stress implementation through emotional weights
Linköping University, Department of Computer and Information Science.
2024 (English)Independent thesis Basic level (degree of Bachelor), 12 credits / 18 HE creditsStudent thesis
Abstract [en]

The exploration of human neurology has been integral to the development of machine learning with neural networks. Initially inspired by the firing of neurons, neural network have seen significant improvements by incorporating cognitive aspects like memory with LSTM, and attention with transformer methods. Drawing from human cognition to enhance neural networks has led to significant advancements in language processing and generative tasks. We explore the integration of stress into neural networks, motivated by its significance for attention and task management. Similar to memory and attention, we propose to directly integrate into neural networks and explore implementation by creating a custom self-attention module for Transformers.

 The aim is to enhance neural networks' adaptability to environmental challenges by identifying threats and developing strong responses to these. By incorporating stress, we seek to improve relational reasoning abilities in neural networks, crucial for effective resource management and learning. Incorporating more cognitive concepts also aims to make neural networks utilize human neurological strengths as emotions.  Two models were developed—one without stress implementation and the other with stress—to assess the architectural changes' effects. Both models were trained and tested in the StarCraft II environment, known for its dynamic and challenging gameplay.  Stress was implemented in the self-attention module of a Transformer layer. An appraisal method for threats and resources was implemented to initiate three different physiological states. Threat weights were learnt through sampling attentional outputs of the self-attention module and modifying it by the game outcome. Queries were linearly transformed with these weights to represent a Threat value for different elements. Resources was determined by the key-query calculation in the dot-product where each pair was seen as confidence in resources. Evaluation then either lowered the Attention if threat-resources were different to simulate apathetic or distressed states, while similar evaluations caused a challenging state increasing focus toward the element. During training both models showed negligible differences in fitting to the dataset and processing speed. Neither model fitted the entire dataset showing that further training could show further differences in progress. When evaluating the models both models showed relatively poor performance only being able to beat bots of the lowest difficulty. The Baseline model won more games and lost more games, while the stress model resulted in timeouts. The stress model showed some effects of stress in regards to changing its strategy to be more cautious and conservative. Stress as a phenomenon in neural networks show possible use cases of changing model strategy to be cautious. Our implementation requires explicit goals limiting it's use cases in domains as NLP. Some aspects of stress remains unexplored such as layer based effects. Overall stress shows promise of affecting agent behaviour with additional testing and fine-tuning required

Place, publisher, year, edition, pages
2024. , p. 26
Keywords [en]
Neural Networks, Stress, Machine Learning, Emotional Artificial Intelligence, Cognitive Evaluation
National Category
Computer Systems
Identifiers
URN: urn:nbn:se:liu:diva-206018ISRN: LIU-IDA/KOGVET-G--24/023--SEOAI: oai:DiVA.org:liu-206018DiVA, id: diva2:1885498
Subject / course
Cognitive science
Supervisors
Examiners
Available from: 2024-08-19 Created: 2024-07-23 Last updated: 2024-08-19Bibliographically approved

Open Access in DiVA

fulltext(405 kB)367 downloads
File information
File name FULLTEXT01.pdfFile size 405 kBChecksum SHA-512
da7b8326750d35470fe4e86cda751f5c4a6f193748501238abed47fd8c442e304f357bf3d4a14d5ca7dae881c986c9707334340241f72228ecb8f17509e7c2be
Type fulltextMimetype application/pdf

By organisation
Department of Computer and Information Science
Computer Systems

Search outside of DiVA

GoogleGoogle Scholar
Total: 371 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 397 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf