A Computational Model of Attention-Guided Visual Learning in a High-Performance Computing Software System
This research investigates transformer architectures in high-performance computing (HPC) software systems for attention-guided visual learning (AGVL). The study focuses on the effects of environmental factors and non-contextual stimuli on cognitive control. It reveals how attention increases respons...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IMS Vogosca
2024-12-01
|
| Series: | Science, Engineering and Technology |
| Subjects: | |
| Online Access: | https://setjournal.com/SET/article/view/245 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841558899887439872 |
|---|---|
| author | Alice Ahmed Md. Tanim Hossain |
| author_facet | Alice Ahmed Md. Tanim Hossain |
| author_sort | Alice Ahmed |
| collection | DOAJ |
| description | This research investigates transformer architectures in high-performance computing (HPC) software systems for attention-guided visual learning (AGVL). The study focuses on the effects of environmental factors and non-contextual stimuli on cognitive control. It reveals how attention increases responses to attentive stimuli, thereby normalizing activity across the population. Transformer blocks use parallelism and less localized attention than current or convolutional models. The study investigates the use of transformer topologies to enhance language modeling, focusing on attention-guided learning and attention-modulated Hebbian plasticity. The model includes an all-attention layer with embedded input vectors, non-contextual vectors containing generic task-relevant information, and self-attentional and feedforward layers. The work employs relative two-dimensional positional encoding to address the challenge of encoding two-dimensional data such as photographs. The feature-similarity gain model proposes that attention multiplicatively strengthens neuronal responses based on how similar their feature tuning is to the attended input. The attention-guided learning approach rewards learning with neural attentional response gain, which the network modifies via gradient descent to achieve the projected objective outputs. The study discovered that supervised error backpropagation and the attention-modulated Hebbian rule outperformed the weight gain rule on MNIST; however, concentration differed.
|
| format | Article |
| id | doaj-art-2f73cec5c5204ca1982fd9db301e0cbf |
| institution | Kabale University |
| issn | 2831-1043 2744-2527 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | IMS Vogosca |
| record_format | Article |
| series | Science, Engineering and Technology |
| spelling | doaj-art-2f73cec5c5204ca1982fd9db301e0cbf2025-01-05T22:04:13ZengIMS VogoscaScience, Engineering and Technology2831-10432744-25272024-12-015110.54327/set2025/v5.i1.245A Computational Model of Attention-Guided Visual Learning in a High-Performance Computing Software SystemAlice Ahmed0https://orcid.org/0009-0005-4625-1280Md. Tanim Hossain1https://orcid.org/0009-0000-8153-5151Department of Software Engineering, Daffodil International University, Dhaka, Bangladesh.Information and Communication Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China.This research investigates transformer architectures in high-performance computing (HPC) software systems for attention-guided visual learning (AGVL). The study focuses on the effects of environmental factors and non-contextual stimuli on cognitive control. It reveals how attention increases responses to attentive stimuli, thereby normalizing activity across the population. Transformer blocks use parallelism and less localized attention than current or convolutional models. The study investigates the use of transformer topologies to enhance language modeling, focusing on attention-guided learning and attention-modulated Hebbian plasticity. The model includes an all-attention layer with embedded input vectors, non-contextual vectors containing generic task-relevant information, and self-attentional and feedforward layers. The work employs relative two-dimensional positional encoding to address the challenge of encoding two-dimensional data such as photographs. The feature-similarity gain model proposes that attention multiplicatively strengthens neuronal responses based on how similar their feature tuning is to the attended input. The attention-guided learning approach rewards learning with neural attentional response gain, which the network modifies via gradient descent to achieve the projected objective outputs. The study discovered that supervised error backpropagation and the attention-modulated Hebbian rule outperformed the weight gain rule on MNIST; however, concentration differed. https://setjournal.com/SET/article/view/245Computational ModelAttention-Guided Visual LearningHigh-Performance ComputingReinforcement LearningComputer Vision |
| spellingShingle | Alice Ahmed Md. Tanim Hossain A Computational Model of Attention-Guided Visual Learning in a High-Performance Computing Software System Science, Engineering and Technology Computational Model Attention-Guided Visual Learning High-Performance Computing Reinforcement Learning Computer Vision |
| title | A Computational Model of Attention-Guided Visual Learning in a High-Performance Computing Software System |
| title_full | A Computational Model of Attention-Guided Visual Learning in a High-Performance Computing Software System |
| title_fullStr | A Computational Model of Attention-Guided Visual Learning in a High-Performance Computing Software System |
| title_full_unstemmed | A Computational Model of Attention-Guided Visual Learning in a High-Performance Computing Software System |
| title_short | A Computational Model of Attention-Guided Visual Learning in a High-Performance Computing Software System |
| title_sort | computational model of attention guided visual learning in a high performance computing software system |
| topic | Computational Model Attention-Guided Visual Learning High-Performance Computing Reinforcement Learning Computer Vision |
| url | https://setjournal.com/SET/article/view/245 |
| work_keys_str_mv | AT aliceahmed acomputationalmodelofattentionguidedvisuallearninginahighperformancecomputingsoftwaresystem AT mdtanimhossain acomputationalmodelofattentionguidedvisuallearninginahighperformancecomputingsoftwaresystem AT aliceahmed computationalmodelofattentionguidedvisuallearninginahighperformancecomputingsoftwaresystem AT mdtanimhossain computationalmodelofattentionguidedvisuallearninginahighperformancecomputingsoftwaresystem |