LIQUID-BRAIN NETWORKS: BIOLOGICALLY INSPIRED FRAMEWORK FOR REAL-TIME ADAPTATION AND LIFELONG LEARNING IN NON-STATIONARY ENVIRONMENTS
Fuente:
Zenodo
Enregistré dans:
| Auteur principal: | |
|---|---|
| Format: | Recurso digital |
| Langue: | anglais |
| Publié: |
Zenodo
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866901529610420224 |
|---|---|
| author | Researcher |
| author_facet | Researcher |
| contents | <p><span lang="EN-US">The Liquid-Brain Network (LBN) paradigm draws from biological principles of neural plasticity and real-time adaptation to address challenges posed by non-stationary learning environments. Inspired by neurodynamic plasticity and recurrent attention mechanisms, this architecture facilitates lifelong learning, efficient memory representation, and adaptive reasoning. The architecture dynamically encodes temporal patterns through variable neural states, enabling continuous learning and generalization without catastrophic forgetting.</span></p> <p><span lang="EN-US">This paper proposes a comprehensive framework that integrates time-varying neuron states with recurrent attention modules, enhancing the model’s ability to react, adapt, and store evolving patterns. Benchmarking results highlight LBN's superior performance in energy efficiency, memory retention, and adaptability compared to classical recurrent and spiking models. Furthermore, visual illustrations, graphs, and comparative tables demonstrate its operational advantage for smart autonomous systems.</span></p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_15647125 |
| institution | Zenodo |
| language | eng |
| publishDate | 2025 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | LIQUID-BRAIN NETWORKS: BIOLOGICALLY INSPIRED FRAMEWORK FOR REAL-TIME ADAPTATION AND LIFELONG LEARNING IN NON-STATIONARY ENVIRONMENTS Researcher Liquid-brain networks, lifelong learning, recurrent attention, non-stationary environments, neural plasticity, biological AI <p><span lang="EN-US">The Liquid-Brain Network (LBN) paradigm draws from biological principles of neural plasticity and real-time adaptation to address challenges posed by non-stationary learning environments. Inspired by neurodynamic plasticity and recurrent attention mechanisms, this architecture facilitates lifelong learning, efficient memory representation, and adaptive reasoning. The architecture dynamically encodes temporal patterns through variable neural states, enabling continuous learning and generalization without catastrophic forgetting.</span></p> <p><span lang="EN-US">This paper proposes a comprehensive framework that integrates time-varying neuron states with recurrent attention modules, enhancing the model’s ability to react, adapt, and store evolving patterns. Benchmarking results highlight LBN's superior performance in energy efficiency, memory retention, and adaptability compared to classical recurrent and spiking models. Furthermore, visual illustrations, graphs, and comparative tables demonstrate its operational advantage for smart autonomous systems.</span></p> |
| title | LIQUID-BRAIN NETWORKS: BIOLOGICALLY INSPIRED FRAMEWORK FOR REAL-TIME ADAPTATION AND LIFELONG LEARNING IN NON-STATIONARY ENVIRONMENTS |
| topic | Liquid-brain networks, lifelong learning, recurrent attention, non-stationary environments, neural plasticity, biological AI |
| url | https://doi.org/10.5281/zenodo.15647125 |