Self Adaptation

Self-adaptation in artificial intelligence focuses on creating systems that can autonomously adjust their behavior in response to changing environments or objectives. Current research emphasizes developing efficient algorithms and models, such as those based on reinforcement learning, evolutionary algorithms, and large language models, to enable this dynamic adaptation. These advancements are improving the robustness and efficiency of various applications, including robotics, portfolio management, and machine learning model optimization, by allowing systems to learn and adapt more effectively in complex and unpredictable situations. The ultimate goal is to create more resilient and adaptable intelligent systems capable of handling unforeseen challenges.

Papers

February 28, 2023

M-L2O: Towards Generalizable Learning-to-Optimize by Test-Time Fast Self-Adaptation
Junjie Yang, Xuxi Chen, Tianlong Chen, Zhangyang Wang, Yingbin Liang
Task Adaptation Self Adaptation Data Driven Optimization L2O Model

January 30, 2023

A Quantification Approach for Transferability in Lifelike Computing Systems
Martin Goller, Sven Tomforde
Task Transferability Self Organization Artificial Life Self Adaptation Biological System Software Behavior

January 22, 2023

Awareness requirement and performance management for adaptive systems: a survey
Tarik A. Rashid, Bryar A. Hassan, Abeer Alsadoon, Shko Qader, S. Vimal, Amit Chhabra, Zaher Mundher Yaseen
Timely Survey Adaptive Importance Performance Evaluation Social Awareness Self Adaptation Self Adaptive System Adaptive System

December 12, 2022

PyPop7: A Pure-Python Library for Population-Based Black-Box Optimization
Qiqi Duan, Guochen Zhou, Chang Shao, Zhuowei Wang, Mingyang Feng, Yijun Yang, Qi Zhao, Yuhui Shi
Metric Learning Black Box Optimization Self Adaptation Population Based Python Toolbox

November 21, 2022

Self-Adaptive, Dynamic, Integrated Statistical and Information Theory Learning
Zsolt János Viharos, Ágnes Szűcs
Neural Network Information Theoretic Self Adaptation Dynamic Learning Training Algorithm Error Metric Levenberg Marquardt

November 4, 2022

Dealing with Drift of Adaptation Spaces in Learning-based Self-Adaptive Systems using Lifelong Self-Adaptation
Omid Gheibi, Danny Weyns
Self Adaptation Real Drift Self Adaptive System Adaptation Space

August 28, 2022

On Evaluating Self-Adaptive and Self-Healing Systems using Chaos Engineering
Moeen Ali Naqvi, Sehrish Malik, Merve Astekin, Leon Moonen
Self Adaptation Self Adaptive System Chaos Theory Self Healing

August 10, 2022

Semantic Self-adaptation: Enhancing Generalization with a Single Sample
Sherwin Bahmani, Oliver Hahn, Eduard Zamfir, Nikita Araslanov, Daniel Cremers, Stefan Roth
Semantic Segmentation Strong Generalization Convolutional Layer Neural Network Generalization Self Adaptation Single Sample

April 13, 2022

Deep Learning for Effective and Efficient Reduction of Large Adaptation Spaces in Self-Adaptive Systems
Danny Weyns, Omid Gheibi, Federico Quin, Jeroen Van Der Donckt
Deep Learning Constructive Reduction Self Adaptation Self Adaptive System Adaptation Space

April 11, 2022

Effective Mutation Rate Adaptation through Group Elite Selection
Akarsh Kumar, Bo Liu, Risto Miikkulainen, Peter Stone
Evolutionary Algorithm Evolutionary Computation Self Adaptation Adaptive Mutation Mutation Rate

April 4, 2022

Lifelong Self-Adaptation: Self-Adaptation Meets Lifelong Machine Learning
Omid Gheibi, Danny Weyns
Self Adaptation Self Adaptive System Lifelong Machine Learning

March 8, 2022

Adaptor: Objective-Centric Adaptation Framework for Language Models
Michal Štefánik, Vít Novotný, Nikola Groverová, Petr Sojka
Language Model Domain Adaptation Unsupervised Domain Adaptation Self Adaptation Model Paradigm Tip Adapter

February 4, 2022

Self-Adaptive Forecasting for Improved Deep Learning on Non-Stationary Time-Series
Sercan O. Arik, Nathanael C. Yoder, Tomas Pfister
Neural Network Self Adaptation Forecasting Task Non Stationary Time Series Adaptive Forecasting

January 11, 2022

Active Reinforcement Learning -- A Roadmap Towards Curious Classifier Systems for Self-Adaptation
Simon Reichhuber, Sven Tomforde
Reinforcement Learning Active Learning Classification Model Reinforcement Learning Approach Requirement Based Roadmap Self Adaptation Reactive Behavior Active Reinforcement Learning

January 2, 2022

Applications of Gaussian Mutation for Self Adaptation in Evolutionary Genetic Algorithms
Okezue Bell
Financial Application Genetic Algorithm Self Adaptation New Metaheuristic Coefficient Mutation

November 23, 2021

Context-based navigation for ground mobile robot in a semi-structured indoor environment
Darko Bozhinoski, Jasper Wijkhuizen
Mobile Robot Indoor Scene Self Adaptation Safe Robot Navigation Solid Ground Model Safety Context Aware Navigation Navigation Scenario