Adaptive Machine

Adaptive machines represent a rapidly evolving field focused on creating systems capable of dynamically adjusting to changing conditions, including hardware faults and varying environmental factors. Current research emphasizes the use of reinforcement learning algorithms (like PPO and SAC), ensemble methods for outlier detection in machine learning models, and novel architectures such as fermion neural networks, to improve robustness, efficiency, and adaptability. These advancements are significant for enhancing the reliability and performance of machine learning-enabled systems across diverse applications, from robotics and hardware design to complex scientific simulations.

Papers

November 14, 2024

An Adaptive Open-Source Dataset Generation Framework for Machine Learning Tasks in Logic Synthesis
Liwei Ni, Rui Wang, Miao Liu, Xingyu Meng, Xiaoze Lin, Junfeng Liu, Guojie Luo, Zhufei Chu, Weikang Qian, Xiaoyan Yang, Biwei Xie, Xingquan Li, Huawei Li
New Machine Dataset Generation Logic Synthesis Learning Task Adaptive Machine

September 19, 2024

CraftRTL: High-quality Synthetic Data Generation for Verilog Code Models with Correct-by-Construction Non-Textual Representations and Targeted Code Repair
Mingjie Liu, Yun-Da Tsai, Wenfei Zhou, Haoxing Ren
Code Generation Synthetic Data Generation Contextual Representation Fine Tuned LLM Hardware Description Language Adaptive Machine

July 21, 2024

Enhancing Hardware Fault Tolerance in Machines with Reinforcement Learning Policy Gradient Algorithms
Sheila Schoepp, Mehran Taghian, Shotaro Miwa, Yoshihiro Mitsuka, Shadan Golestan, Osmar Zaïane
New Machine Policy Gradient Proximal Policy Optimization Robot Learning State of the Art Reinforcement Adaptive Machine

February 27, 2024

Outlier-Detection for Reactive Machine Learned Potential Energy Surfaces
Luis Itza Vazquez-Salazar, Silvan Käser, Markus Meuwly
Uncertainty Quantification Outlier Detection Ensemble Model High Uncertainty Value Potential Energy Surface Evidential Regression Adaptive Machine

December 18, 2023

Counting Reward Automata: Sample Efficient Reinforcement Learning Through the Exploitation of Reward Function Structure
Tristan Bester, Benjamin Rosman, Steven James, Geraud Nangue Tasse
Reward Function Sample Efficient Reinforcement Learning Real World eXploitation Finite State Machine Adaptive Machine Automaton Model

August 19, 2023

Towards Self-Adaptive Machine Learning-Enabled Systems Through QoS-Aware Model Switching
Shubham Kulkarni, Arya Marda, Karthik Vaidhyanathan
System Description Self Adaptation Self Adaptive System Adaptive Machine Model Switching

May 1, 2023

Human adaptation to adaptive machines converges to game-theoretic equilibria
Benjamin J. Chasnov, Lillian J. Ratliff, Samuel A. Burden
Game Theoretic Game Theory Adaptive Machine Human Adaptation Adaptive Partner

December 7, 2022

FPGA Implementation of Multi-Layer Machine Learning Equalizer with On-Chip Training
Keren Liu, Erik Börjeson, Christian Häger, Per Larsson-Edefors
Parametric Equalizer Chip Learning FPGA Implementation Neural Network Based Equalizer Adaptive Machine

November 10, 2022

Efficient and quantum-adaptive machine learning with fermion neural networks
Pei-Lin Zheng, Jia-Bao Wang, Yi Zhang
Neural Network High Efficiency Quantum Physic Quantum System Classical Neural Network Adaptive Machine Bell Correlation

Adaptive Machine

Papers

An Adaptive Open-Source Dataset Generation Framework for Machine Learning Tasks in Logic Synthesis

CraftRTL: High-quality Synthetic Data Generation for Verilog Code Models with Correct-by-Construction Non-Textual Representations and Targeted Code Repair

Enhancing Hardware Fault Tolerance in Machines with Reinforcement Learning Policy Gradient Algorithms

Outlier-Detection for Reactive Machine Learned Potential Energy Surfaces

Counting Reward Automata: Sample Efficient Reinforcement Learning Through the Exploitation of Reward Function Structure

Towards Self-Adaptive Machine Learning-Enabled Systems Through QoS-Aware Model Switching

Human adaptation to adaptive machines converges to game-theoretic equilibria

FPGA Implementation of Multi-Layer Machine Learning Equalizer with On-Chip Training

Efficient and quantum-adaptive machine learning with fermion neural networks