arXiv research

Meta-reinforcement learning improves fault-adaptive control efficiency.

Recent developments in machine-learning algorithms have led to impressive performance increases in many traditional application scenarios of artificial intelligence research. In the area of deep reinforcement learning, deep learning functional architectures are combined with incremental learning schemes for sequential …

AdaptOn achieves logarithmic regret in adaptive control of unknown partially observable linear systems.

Adaptive financial dataflow system improves model robustness in dynamic markets.

Paper proposes adaptive control for unknown systems using reinforcement learning.

The abstract explores a new wave equation linking quantum mechanics and complex adaptive systems.

CoDA adapts dynamics models to new physical systems by conditioning on context.

This paper tackles adaptive control of unknown Markov jump systems with sample complexity and regret bounds.

Recursive experts improve dynamic sequential learning systems.

Deep reinforcement learning finds optimal learning policies for adaptive systems.

LqgOpt learns optimal control in unknown LQG systems with minimal regret.

The study sets limits on how well systems can be controlled adaptively.

Adaptive ML learns complex time-varying systems without new data.

Locally adaptive nearest neighbors improve automated systems' performance and are easier to interpret.

Sparse Meta Networks adapt deep neural networks incrementally for fast learning.

Feature extraction from persistence diagrams, as a tool to enrich machine learning techniques, has received increasing attention in recent years. In this paper we explore an adaptive methodology to localize features in persistent diagrams, which are then used in learning tasks. Specifically, we investigate three algori…

Adaptive Stress Testing detects financial fraud by simulating potential failures.

Consider an assistive system that guides visually impaired users through speech and haptic feedback to their destination. Existing robotic and ubiquitous navigation technologies (e.g., portable, ground, or wearable systems) often operate in a generic, user-agnostic manner. However, to minimize confusion and navigation …

FNSDA adapts to new dynamics via Fourier space adaptation.

Study optimizes health incentives to balance efficiency and fairness.

This paper improves MARL for networked systems through new protocols and discount factors.

Work maximization guides machine learning models in adaptive systems.

Paper presents a method for efficient robot adaptation using fine-tuning.

Designs adaptive controller for networked control systems with wireless data transmission.

We present an approach to adaptively utilize deep neural networks in order to reduce the evaluation time on new examples without loss of accuracy. Rather than attempting to redesign or approximate existing networks, we propose two schemes that adaptively utilize networks. We first pose an adaptive network evaluation sc…

Adapts MBDOE for real-time parameter estimation in complex systems.

Wireless systems perform rate adaptation to transmit at highest possible instantaneous rates. Rate adaptation has been increasingly granular over generations of wireless systems. The base-station uses SINR and packet decode feedback called acknowledgement/no acknowledgement (ACK/NACK) to perform rate adaptation. SINR i…

Bayesian approach improves speech recognition with limited speaker data.

First order optimization algorithms play a major role in large scale machine learning. A new class of methods, called adaptive algorithms, were recently introduced to adjust iteratively the learning rate for each coordinate. Despite great practical success in deep learning, their behavior and performance on more genera…

This paper describes a reference architecture for self-maintaining systems that can learn continually, as data arrives. In environments where data evolves, we need architectures that manage Machine Learning (ML) models in production, adapt to shifting data distributions, cope with outliers, retrain when necessary, and …

New algorithm reduces control error in systems with changing dynamics.

Unified framework for adaptive learning systems using consolidation and expansion operations.

Computational Intelligence (CI) is a sub-branch of Artificial Intelligence paradigm focusing on the study of adaptive mechanisms to enable or facilitate intelligent behavior in complex and changing environments. There are several paradigms of CI [like artificial neural networks, evolutionary computations, swarm intelli…

Survey combines FL and control for better adaptability and privacy.

Power system emergency control is generally regarded as the last safety net for grid security and resiliency. Existing emergency control schemes are usually designed off-line based on either the conceived "worst" case scenario or a few typical operation scenarios. These schemes are facing significant adaptiveness and r…

A new method helps deep learning systems adapt to changing conditions.

Interpretable meta-learning for physical systems reduces computational costs and improves interpretability.

Recent deep neural networks based techniques, especially those equipped with the ability of self-adaptation in the system level such as deep reinforcement learning (DRL), are shown to possess many advantages of optimizing robot learning systems (e.g., autonomous navigation and continuous robot arm control.) However, th…

Multi-hop inference is necessary for machine learning systems to successfully solve tasks such as Recognising Textual Entailment and Machine Reading. In this work, we demonstrate the effectiveness of adaptive computation for learning the number of inference steps required for examples of different complexity and that l…

Improved RL algorithm stabilizes unknown linear systems with polynomial regret.

New neural net learns time-reversible symplectic dynamics.

Adaptive filters are applied in several electronic and communication devices like smartphones, advanced headphones, DSP chips, smart antenna, and teleconference systems. Also, they have application in many areas such as system identification, channel equalization, noise reduction, echo cancellation, interference cancel…

NAC-FL optimizes model updates in FL systems by adapting compression to network congestion.

Machine learning approaches have seen considerable applications in human movement modeling, but remain limited for motor learning. Motor learning requires accounting for motor variability, and poses new challenges as the algorithms need to be able to differentiate between new movements and variation of known ones. In t…

Adaptive probabilistic load forecasting improves performance in power systems.

KSOS improves kernel learning for dynamical systems via global optimization.

Adapting policy learning for data collected from evolving systems.

Introduces GFC for learning complex dynamical systems with geometric constraints.