Related papers: New S-norm and T-norm Operators for Active Learnin…
In UAV dynamic decision, complex and variable hazardous factors pose severe challenges to the generalization capability of algorithms. Despite offering semantic understanding and scene generalization, Large Language Models (LLM) lack…
Active learning (AL) is a human-and-model-in-the-loop paradigm that iteratively selects informative unlabeled data for human annotation, aiming to improve over random sampling. However, performing AL experiments with human annotations…
Deep Active Learning (AL) techniques can be effective in reducing annotation costs for training deep models. However, their effectiveness in low- and high-budget scenarios seems to require different strategies, and achieving optimal results…
Active learning algorithms have been an integral part of recent advances in artificial intelligence. However, the research in the field is widely varying and lacks an overall organizing leans. We outline a Markovian formalism for the field…
Active learning is designed to minimize annotation efforts by prioritizing instances that most enhance learning. However, many active learning strategies struggle with a `cold-start' problem, needing substantial initial data to be…
Soft set theory, introduced by Molodtsov [Molodtsov, D. (1999). Soft set theory-first results. Comput. Math. Appl., 37(4-5), 19-31], provides a flexible framework for managing uncertainty and vagueness, addressing limitations in traditional…
Reinforcement Learning (RL) is an emerging approach to control many dynamical systems for which classical control approaches are not applicable or insufficient. However, the resultant policies may not generalize to variations in the…
A survey of existing methods for stopping active learning (AL) reveals the needs for methods that are: more widely applicable; more aggressive in saving annotations; and more stable across changing datasets. A new method for stopping AL…
The augmented Lagrangian method (ALM) is a classical optimization tool that solves a given "difficult" (constrained) problem via finding solutions of a sequence of "easier"(often unconstrained) sub-problems with respect to the original…
Labeling data can be an expensive task as it is usually performed manually by domain experts. This is cumbersome for deep learning, as it is dependent on large labeled datasets. Active learning (AL) is a paradigm that aims to reduce…
This work develops an active learning framework to intelligently enrich data-driven reduced-order models (ROMs) of parametric dynamical systems, which can serve as the foundation of virtual assets in a digital twin. Data-driven ROMs are…
In situations where the solution of a high-fidelity dynamical system needs to be evaluated repeatedly, over a vast pool of parametric configurations and in absence of access to the underlying governing equations, data-driven model reduction…
Recent advances in natural language processing (NLP) have led to strong text classification models for many tasks. However, still often thousands of examples are needed to train models with good quality. This makes it challenging to quickly…
Model transparency, label correlation learning and the robust-ness to label noise are crucial for multilabel learning. However, few existing methods study these three characteristics simultaneously. To address this challenge, we propose the…
In this paper, we suggest a novel data-driven approach to active learning (AL). The key idea is to train a regressor that predicts the expected error reduction for a candidate sample in a particular learning state. By formulating the query…
In the last years, the adoption of active systems has increased in many fields of computer science, such as databases, sensor networks, and software engineering. These systems are able to automatically react to events, by collecting…
The superior interpretability and uncertainty modeling ability of Takagi-Sugeno-Kang fuzzy system (TSK FS) make it possible to describe complex nonlinear systems intuitively and efficiently. However, classical TSK FS usually adopts the…
The "all-or-nothing" clause evaluation strategy is a core mechanism in the Tsetlin Machine (TM) family of algorithms. In this approach, each clause - a logical pattern composed of binary literals mapped to input data - is disqualified from…
Autonomous robots must operate in complex and changing environments subject to requirements on their behaviour. Verifying absolute satisfaction (true or false) of these requirements is challenging. Instead, we analyse requirements that…
Active learning aims to reduce annotation cost by selectively querying informative samples for supervision under a limited labeling budget. In this work, we investigate how vision-language models (VLMs) can be leveraged to further reduce…