Related papers: Active learning strategies for atomic cluster expa…
Exploration-Exploitation (E{\&}E) algorithms are commonly adopted to deal with the feedback-loop issue in large-scale online recommender systems. Most of existing studies believe that high uncertainty can be a good indicator of potential…
Computer simulations have long been key to understanding and designing phase-change materials (PCMs) for memory technologies. Machine learning is now increasingly being used to accelerate the modelling of PCMs, and yet it remains…
The atomic cluster expansion (ACE) (Drautz, 2019) yields a highly efficient and intepretable parameterisation of symmetric polynomials that has achieved great success in modelling properties of many-particle systems. In the present work we…
Active learning has long been a topic of study in machine learning. However, as increasingly complex and opaque models have become standard practice, the process of active learning, too, has become more opaque. There has been little…
We propose an approach to materials prediction that uses a machine-learning interatomic potential to approximate quantum-mechanical energies and an active learning algorithm for the automatic selection of an optimal training dataset. Our…
In this paper, we propose an actor ensemble algorithm, named ACE, for continuous control with a deterministic policy in reinforcement learning. In ACE, we use actor ensemble (i.e., multiple actors) to search the global maxima of the critic.…
The silicon-hydrogen system is of key interest for solar-cell devices, including both crystalline and amorphous modifications. Elemental amorphous Si is now well understood, but the atomic-scale effects of hydrogenating the silicon matrix…
Although deep neural networks have made remarkable achievements in the field of automatic modulation recognition (AMR), these models often require a large amount of labeled data for training. However, in many practical scenarios, the…
Active learning (AL) aims to enable training high performance classifiers with low annotation cost by predicting which subset of unlabelled instances would be most beneficial to label. The importance of AL has motivated extensive research,…
Active learning (AL) has emerged as a crucial methodology for minimizing labeling costs in deep learning by selecting the most valuable samples from a pool of unlabeled data for annotation. Traditional AL operates under a closed-set…
Conventional active learning (AL) frameworks aim to reduce the cost of data annotation by actively requesting the labeling for the most informative data points. However, introducing AL to data hungry deep learning algorithms has been a…
Cluster expansions are commonly employed as surrogate models to link the electronic structure of an alloy to its finite-temperature properties. Using cluster expansions to model materials with several alloying elements is challenging due to…
An active learner is given a class of models, a large set of unlabeled examples, and the ability to interactively query labels of a subset of these examples; the goal of the learner is to learn a model in the class that fits the data well.…
Inspired by the recent success of machine-learned interatomic potentials for crystal structure prediction of the inorganic crystals, we present a methodology that exploits Moment Tensor Potentials and active learning (based on maxvol…
In reinforcement learning, temporal abstraction in the action space, exemplified by action repetition, is a technique to facilitate policy learning through extended actions. However, a primary limitation in previous studies of action…
Machine-learning force fields enable an accurate and universal description of the potential energy surface of molecules and materials on the basis of a training set of ab initio data. However, large-scale applications of these methods rest…
The performance of machine learning interatomic potentials relies on the quality of the training dataset. In this work, we present an approach for generating diverse and representative training data points which initiates with \it{ab…
Actor-critic (AC) algorithms are a class of model-free deep reinforcement learning algorithms, which have proven their efficacy in diverse domains, especially in solving continuous control problems. Improvement of exploration (action…
The force field describing the calculated interaction between atoms or molecules is the key to the accuracy of many molecular dynamics (MD) simulation results. Compared with traditional or semi-empirical force fields, machine learning force…
Ensemble approaches for deep-learning-based semantic segmentation remain insufficiently explored despite the proliferation of competitive benchmarks and downstream applications. In this work, we explore and benchmark the popular ensembling…