相关论文: Curiosity-driven search for novel non-equilibrium …

Ordered, collective motions commonly arise spontaneously in systems of many interacting, active units, ranging from cellular tissues and bacterial colonies to self-propelled colloids and animal flocks. Active phases are especially rich when…

Active learning emerged as an alternative to alleviate the effort to label huge amount of data for data hungry applications (such as image/video indexing and retrieval, autonomous driving, etc.). The goal of active learning is to…

Motivated by recent progress in data assimilation, we develop an algorithm to dynamically learn the parameters of a chaotic system from partial observations. Under reasonable assumptions, we rigorously establish the convergence of this…

A Probabilistic Movement Primitive (ProMP) defines a distribution over trajectories with an associated feedback policy. ProMPs are typically initialized from human demonstrations and achieve task generalization through probabilistic…

Obtaining reliable feedback from the environment is a fundamental capability for intelligent agents to evaluate the correctness of their actions and to accumulate reusable knowledge. However, most existing approaches rely on predefined…

Active Learning (AL) has emerged as a powerful approach for minimizing labeling costs by selectively sampling the most informative data for neural network model development. Effective AL for large-scale vision-language models necessitates…

Most prior work on active learning of classifiers has focused on sequentially selecting one unlabeled example at a time to be labeled in order to reduce the overall labeling effort. In many scenarios, however, it is desirable to label an…

Ecological systems, as is often noted, are complex. Equally notable is the generalization that complex systems tend to be oscillatory, whether Huygens simple patterns of pendulum entrainment or the twisted chaotic orbits of Lorenz…

What are the functions of curiosity? What are the mechanisms of curiosity-driven learning? We approach these questions about the living using concepts and tools from machine learning and developmental robotics. We argue that…

Collective behavior is widespread across the animal kingdom. To date, however, the developmental and mechanistic foundations of collective behavior have not been formally established. What learning mechanisms drive the development of…

This paper introduces a new approach for continual planning and model learning in relational, non-stationary stochastic environments. Such capabilities are essential for the deployment of sequential decision-making systems in the uncertain…

Inverse optimal control can be used to characterize behavior in sequential decision-making tasks. Most existing work, however, is limited to fully observable or linear systems, or requires the action signals to be known. Here, we introduce…

The slowing of Moore's law and the increasing energy demands of machine learning present critical challenges for both the hardware and machine learning communities, and drive the development of novel computing paradigms. Of particular…

Habituation - a phenomenon in which a dynamical system exhibits a diminishing response to repeated stimulations that eventually recovers when the stimulus is withheld - is universally observed in living systems from animals to unicellular…

State-of-the-art machine learning models require access to significant amount of annotated data in order to achieve the desired level of performance. While unlabelled data can be largely available and even abundant, annotation process can…

Trained human pilots or operators still stand out through their efficient, robust, and versatile skills in guidance tasks such as driving agile vehicles in spatial environments or performing complex surgeries. This research studies how…

Active learning shows promise to decrease test bench time for model-based drivability calibration. This paper presents a new strategy for active output selection, which suits the needs of calibration tasks. The strategy is actively learning…

Traditional models of active learning assume a learner can directly manipulate or query a covariate $X$ in order to study its relationship with a response $Y$. However, if $X$ is a feature of a complex system, it may be possible only to…

Hardly any real self-propelling or actively driven object is perfect. Thus, undisturbed motion will generally not follow straight lines but rather circular trajectories. We here address self-propelled or actively driven objects that move in…

We propose an algorithm to actively estimate the parameters of a linear dynamical system. Given complete control over the system's input, our algorithm adaptively chooses the inputs to accelerate estimation. We show a finite time bound…