Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain
the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in
Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles
and JavaScript.
Humans infer much of the intentions of others by just looking at their gaze. Similarly, we want to understand how machine learning systems solve a problem. New tools are developed to find out what strategies a learning machine is using, such as what it is paying attention to when classifying images.
Research on reinforcement learning in artificial agents focuses on a single complex problem within a static environment. In biological agents, research focuses on simple learning problems embedded in flexible, dynamic environments. The authors review the literature on these topics and suggest areas of synergy between them.
A bibliometric analysis of the past and present of AI research suggests a consolidation of research influence. This may present challenges for the exchange of ideas between AI and the social sciences.
A survey of 300 fictional and non-fictional works featuring artificial intelligence reveals that imaginings of intelligent machines may be grouped in four categories, each comprising a hope and a parallel fear. These perceptions are decoupled from what is realistically possible with current technology, yet influence scientific goals, public understanding and regulation of AI.
Arguably one of the most promising as well as critical applications of deep learning is in supporting medical sciences and decision making. It is time to develop methods for systematically quantifying uncertainty underlying deep learning processes, which would lead to increased confidence in practical applicability of these approaches.
To be useful in a variety of daily tasks, robots must be able to interact physically with humans and infer how to be most helpful. A new theory for interactive robot control allows a robot to learn when to assist or challenge a human during reaching movements.
Deep neural networks have become very successful at certain machine learning tasks partly due to the widely adopted method of training called backpropagation. An alternative way to optimize neural networks is by using evolutionary algorithms, which, fuelled by the increase in computing power, offers a new range of capabilities and modes of learning.
A new vision for robot engineering, building on advances in computational materials techniques, additive and subtractive manufacturing as well as evolutionary computing, describes how to design a range of specialized robots uniquely suited to specific tasks and environmental conditions.