English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

How can we train an assistive human-machine interface (e.g., anelectromyography-based limb prosthesis) to translate a user's raw commandsignals into the actions of a robot or computer when there is no prior mapping,we cannot ask the user for supervision in the form of action labels or rewardfeedback, and we do not have prior knowledge of the tasks the user is trying toaccomplish? The key idea in this paper is that, regardless of the task, when aninterface is more intuitive, the user's commands are less noisy. We formalizethis idea as a completely unsupervised objective for optimizing interfaces: themutual information between the user's command signals and the induced statetransitions in the environment. To evaluate whether this mutual informationscore can distinguish between effective and ineffective interfaces, we conductan observational study on 540K examples of users operating various keyboard andeye gaze interfaces for typing, controlling simulated robots, and playing videogames. The results show that our mutual information scores are predictive ofthe ground-truth task completion metrics in a variety of domains, with anaverage Spearman's rank correlation of 0.43. In addition to offline evaluationof existing interfaces, we use our unsupervised objective to learn an interfacefrom scratch: we randomly initialize the interface, have the user attempt toperform their desired tasks using the interface, measure the mutual informationscore, and update the interface to maximize mutual information throughreinforcement learning. We evaluate our method through a user study with 12participants who perform a 2D cursor control task using a perturbed mouse, andan experiment with one user playing the Lunar Lander game using hand gestures.The results show that we can learn an interface from scratch, without any usersupervision or prior knowledge of tasks, in under 30 minutes.

First Contact: Unsupervised Human-Machine Co-Adaptation via Mutual Information Maximization