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/

Zendy Plus

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

Zendy Tools

Zendy Open

Continual learning refers to the ability of humans and animals toincrementally learn over time in a given environment. Trying to simulate thislearning process in machines is a challenging task, also due to the inherentdifficulty in creating conditions for designing continuously evolving dynamicsthat are typical of the real-world. Many existing research works usuallyinvolve training and testing of virtual agents on datasets of static images orshort videos, considering sequences of distinct learning tasks. However, inorder to devise continual learning algorithms that operate in more realisticconditions, it is fundamental to gain access to rich, fully customizable andcontrolled experimental playgrounds. Focussing on the specific case of vision,we thus propose to leverage recent advances in 3D virtual environments in orderto approach the automatic generation of potentially life-long dynamic sceneswith photo-realistic appearance. Scenes are composed of objects that move alongvariable routes with different and fully customizable timings, and randomnesscan also be included in their evolution. A novel element of this paper is thatscenes are described in a parametric way, thus allowing the user to fullycontrol the visual complexity of the input stream the agent perceives. Thesegeneral principles are concretely implemented exploiting a recently published3D virtual environment. The user can generate scenes without the need of havingstrong skills in computer graphics, since all the generation facilities areexposed through a simple high-level Python interface. We publicly share theproposed generator.

Evaluating Continual Learning Algorithms by Generating 3D Virtual Environments