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

We introduce an approach to building a custom model from ready-madeself-supervised models via their associating instead of training andfine-tuning. We demonstrate it with an example of a humanoid robot looking atthe mirror and learning to detect the 3D pose of its own body from the image itperceives. To build our model, we first obtain features from the visual inputand the postures of the robot's body via models prepared before the robot'soperation. Then, we map their corresponding latent spaces by a sample-efficientrobot's self-exploration at the mirror. In this way, the robot builds thesolicited 3D pose detector, which quality is immediately perfect on theacquired samples instead of obtaining the quality gradually. The mapping, whichemploys associating the pairs of feature vectors, is then implemented in thesame way as the key-value mechanism of the famous transformer models. Finally,deploying our model for imitation to a simulated robot allows us to study, tuneup, and systematically evaluate its hyperparameters without the involvement ofthe human counterpart, advancing our previous research.

Robot at the Mirror: Learning to Imitate via Associating Self-supervised Models