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

Human learning and intelligence work differently from the supervised patternrecognition approach adopted in most deep learning architectures. Humans seemto learn rich representations by exploration and imitation, build causal modelsof the world, and use both to flexibly solve new tasks. We suggest a simple buteffective unsupervised model which develops such characteristics. The agentlearns to represent the dynamical physical properties of its environment byintrinsically motivated exploration, and performs inference on thisrepresentation to reach goals. For this, a set of self-organizing maps whichrepresent state-action pairs is combined with a causal model for sequenceprediction. The proposed system is evaluated in the cartpole environment. Afteran initial phase of playful exploration, the agent can execute kinematicsimulations of the environment's future, and use those for action planning. Wedemonstrate its performance on a set of several related, but different one-shotimitation tasks, which the agent flexibly solves in an active inference style.

Learning intuitive physics and one-shot imitation using state-action-prediction self-organizing maps