Mechanical intelligence for learning embodied sensor-object relationships.

ABSTRACT: Intelligence involves processing sensory experiences into representations useful for prediction. Understanding sensory experiences and building these contextual representations without prior knowledge of sensor models and environment is a challenging unsupervised learning problem. Current machine learning methods process new sensory data using prior knowledge defined by either domain knowledge or datasets. When datasets are not available, data acquisition is needed, though automating exploration in support of learning is still an unsolved problem. Here we develop a method that enables agents to efficiently collect data for learning a predictive sensor model-without requiring domain knowledge, human input, or previously existing data-using ergodicity to specify the data acquisition process.

SUBMITTER: Prabhakar A 

PROVIDER: S-EPMC9287329 | biostudies-literature | 2022 Jul

REPOSITORIES: biostudies-literature