An intrinsic value system for developing multiple invariant representations with incremental slowness learning

نویسندگان
چکیده

برای دانلود باید عضویت طلایی داشته باشید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

An intrinsic value system for developing multiple invariant representations with incremental slowness learning

Curiosity Driven Modular Incremental Slow Feature Analysis (CD-MISFA;) is a recently introduced model of intrinsically-motivated invariance learning. Artificial curiosity enables the orderly formation of multiple stable sensory representations to simplify the agent's complex sensory input. We discuss computational properties of the CD-MISFA model itself as well as neurophysiological analogs ful...

متن کامل

An Integrated System for Incremental Learning of Multiple Visual Categories

An amazing capability of the human visual system is the ability to learn an enormous repertoire of visual categories. This large amount of categories is acquired incrementally during our life and requires at least partially the direct interaction with a tutor. Inspired by child-like learning we propose an architecture for learning several visual categories in an incremental and interactive fash...

متن کامل

An Advisory System for Developing Data Representations

A knowledge-based interactive system for choosing abstract data structures and concrete represent.* tions for them is described. The system acts as an "expert" on data structures and is to be consulted by programmers during the design stage of their work A specification method is described which assumes a restricted vocabulary of data structure terminology common to the user and the system. The...

متن کامل

Learning with Multiple Representations

1. Abstract This paper reports a study which examined support the translation between multiple representations in simulation-based learning. We compared three versions of the same simulation-based learning environment: a learning environment with separated representations (control condition), a learning environment with dynamically linked representations, and a learning environment with integra...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Frontiers in Neurorobotics

سال: 2013

ISSN: 1662-5218

DOI: 10.3389/fnbot.2013.00009