NDLI: Autonomous learning of abstractions using Curiosity-Driven Modular Incremental Slow Feature Analysis

Content Provider	IEEE Xplore Digital Library
Author	Kompella, V.R. Luciw, M. Stollenga, M. Pape, L. Schmidhuber, J.
Copyright Year	2012
Description	Author affiliation: IDSIA, Galleria 2, Manno-Lugano 6928, Switzerland (Kompella, V.R.; Luciw, M.; Stollenga, M.; Pape, L.; Schmidhuber, J.)
Abstract	To autonomously learn behaviors in complex environments, vision-based agents need to develop useful sensory abstractions from high-dimensional video. We propose a modular, curiosity-driven learning system that autonomously learns multiple abstract representations. The policy to build the library of abstractions is adapted through reinforcement learning, and the corresponding abstractions are learned through incremental slow-feature analysis (IncSFA). IncSFA learns each abstraction based on how the inputs change over time, directly from unprocessed visual data. Modularity is induced via a gating system, which also prevents abstraction duplication. The system is driven by a curiosity signal that is based on the learnability of the inputs by the current adaptive module. After the learning completes, the result is multiple slow-feature modules serving as distinct behavior-specific abstractions. Experiments with a simulated iCub humanoid robot show how the proposed method effectively learns a set of abstractions from raw un-preprocessed video, to our knowledge the first curious learning agent to demonstrate this ability.
Starting Page	1
Ending Page	8
File Size	2066918
Page Count	8
File Format	PDF
ISBN	9781467349642
e-ISBN	9781467349659
e-ISBN	9781467349635
DOI	10.1109/DevLrn.2012.6400829
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2012-11-07
Publisher Place	USA
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Training Estimation error Adaptation models Switches Libraries Encoding Vectors
Content Type	Text
Resource Type	Article

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

1Autonomous Learning of Abstractions using Curiosity-Driven Modular Incremental Slow Feature Analysis

Optimal Curiosity-Driven Modular Incremental Slow Feature Analysis.

Dynamic Scene Classification: Learning Motion Descriptors with Slow Features Analysis

Speaker adaptation of neural network acoustic models using i-vectors

Feature compensation using linear combination of speaker and environment dependent correction vectors

Learning skills from play: Artificial curiosity on a Katana robot arm

Artificial curiosity driven autonomous knowledge discovery based on learning by interaction

Curiosity-driven exploration in reinforcement learning

Incremental Compressive Pattern Classification

Autonomous learning of abstractions using Curiosity-Driven Modular Incremental Slow Feature Analysis

Similar Documents

1Autonomous Learning of Abstractions using Curiosity-Driven Modular Incremental Slow Feature Analysis

Optimal Curiosity-Driven Modular Incremental Slow Feature Analysis.

Dynamic Scene Classification: Learning Motion Descriptors with Slow Features Analysis

Speaker adaptation of neural network acoustic models using i-vectors

Feature compensation using linear combination of speaker and environment dependent correction vectors

Learning skills from play: Artificial curiosity on a Katana robot arm

Artificial curiosity driven autonomous knowledge discovery based on learning by interaction

Curiosity-driven exploration in reinforcement learning

Incremental Compressive Pattern Classification

Autonomous learning of abstractions using Curiosity-Driven Modular Incremental Slow Feature Analysis