Autonomous Machine Learning (AML) Section
Chair: Asim Roy
Website: www.lifeboat.com/ex/bios.asim.roy

Scope

Much of the justification for creating this SIG (now a Section) is derived from the report of a US National Science Foundation (NSF) workshop in July 2007 on “Future Challenges for the Science and Engineering of Learning.” Here is the summary of the “Open Questions in Both Biological and Machine Learning” from the workshop (http://www.cnl.salk.edu/Media/NSFWorkshopReport.v4.pdf).

“Biological learners have the ability to learn autonomously, in an ever changing and uncertain world. This property includes the ability to generate their own supervision, select the most informative training samples, produce their own loss function, and evaluate their own performance. More importantly, it appears that biological learners can effectively produce appropriate internal representations for composable percepts -- a kind of organizational scaffold - - as part of the learning process. By contrast, virtually all current approaches to machine learning typically require a human supervisor to design the learning architecture, select the training examples, design the form of the representation of the training examples, choose the learning algorithm, set the learning parameters, decide when to stop learning, and choose the way in which the performance of the learning algorithm is evaluated. This strong dependence on human supervision is greatly retarding the development and ubiquitous deployment autonomous artificial learning systems. Although we are beginning to understand some of the learning systems used by brains, many aspects of autonomous learning have not yet been identified.”

We believe INNS and the neural network community at large has a special obligation to step up to this challenge of creating autonomous learning systems that do not depend on human supervision. 

Objectives

The objectives of this Section are to:

  1. Promote research and development of autonomous machine learning systems
  2. Create a body of researchers focused on autonomous learning systems
  3. Facilitate collaboration among researchers on this new breed of learning algorithms
  4. Organize special sessions on autonomous machine learning at various conferences (IJCNN, WCCI and others)
  5. Organize special workshops at various conferences to get a deeper understanding of autonomous learning by biological systems; invite prominent researchers to these workshops
  6. Promote applications of autonomous machine learning systems in various application areas

We hope more INNS members will join the AML Section this year and be part of the worldwide effort to create widely deployable learning systems.

 

Membership

Membership will be open to all INNS members interested in Autonomous Machine Learning. 

Section Membership Application