Autonomous machines edge towards greater independence

June 8, 2017
Credit: CC0 Public Domain

Cars that can drive autonomously have recently made headlines. In the near future, machines that can learn autonomously will become increasingly present in our lives. The secret to efficient learning for these machines is to define an iterative process to map out the evolution of how key aspects of these systems change over time.

In a study published in EPJ B, Agustín Bilen and Pablo Kaluza from Universidad Nacional de Cuyo, Mendoza, Argentina show that these smart systems can evolve autonomously to perform a specific and well-defined task over time. Applications range from nanotechnology to biological systems, such as biological signal transduction networks, genetic regulatory networks with adaptive responses, or genetic networks in which the expression level of certain genes in a network oscillates from one state to another.

These do not need an external tutor. Nor do they report to a central unit designed to modify what the system must learn depending on their . To increase their autonomy, the authors have built in delayed dynamics and a feedback loop with the system's performance. The delayed dynamics provide information on the history of the system, thus presenting the past relationships between its structure and performance. In turn, the offers information on the system's actual performance in terms of how close it is to the desired task.

The researchers first successfully applied their approach to a neural responsible for classifying several patterns, which yielded 66% robustness. These insights can be applied e.g. in analogue electronics, where a piece of hardware can learn a task autonomously without a or external control. The team also tested their solution on a system of phase oscillators, which are interesting because the populations of such oscillators display some remarkable synchronisation traits. In such cases, autonomous learning helps to avoid the inherent fluctuations of error normally found in such systems.

Explore further: New algorithm allows human being to communicate task to robot by performing it first in virtual reality

More information: Agustín M. Bilen et al, Autonomous learning by simple dynamical systems with a discrete-time formulation, The European Physical Journal B (2017). DOI: 10.1140/epjb/e2017-70714-7

Related Stories

The thermodynamics of learning

February 6, 2017

(Phys.org)—While investigating how efficiently the brain can learn new information, physicists have found that, at the neuronal level, learning efficiency is ultimately limited by the laws of thermodynamics—the same principles ...

Brain learning simulated via electronic replica memory

May 18, 2015

Scientists are attempting to mimic the memory and learning functions of neurons found in the human brain. To do so, they investigated the electronic equivalent of the synapse, the bridge, making it possible for neurons to ...

Recommended for you

Enhancing the quantum sensing capabilities of diamond

November 22, 2017

Researchers have discovered that dense ensembles of quantum spins can be created in diamond with high resolution using an electron microscopes, paving the way for enhanced sensors and resources for quantum technologies.

Study shows how to get sprayed metal coatings to stick

November 21, 2017

When bonding two pieces of metal, either the metals must melt a bit where they meet or some molten metal must be introduced between the pieces. A solid bond then forms when the metal solidifies again. But researchers at MIT ...

Imaging technique unlocks the secrets of 17th century artists

November 21, 2017

The secrets of 17th century artists can now be revealed, thanks to 21st century signal processing. Using modern high-speed scanners and the advanced signal processing techniques, researchers at the Georgia Institute of Technology ...

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.