Autonomous machines edge towards greater independence

June 8, 2017, Springer
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

Bringing a hidden superconducting state to light

February 16, 2018

A team of scientists has detected a hidden state of electronic order in a layered material containing lanthanum, barium, copper, and oxygen (LBCO). When cooled to a certain temperature and with certain concentrations of barium, ...

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.