Autonomous machines edge towards greater independence

June 08, 2017

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 autonomous systems 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 performance. 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 feedback loop 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 network 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 central processing unit 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.
-end-
Reference:

Agustín M. Bilen and Pablo Kaluza (2017), Autonomous learning by simple dynamical systems with a discrete-time formulation, Eur. Phys. J. B 90:94, DOI 10.1140/epjb/e2017-70714-7

Springer

Related Autonomy Articles from Brightsurf:

Improving health care autonomy for young adults with autism
Independence has always been a driving force in Nancy Cheak-Zamora's life.

Muscle aging: Stronger for longer
With life expectancy increasing, age-related diseases are also on the rise, including sarcopenia, the loss of muscle mass due to aging.

AI management can benefit the growing online workforce
USC research shows that gig workers and others in the new crowdwork economy need more autonomy and clear purpose in online tasks to perform at a high level -- advantages that AI assistance offers.

Is your job killing you? Stress, lack of autonomy, ability can lead to depression, death
A new study from the Indiana University Kelley School of Business finds that our mental health and mortality have a strong correlation with the amount of autonomy we have at our job, our workload and job demands, and our cognitive ability to deal with those demands.

New Chicago Booth research suggests patients prefer expert guidance for medical decisions
New research from University of Chicago Booth School of Business suggests that in times of uncertainty, people want expert guidance when making choices about their medical care.

'Terrible twos' not inevitable: With engaged parenting, happy babies can become happy toddlers
Parents should not feel pressured to make their young children undertake structured learning or achieve specific tasks, particularly during lockdown.

More autonomy at work reduces the risk of low back pain
A team of psychologists from Technische Universit├Ąt Dresden, in cooperation with experts from health sciences and the Federal Institute for Occupational Safety and Health, has carried out a meta-analysis to identify psychosocial work factors that pose a risk for the development of chronic low back pain (CLBP).

Hastings Center Report, November-December 2019
GoFundMe urged to halt campaigns for unproven medical treatments; the case for new laws to stem the doctor burnout crisis; why sugar taxes don't undermine liberty, and more.

Scientists help soldiers figure out what robots know
An Army-led research team developed new algorithms and filled in knowledge gaps about how robots contribute to teams and what robots know about their environment and teammates.

Tension around autonomy increases family conflict at end of life
Conflict within families can be stressful and confusing, and it can lead to feelings of sadness.

Read More: Autonomy News and Autonomy Current Events
Brightsurf.com is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to Amazon.com.