Physicists are providing a greater level of autonomy for self-taught systems by combining how they respond to their learning as they evolve
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.
The Latest on: Autonomous machines
- Defining Autonomous Machine Vision on October 8, 2018 at 6:48 am
“You never change things by fighting the existing reality. To change something, build a new model that makes the existing model obsolete.” These are the words of Buckminster Fuller, an architect, engi... […]
- Tracy Tynan Joins CIT as Director of Virginia Center for Unmanned Systems on October 8, 2018 at 6:42 am
For more information about the Autonomous Systems Center of Excellence, please visit https://www.vus.virginia.gov/. About the Center for Innovative Technology (CIT) […]
- Autonomous systems to play key role in NATO logistics drills on October 7, 2018 at 5:10 pm
WASHINGTON — As the U.S. military begins to tackle the challenges posed by great power competition and 21st century combat, expeditionary logistics is an area receiving extra attention to ensure troop... […]
- Gaurav Kumar Singh, Machine Learning and Deep Learning Researcher – Autonomous Vehicles of Ford Motor Company on October 5, 2018 at 9:30 am
Gaurav Kumar Singh is a Machine and Deep Learning Researcher at the Robotics and AI department at Ford Motor Company, located in Dearborn, Michigan. Gaurav Kumar Singh, Machine Learning and Deep Learn... […]
- Cadillac beats out Tesla for best semi-autonomous driving system, according to Consumer Reports (GM, TSLA) on October 4, 2018 at 8:04 am
Consumer Reports tested four semi-autonomous driver assistance systems and rated Cadillac's Super Cruise as the best. The publication ranked Tesla's Autopilot second, Nissan's ProPilot Assist third, a... […]
via Google News and Bing News