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
- Rise of the Machines: Here’s how much robots and A.I. progressed in 2018 on December 14, 2018 at 9:45 pm
Maybe they think they’ll be spared when the rise of the machines eventually happens ... That could prove useful for everything from training autonomous cars to reducing the workload on game designers, ... […]
- Sea Machines Robotics Offers Remote Operation Systems for Fireboats on December 14, 2018 at 4:38 pm
Sea Machines recognizes these risks and urges marine firefighters to consider the benefits of adding autonomous-command, remote-control workboats to their fleets. The company’s SM300 and SM200 product... […]
- Autonomous Machines Power the Future at F2F Start-Up Competition on December 14, 2018 at 3:05 pm
The future of agriculture is autonomous, if the victors of Farmers Business Network’s Start-Up Competition at the 2018 Farmer2Farmer event are any indication. Autonomous machines operate independently ... […]
- NVIDIA's autonomous robot brain goes on sale for $1,099 on December 13, 2018 at 3:41 pm
NVIDIA announced on Wednesday that its Jetson AGX Xavier module, designed to be the brains of autonomous machines, is now available for purchase -- but only in batches of 1,000 or more, starting at $1 ... […]
- Postmates Serve autonomous on-demand delivery rover is made for cities on December 13, 2018 at 2:33 pm
The machine is designed for cities ... The company will initially deploy the autonomous delivery vehicle in Los Angeles, but anticipates an expansion into other big US cities over the next year. […]
via Google News and Bing News