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
UK trials unmanned systems to supply troops on the front line
on July 18, 2018 at 8:00 pm
Three of the other four systems selected by DSTL have also been produced by ... which has the backing of French aerospace and defence group Thales to develop an autonomous quadcopter. With DSTL having ... […]
AI Innovators Take Pledge Against Autonomous Killer Weapons
on July 18, 2018 at 3:15 pm
we the undersigned agree that the decision to take a human life should never be delegated to a machine," the pledge says. It goes on to say, "... we will neither participate in nor support the develop... […]
Elon Musk, AI innovators sign pledge to not develop lethal, autonomous weapons systems
on July 18, 2018 at 11:45 am
Anyone who's lived in fear of being murdered by some form of artificial intelligence in the same ballpark at Skynet can sleep a little easier now. Maybe. The 2018 International Joint Conference on Art... […]
Simbe Robotics Reveals RFID and Machine Learning Capabilities in the Latest Iteration of their Autonomous Inventory Robot – Tally
on July 18, 2018 at 9:19 am
SAN FRANCISCO, July 18, 2018 (GLOBE NEWSWIRE) -- Simbe Robotics today announced the integration of RFID and Machine Learning technology that enables Tally to capture in-store data on all RFID-tagged m... […]
AI companies pledge to not develop deadly autonomous weapons
on July 18, 2018 at 8:45 am
over 100 AI developers signed a pledge to not work on Lethal Autonomous Systems. (Jhoan M. Montolio/Navy) If killer robots are coming, many prominent artificial intelligence developers want no part in ... […]
via Google News and Bing News