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
IEEE Advocates for Ethics in AI and Autonomous Systems Design at WSIS Forum
on April 19, 2018 at 4:05 am
IEEE joined global leaders at the World Summit on the Information Society (WSIS) Forum, held 19 to 23 March in Geneva. The annual event, organized by the United Nations and hosted by the International Telecommunications Union (ITU), brought together more ... […]
Baidu Unveils Apollo 2.5, the Newest Upgrade to its Autonomous Driving Open Platform
on April 19, 2018 at 2:37 am
By creating this lab, we aim to set a new standard for research in cybersecurity for autonomous vehicles.” The lab will conduct research into automotive cybersecurity technologies, trends and solutions for in-vehicle systems, car-to-car communications ... […]
WATCH: Israel at 70 - Israeli scientists and the future of autonomous cars
on April 18, 2018 at 11:47 pm
a leader in autonomous driving. Prof. Shalev-Shwartz has authored two books and over 80 research papers, focusing on machine learning, online prediction, optimization techniques and practical algorithms. The Israel 70+ project is comprised of 12 short ... […]
VW promises cars with autonomous parking tech in 2020
on April 18, 2018 at 10:28 am
The VW Group is already planning to equip its future cars with the necessary hardware, which will also be usable on the street as part of autonomous driving systems. "Autonomous parking can make an important contribution to creating convenient, stress-free ... […]
DHL Gets Logical – And Logistical – About Machine Learning
on April 18, 2018 at 9:09 am
At DHL, there are a broad array of projects big and small underway that are using AI, machine learning and deep learning to help the company become more proactive, predictive and autonomous, and to change its services from standardized to more personal. […]
via Google News and Bing News