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
- Assisted Intelligence vs. Augmented Intelligence and Autonomous Intelligenceon January 31, 2020 at 10:05 am
How can governments best do this to get the fullest advantage of AI? To answer that question, it’s helpful to first discuss the three models (assisted, augmented and autonomous) and four types ...
- Andrew Yang warns against ‘slaughterbots’ and urges global ban on autonomous weaponryon January 31, 2020 at 9:31 am
Ahead of the Democratic presidential primaries that begin Monday with the Iowa caucus, presidential candidate Andrew Yang called for a global ban on the use of autonomous weaponry. In a tweet Thursday ...
- Autonomous Military Vehicle Market Growing Rapidly In Defense Sector: Analysis By Key Players will reach CAGR of 15.85% in 2023on January 31, 2020 at 7:16 am
Autonomous Military Vehicle Industry 2020 Global Market research report is a professional and in-depth study on the market size, growth, share, trends, as well as industry analysis. "Autonomous ...
- Autonomous Vehicles Market 2020 Emerging Trends, Future Analysis and Forecast Outlook till 2025on January 31, 2020 at 4:09 am
An up-to-date research report has been disclosed by Adroit Market Research highlighting the title "Global Autonomous Vehicles Market Insights, Forecast to 2025" which provides an outlook for current ...
- Waymo's head of design explains the challenges of creating an autonomous robot 'driver'on January 30, 2020 at 12:31 pm
YooJung Ahn oversees the design of the Waymo "driver," a complicated combination of hardware, software, and user experiences.
via Google News and Bing News