Machines can learn by simply observing, without being told what to look for

by Roderich Gross Research & Innovation News September 15, 2016 We have developed a new machine learning method at the University of Sheffield called Turing Learning that allows machines to model natural or artificial systems. In Turing Learning, a machine optimizes models of a system under investigation. The machine observes the system, without being told what to look for. This overcomes the limitation of conventional machine learning methods that optimize models according to predefined similarity metrics, such as the sum of square error to measure the difference between the output of the models and that of the system. For complex systems, such as swarms, defining a useful metric can be challenging. Moreover, an unsuitable metric may not distinguish well between good and bad models, or even bias the learning process. This is the case, for example, for the swarm systems considered here – we prove that using the sum of square error metric one is unable to infer the behaviors correctly. Turing Learning takes inspiration from the work of pioneering computer scientist Alan Turing, who proposed a test which required a machine to behave indistinguishably from a human in some respect. In this test, an interrogator exchanges messages with two players in a different room: one human, the other a machine. The interrogator has to find out which of the two players is human. If they consistently fail to do so – meaning that they are no more successful than if they had chosen one player at random – the machine has passed the test and is considered to have human-level intelligence. Turing learning was successfully applied to infer swarm behaviors. We put a swarm of robots under surveillance and wanted to find out which rules caused their movements.To do so, we put a second swarm – made of learning robots – under surveillance as well. The movements of all the robots were recorded, and the motion data shown to interrogators. Unlike in the original Turing test, however, the interrogators in Turing Learning are not human but rather computer programs that learn by themselves. Their task is to distinguish between robots from either swarm. They are rewarded for correctly categorizing the motion data from the original swarm as genuine and those from the other swarm as counterfeit. The learning robots that succeed in fooling an interrogator – making it believe that their motion data were genuine – receive a reward. By doing so, Turing Learning can not only infer the behavioral rules of the swarm but also detect abnormalities in behavior. Turing Learning could prove useful whenever a behavior is not easily characterizable using metrics, making it suitable for a wide range of applications. For example, computer games, could gain in realism as virtual players could observe and assume characteristic traits of their human counterparts. They would not simply copy the observed behavior, but rather reveal what makes human players distinctive from the rest. Turing Learning could also be used to reveal the workings of some animal collectives, such as, schools of fish or colonies of bees. This could lead to a better understanding of what factors influence the behavior of these animals, and eventually inform policy for their protection. Reference: The study is published in the September issue of the journal Swarm Intelligence. If you liked this article, you may also want to read: Robots Podcast #197: Multi-agent systems and human-swarm interaction, with Magnus Egerstedt Bioinspired robotics #1: Swarm collectives, with Radhika Nagpal Evolving robot swarm behaviour suggests forgetting may be important to cultural evolution Surgical micro-robot swarms: Science fiction, or realistic prospect? See all the latest robotics news on Robohub, or sign up for our weekly newsletter. Roderich Gross received a Diploma degree in Computer Science from TU Dortmund University in 2001.. read more machine learning swarm learning swarm robotics Turing Learning Research & Innovation Business & Finance Health & Medicine Politics, Law & Society Arts & Entertainment Education & DIY Events Military & Defense Exploration & Mining Mapping & Surveillance Enviro. & Agriculture Aerial Automotive Industrial Automation Consumer & Household Space latest posts popular reported elsewhere Integrators are dead, long live the integrator by Frank Tobe Watch humanoid robot Atlas balance on one foot by Robohub Editors Breaking down robotaxi economics by Brad Templeton, Robocars.com Top 10 technologies in precision agriculture by Frank Tobe Robohub roundtable: Cybathlon and advancements in prosthetics by Kassie Perlongo Tune in: Economist holding Facebook Live Q&A about AI and the future of work by Robohub Editors The Drone Center’s Weekly Roundup: 9/12/16 by Center for the Study of the Drone at Bard College Robotiq launches DoF: A community for robotics professionals by Robotiq Inc. Telepresence robots help chronically ill kids maintain social, academic ties at school by University of California, Irvine HAPTIX program underway to create prosthetic hand system that moves and feels like a real hand by Open Source Robotics Foundation latest posts popular reported elsewhere HAPTIX program underway to create prosthetic hand system that moves and feels like a real handRobotiq launches DoF: A community for robotics professionalsHuman-robot disaster response team successfully deployed robots in earthquake damaged monumentsYesterday I looked through the eyes of a robotRobohub roundtable: Cybathlon and advancements in prostheticsThe evolution of assembly lines: A brief historyCase IH displays new cab-less concept tractorFarming with robotsHow do self-driving cars work?Cybathlon: A bionics competition for people with disabilities latest posts popular reported elsewhere Surgeons use robot to operate inside eye in world first The Head of CMU’s Robotics Lab Says Self-Driving Cars Are ‘Not Even Close’ Japan to develop 3-D maps for self-driving cars- Nikkei Asian Review No Sailors Needed: Robot Sailboats Scour the Oceans for Data Boris Sofman & Hanns Tappeiner: The Journey to Consumer Robotics | CMU RI Seminar Drive.ai uses deep learning to teach self-driving cars – and to give them a voice Baidu and Nvidia to Build Artificial Intelligence Platform for Self-Driving Cars How Tech Giants Are Devising Real Ethics for Artificial Intelligence Robot Tractor Draws Crowds on Debut at Iowa Farm Show 3D Print Your Own Breakfast Inside the Robot-Run Genetics Lab of Tomorrow (Just Watch Your Step) Interview: How to build a lionfish-killing robot Lowe’s robot wants to help you find the plumbing aisle Legions of nanorobots target cancerous tumours with precision Why the death of Moore’s Law could give birth to more human-like machines Teaching physics 101 to robots is harder than you think FAA expects 600,000 commercial drones within a year | NPR Cybathlon adds robots to olympics Willow Garage as PARC for robotics Are Robots Really Destined to Take Over Restaurant Kitchens? Software marketplace April 5, 2013 A dedicated jobs board for the global robotics community. Robohub Science Communication Internship - RobohubSenior Researcher in UAV Communications and Coordination - Lakeside Labs GmbHSenior Research Engineer - ConSol PartnersLead Mechanical Engineer – Robotics - Sealed Air Corporation - Intellibot RoboticsElectrical Engineering Manager – Robotics - Sealed Air Corporation - Intellibot Robotics