• : I'mnovation
    Imnovation
      • Startups
      • esp
      • eng
    • Energy
    • Construction
    • Water
    • dt Created with Sketch. Digital Transformation
    • st Created with Sketch. Science & Technology
    • Society
    • SUSCRÍBETE A NUESTRA RSS
      • Startups
      • esp
      • eng
  • Home
  • Digital Transformation
  • Reinforcement Learning: when machines are self-taught
Previous Next
  • Reinforcement Learning: when machines are self-taught

    Can we really deal with robots on the same level? Learning methods for machines to operate autonomously are becoming increasingly sophisticated and nowadays they’re even capable of acquiring knowledge by themselves. Let's see what technology reinforcement learning is about.

Seniors will surely remember the Spanish group Radio Futura, and how Santiago Auserón and his bandmates proclaimed in 1980 that “Future is already here”. Indeed, it seems that that future is already our present time, and robotic technologies have a lot to say about it. Artificial intelligence has become a true revolution already playing a part in our everyday life, with applications ranging from computing to medicine, transportation or construction. In fact, you may be reading this article in a smartphone featuring some kind of facial, text or voice recognition system… artificial intelligence is already being settled in our daily life.

IBM’s Watson computer, winner of American quiz Jeopardy!, is nothing but another instance of this: a system using super-advanced learning techniques, currently being trained to help physicians make better decisions.

What appears as a certain trend is the one regarding the improvement of training algorithms so that computers are capable of learning by themselves in order to end up behaving like human beings. This is where the concept being discussed all over this article, technology reinforcement learning, appears: a set of algorithms capable of allowing robots to behave in an increasingly autonomous way. Let’s see…

Nanotexture infographic

Increasingly less-supervised Machine Learning systems

How do machines learn? The foundation of this technology lies in Supervised Learning, a kind of Machine Learning that relies on a set of examples whose answers are known by the machine beforehand. In other words, it attempts to make future predictions based on already familiar behaviour patterns which are stored in its data history.

The astonishing enhancement in computing power has allowed this learning process to be increasingly precise, facing a much more advanced artificial intelligence training concept: Deep Learning. Unlike the former, requires much less human direct supervision.

Deep Learning relies on a large simulated neural network and is capable of recognizing behavioural patterns in those stored data. The most known Deep learning examples in operation are Google’s Now, Apple’s Siri or Microsoft’s Cortana voice recognition systems.

Combining Deep and Reinforcement Learning may be the key to achieve true human behaviour on the part of machines.

Experience as a foundation for Technology Reinforcement Learning

Are machines capable of learning by themselves, then? The short answer is yes, the long answer forces us to comprehend what Reinforcement Learning is capable of when speaking of boosting automation processes of a robot or a computer.

Technology Reinforcement Learning is attempting to make any artificial intelligence-equipped system make decisions based on its own experience. In other words, when facing a certain situation, it should be capable of implementing the most adequate action by means of an interactive trial and error process, based on positive reinforcement every time it achieves a certain goal.

That’s why a machine is able to make decisions through Reinforcement Learning even if it does not store a priori any knowledge of the environment or the variables happening, and perform more advanced abstract issues successfully.

The implementation of this learning process already allows them to recognize faces, arrange DNA sequences, drive vehicles or make medical diagnostics. Currently, leading companies such as Google, Apple or IBM are investing on research in order to train robots to perform easy tasks through this technique.

The idea is to make robots capable of auto-programming themselves while learning on the fly, sharing this learning process with other robots in order to accelerate the whole procedure. The results obtained will feed some kind of central server, a large neural network featuring all the patterns learned, that will distribute them back to the robots to create a new learning cycle.

Technology Reinforcement Learning applied to driving

That is the dream of those who spend too many hours behind the wheel… a car capable of driving by itself. Behavioural psychology-inspired, Reinforcement Learning is the key to make autonomous driving a reality: a car being able to go into a roundabout on the right lane, enter a motorway safely, or act accordingly during a monumental traffic jam.

We have been reading news about autonomous driving for years now and it seems that its implementation is around the corner, but driver-less vehicles still hesitate before complex situations involving other human drivers, such as entering lanes. If we don’t want to undergo unnecessary risks or traffic jams, they will have to acquire more precise driving skills, such as proper performance when surrounded by many vehicles.

Mobileye, an Israeli enterprise specialized in providing safety systems for diverse motor companies, is currently working on a platform that will allow manufacturers to share data collected by their respective autonomous vehicles, thus learning from the whole environmental factors, be it human or self-driven cars. This software enhances processes and is much more efficient than a bunch of programmers trying to decode all those decisions.

Collaboration as a working methodology between robots and humans

As for many professional fields, this is not the time to replace people by machines, but to work and improve together instead.

 

A Canadian start-up, Kindred AI, is teaching machines to perform complex tasks with the help of human “pilots” who assist them by means of Virtual Reality. Robots attempt to perform a task, such as grabbing an object, and achieve the desired result through Machine Learning. But when none of their algorithms provides a solution, the robot asks for human assistance. At this stage, a person utilizes virtual reality hardware to visualize the challenge and assume control of the action temporarily. Thanks to Reinforcement Learning, the robot learns from what the human assistant is doing and accumulates that experience for further occasions.

 

Even if the arrival of the future was already announced to us in 1980, its fast pace is clearly unstoppable nowadays. Machines will be our allies in a future that is closer by the day. However, drawing the line regarding how far we want them to go will depend on us eventually.

 

Fuente: MIT Technology Review, Advanced Tech, Fernando Sancho Caparrini, Clever Data

  • Artificial intelligence
  • Machine Learning
  • Reinforcement Learning

Share on social media

{{CommentsCount}} Comments

Currently no one has commented on the news.
Be the first to leave a comment.

{{firstLevelComment.Name}}

{{firstLevelComment.DaysAgo}} days ago

{{firstLevelComment.Text}}

Answer

{{secondLevelComment.Name}}

{{secondLevelComment.DaysAgo}} days ago

{{secondLevelComment.Text}}

Write your comment

All fields are mandatory.

Name

Email address

Comments

250 max char.

Accept the information on data protection

You must accept the information on data protection

{{btnSendCommentText}}

Thank you for your comment

Information on data protection

In compliance with Regulation (EU) 2016/679 on Data Protection and with other Data Protection regulations in force, you are hereby informed that your personal data shall be processed by Acciona, S.A. (hereinafter “ACCIONA”), whose identification data are as follows: Tax ID No. (NIF): A08001851, Address: Avenida de Europa, 18, Parque Empresarial de la Moraleja, 28108 in Alcobendas, Madrid, Tel. No.: +34 91 663 28 50, email: protecciondedatos@acciona.com, in order to address and manage your queries, requests, claims and suggestions, as well as to electronically send information regarding our products and services through the contact email address.

The consent given by users when they contact us comprises the legal grounds for processing the data.

The data shall be stored as long as the relationship is maintained and the elimination thereof is not requested, and in any case, never for more than twelve months.

In the event your request is not addressed to ACCIONA but to an entity belonging to the Acciona Group, such entity shall transmit the data to the Group company that can most efficiently address your request for information or a service. Accordingly, when these data are transferred such transfer may be international due to the fact that these companies are located in countries outside the European Union, in order to address the communication needs among the individuals that comprise the Group at the global level. (You can consult a list of Group companies at www.acciona.com/shareholders-investors/financial-information/annual-accounts/. By accepting the privacy terms, you consent to your data being transferred internationally in order for your request to be properly processed. Other data transfers are not anticipated, except where required by law.

The interested party can exercise their rights of portability and to access, correct, eliminate, restrict and oppose the processing of their data before Acciona, S.A. by addressing ACCIONA in writing at the Department of Data Protection located at Avenida de Europa, 18, 28108, in Alcobendas, Madrid or by sending an email to the following address: protecciondedatos@acciona.com. In either case, the interested party must enclose or attach a copy of their National ID (DNI) or other ID. Furthermore, at any time the interested party may withdraw the granted consent by contacting the aforementioned address and file a claim before the Supervisory Authority (the Spanish Data Protection Agency www.aepd.es).

You can find more information in our Privacy Policy on our website.

Subscribe to our newsletter

... and stay informed with the latest news on innovation.

Send me the newsletter
{{ btnSendText }}

Wrong email format

Accept the information on data protection

You must accept the information on data protection

YOU'RE JUST ONE STEP AWAY!

Please, confirm your subscription on the email we have sent you and your registration will be completed.

YOU ARE ALREADY SUBSCRIBED TO THE NEWSLETTER!

If you've missed our content, try checking your junk mailbox and add us to your address book so you can enjoy them without any problem.

Information on data protection

In compliance with Regulation (EU) 2016/679 on Data Protection and with other Data Protection regulations in force, you are hereby informed that your personal data shall be processed by Acciona, S.A. (hereinafter “ACCIONA”), whose identification data are as follows: Tax ID No. (NIF): A08001851; Address: Avenida de Europa, 18, Parque Empresarial La Moraleja, 28108 in Alcobendas, Madrid; Tel. No.: +34 91 663 28 50; email: protecciondedatos@acciona.com. Your data shall be processed in order to send you information, through the subscription to our Newsletter through electronic means, regarding our latest technological innovation of ACCIONA´s initiative "I’MNOVATION #Hub", which aims to bring the general public main news, advances and curiosities of the innovation technology of all the companies that make up the ACCIONA Group.

 

The consent given by the data subject by indicating that they have read and accept this data protection information comprises the lawfulness of processing. The data provide is your email address. If you fails to provide the required data, the subscription Request cannot be satisfied. We may also process your satisfaction or preferences, if you voluntarily respond to surveys. Data shall be stored until the elimination is requested.

In order to carry out our purpose, we may give access to your data to service providers (such as technology service providers) who assist us in fulfilling this purpose. Some of its service providers, may be located outside of the European Economic Area in territories that do not offer a level of data protection that is comparable to that of the European Union. In such cases, we transfer User data with appropriate safeguards and always ensuring the security of the same.

 

The data subject can exercise their rights of portability and to access, correct, eliminate, restrict and oppose the processing of their data to Acciona, S.A. by writing the Department of Data Protection located at Avenida de Europa, 18, 28108, Parque Empresarial La Moraleja, in Alcobendas, Madrid or by sending an email to the following address: protecciondedatos@acciona.com. If we consider it necessary in order to be able to identify you, we may ask you for a copy of an identity document. Furthermore, at any time the data subject may withdraw the granted consent by contacting the aforementioned address and file a claim to the Supervisory Authority (Agencia Española de Protección de Datos www.aepd.es). You can also unsubscribe from the Newsletter communication.

 

For any further information you can visit the Privacy Police on the website https://www.acciona.com/privacy-policy/.

More about Digital Transformation

  • Digital Transformation

    WiFi everywhere with Google Loon

    Helium balloons are carrying WiFi connectivity to developing regions lacking network infrastructure

  • Digital Transformation

    The gentle arm of static electricity

    Robots now use electrostatic attraction to manipulate the more fragile goods on assembly lines

  • Digital Transformation

    Lifesaving app for smartphones

    An earthquake-detecting app sends alerts to people near the epicenter, giving them vital seconds to seek shelter

Featured topics

Read the most discussed articles

  • Artificial intelligence
  • Robots
  • Digital transformation
  • Technology
  • robotics
  • big data
  • Cities
  • Society
  • Mobiles
  • Virtual reality
  • Renewable energies
  • Internet

Categories

  • Energy
  • Construction
  • Water
  • Digital Transformation
  • Science & Technology
  • Society

Featured topics

  • Innovation
  • Renewable energies
  • Sustainability
  • Technology
  • Water
  • Robots

Innovation is a change that introduces new features. The concept is generally used in the sense of inventions, new ideas, devices, methods and processes, and the application of improved solutions meeting fresh economic or societal requirements. Strictly speaking, however, ideas can only be termed “innovations” once they have imposed themselves as successful new products, services or procedures.

About us
Subscribe to our RSS
Imnovation
Acciona

An ACCIONA innovation initiative

  • Privacy policy
  • Cookies policy
  • Legal notice
  • Site map
  • Contact
  • ACCIONA's websites