Neuronal networks simulating the brain | EBV Elektronik

Display portlet menu

Neuronal networks simulating the brain | EBV Elektronik

Display portlet menu

Neuronal networks simulating the brain

Artificial neuronal networks are playing a big role

Machines are being made more intelligent based on a variety of data analysis methods. The focus of these efforts is shifting increasingly from mere performance capability towards creating the kind of flexibility that the human brain achieves. Artificial neuronal networks are playing a big role.

All forms of Artificial Intelligence are not the same – there are different approaches to how the systems map their knowledge. A distinction is made primarily between two methods: neuronal networks and symbolic AI.

Knowledge represented by symbols

Conventional AI is mainly about logical analysis and planning of tasks. Symbolic, or rule-based, AI is the original method developed back in the 1950s. It attempts to simulate human intelligence by processing abstract symbols and with the aid of formal logic. This means that facts, events or actions are represented by concrete and unambiguous symbols. Based on these symbols, mathematical operations can be defined, such as the programming paradigm “if X, then Y, otherwise Z”. The knowledge – that is to say, the sum of all symbols – is stored in large databases against which the inputs are cross-checked. The databases must be “fed” in advance by humans. Classic applications of -symbolic AI include, for example, text processing and voice recognition. Probably the most famous example of -symbolic AI is DeepBlue, IBM’s chess computer which beat then world champion Garry Kasparov using symbolic AI in 1997.

As computer performance increases steadily, symbolic AI is able to solve ever more complex problems. It works on the basis of fixed rules, however. For a machine to operate beyond tightly constrained bounds, it needs much more flexible AI capable of handling uncertainty and processing new experiences.

Advancing knowledge about neurons autonomously

That flexibility is offered by artificial neuronal networks, which are currently the focus of research activity. They simulate the functionality of the human brain. Like in nature, artificial neuronal networks are made up of nodes, known as neurons, or also units. They receive information from their environment or from other neurons and relay it in modified form to other units or back to the environment (as output). There are three different kinds of unit:

Input units receive various kinds of information from the outside world. This may be measurement data or image information, for example. The data, such as a photo of an animal, is analysed across multiple layers by hidden units. At the end of the process, output units present the result to the outside world: “The photo shows a dog.” The analysis is based on the edge by which the individual neurons are interconnected. The strength of the connection between two neurons is expressed by a weight. The greater the weight, the more one unit influences another. Thus the knowledge of a neuronal network is stored in its weights. Learning normally occurs by a change in weight; how and when a weight changes is defined in learning rules. So before a neuronal network can be used in -practice, it must first be taught those learning rules. Then neuronal networks are able to apply their learning algorithm to learn independently and grow autonomously. That is what makes neuronal AI a highly dynamic, adaptable system capable of mastering challenges at which symbolic AI fails.

Cognitive processes as the basis of a new AI

Another new form of Artificial Intelligence has been developed by computer scientists at the University of -Tübingen: their “Brain Control” computer program simulates a 2D world and virtual figures – or agents – that act, cooperate and learn autonomously within it. The aim of the simulation is to translate state-of-the-art cognitive science theories into a model and research new variants of AI. Brain Control has not made use of neuronal networks to date, but nor does it adhere to the conventional AI paradigm. The core theoretical idea underlying the program originates from a cognitive psychology theory, according to which cognitive processes are essentially predictable, and based on so-called events. According to the theory, events – such as a movement to grip a pen, and sequences of events such as packing up at the end of the working day – form the building blocks of cognition, by which interactions, and sequences of interactions, with the world are selected and controlled in a goal-oriented way. This hypothesis is mirrored by Brain Control: the figures plan and decide by simulating events and their sequencing, and are thus able to carry out quite complex sequences of actions. In this way, the virtual figures can even act collaboratively. First, one figure places another figure on a platform so that the second figure can clear the way, then both of them are able to advance. The modelling of cognitive systems such as in Brain Control is still an ambitious undertaking. But its aim is to deliver improved AI over the long term.

 

****

This article is also available in German language. Click here for the German version.

 

Neuronal networks simulating the brain | EBV Elektronik

Display portlet menu

Neuronal networks simulating the brain | EBV Elektronik

Display portlet menu
Related Articles
The brain functions like a machine, or so according to the theory of Marvin Minsky, one of the most important pioneers of artificial intelligence.
KI-Pionier Minsky: Vorläufig tot?
March 4, 2019
Das Gehirn funktioniert wie eine Maschine, so die ­These von einem der wichtigsten Pioniere der ­Künstlichen Intelligenz. Also kann man es nach­bauen – und sich durch ein Back-up des Bewusstseins auf einem Rechner unsterblich machen.
Could our entire life simply be a computer simulation
AI-pioneer Minsky: Temporarily dead?
March 4, 2019
The brain functions like a machine, or so according to the theory of Marvin Minsky, one of the most important pioneers of artificial intelligence. In other words, it can be recreated – made immortal by backing up its consciousness onto a computer.
Mit verschiedenen Ansätzen der Datenauswertung sollen Maschinen intelligent werden.
Neuronale netze simulieren das gehirn
February 27, 2019
Mit verschiedenen Ansätzen der Datenauswertung sollen Maschinen intelligent werden. Im ­Fokus steht dabei nicht nur die Leistungsfähigkeit, ­sondern immer mehr auch eine Flexibilität, wie sie das menschliche Gehirn bietet.
Kognitive Computerassistenten helfen Medizinern bei Diagnose- und Therapieentscheidungen.
Ist KI besser als der arzt?
February 27, 2019
Kognitive Computerassistenten helfen Medizinern bei Diagnose- und Therapieentscheidungen. ­Sie sind deutlich schneller bei der Auswertung von medizinischen Informationen und erreichen ­mindestens die gleiche Präzision.
Cognitive computer assistants are helping clinicians to make diagnostic and therapeutic ­decisions
AI better than the doctor?
February 27, 2019
Cognitive computer assistants are helping clinicians to make diagnostic and therapeutic ­decisions. They evaluate medical­ data much faster, while ­delivering at least the same level of precision.
Artificial Intelligence has enormous potential for improving our lives
AI Smarter than humans?
February 25, 2019
What began in the 1950s with a conference has grown into a ­key technology. It is already influencing our lives today, and as the intelligence of machines increases in the future that influence is bound to spread much more.
KI ist eine Schlüsseltechnologie, die sich in den kommenden Jahren nicht nur maßgeblich auf unser tägliches Leben, sondern auch auf die Wettbewerbsfähigkeit der gesamten Wirtschaft auswirkt.
Ist KI schlauer als der Mensch?
February 27, 2017
Was in den 1950ern mit einer Konferenz der KI-Pioniere John McCarthy und Marvin Minsky begann, ist zu einer Schlüsseltechnologie ­geworden.­ Sie beeinflusst schon heute­ ­unser Leben – und wird es mit steigender Intelligenz der Maschinen in Zu

Neuronal networks simulating the brain | EBV Elektronik

Display portlet menu
Related Events
Webinar - Ultra96 Technical Training Courses
Date: July 7, 2019
Location: Online, On Demand
Tech Trends Turkey 01/2020
Date: January 14, 2020
Location: Tukey, tbd.
Journée Technique Intelligence Artificielle
Date: February 11, 2020
Location: France, Vénissieux; EBV Elektronik; 33 rue du Docteur Georges Lévy; 69200 Vénissieux
Journée Technique Intelligence Artificielle
Date: January 14, 2020
Location: France, Toulouse; B612; 3 rue Tarfaya; 31400 Toulouse
Journée Technique Intelligence Artificielle
Date: January 30, 2020
Location: France, Rennes, La fabrique – 20/22 avenue Jules Maniez – 35000 Rennes
AI & ML workshops Italy
Date: January 21, 2020
Location: Italy; Milano, Padova, Bologna