A New Method of Artificial Intelligence Inspired by the Functioning of the Human Brain

Despite the immense progress in the field of AI in recent years, we are still very far from human intelligence. Indeed, if current AI techniques allow to train computer agents to perform certain tasks better than humans when they are trained specifically for them, the performance of these same agents is often very disappointing when they are put in conditions (even slightly) different from those experienced during training.

The human being is capable of adapting to new situations very effectively by using the skills he has acquired throughout his life. For example, a child who has learned to walk in a living room will quickly learn to walk in a garden as well. In such a context, learning to walk is associated with synaptic plasticity, which modifies the connections between neurons, while the rapid adaptation of walking skills learned in the living room to those needed to walk in the garden is associated with neuromodulation. Neuromodulation modifies the input-output properties of the neurons themselves via chemical neuromodulators.

Synaptic plasticity is the basis of all the latest advances in AI. However, no scientific work has so far proposed a way to introduce a neuromodulation mechanism into artificial neural networks. This result, described this week in the journal PLOS ONE, is the result of an extremely fruitful collaboration between neuroscientists and artificial intelligence researchers at the University of Liège developing intelligent algorithms: two PhD researchers, Nicolas Vecoven and Antoine Wehenkel, as well as two professors, Damien Ernst (specialist in artificial intelligence) and Guillaume Drion (neuroscientist).

These ULiège researchers have developed a completely original artificial neural network architecture, introducing an interaction between two sub-networks. The first one takes into account all the contextual information concerning the task to be solved and, on the basis of this information, neuromodule the second subnetwork in the manner of the brain's chemical neuromodulators. Thanks to neuromodulation, this second sub-network, which determines the actions to be performed by the intelligent agent, can therefore be adapted extremely quickly to the current task. This allows the agent to efficiently solve new tasks.

This innovative architecture has been successfully tested on classes of navigation problems for which adaptation is necessary. In particular, agents trained to move towards a target, while avoiding obstacles, were able to adapt to situations in which their movement was disrupted by extremely variable wind directions.

Prof. Damien Ernst: "The novelty of this research is that, for the first time, cognitive mechanisms identified in neuroscience are finding algorithmic applications in a multi-tasking context. This research opens perspectives in the exploitation in AI of neuromodulation, a key mechanism in the functioning of the human brain."

Nicolas Vecoven, Damien Ernst, Antoine Wehenkel, Guillaume Drion.
Introducing neuromodulation in deep neural networks to learn adaptive behaviours.
PLoS ONE 15(1), 2020. doi: 10.1371/journal.pone.0227922.

Most Popular Now

International Scientific Symposium DigiH…

13 November 2020, Pfarrkirchen, Germany DigiHealthDay @DIT-ECRI is going to be a daylong action-packed event targeting primarily academia - from established researchers, to young scientists and students. Following the theme "How...

Siemens Healthineers Introduces Teamplay…

Siemens Healthineers announces market introduction of the teamplay digital health platform. With the teamplay digital health platform Siemens Healthineers paves the way for healthcare providers' digital transformation - facilitating easy...

Oxford University Provide Evidence for C…

A team of medical research and bioethics experts at Oxford University are supporting several European governments to explore the feasibility of a coronavirus mobile app for instant contact tracing. If...

Portable AI Device Turns Coughing Sounds…

University of Massachusetts Amherst researchers have invented a portable surveillance device powered by machine learning - called FluSense - which can detect coughing and crowd size in real time, then...

Fighting Hand Tremors: First comes AI, t…

Robots hold promise for a large number of people with neurological movement disorders severely affecting the quality of their lives. Now researchers have tapped artificial intelligence techniques to build an...

Buddy Healthcare Launches COVID-19 Remot…

Buddy Healthcare wants to help hospitals and healthcare professionals in the battle against the COVID-19. BuddyCare virtual care platform can be used for not only symptom tracking, remote monitoring and...

Preventicus Appoints Ljubisav Matejevic …

Preventicus is proud to announce that the company continues to grow by bringing its unique, comprehensive care management programs for prevention of strokes and cardiovascular events to new international markets...

Philips Ramps Up Production of Critical …

Royal Philips (NYSE: PHG, AEX: PHIA), a global leader in health technology, announced that it is increasing the production of certain critical care products and solutions to help diagnose and...

DMEA Postponed and Rescheduled for 16 to…

16 - 18 June 2020, Berlin, Germany. The German Association of Healthcare IT Vendors (bvitg) and Messe Berlin have agreed to postpone this year's edition of DMEA - Connecting Digital Health...

COVID-19 should be Wake-Up Call for Robo…

Robots could perform some of the "dull, dirty and dangerous" jobs associated with combating the COVID-19 pandemic, but that would require many new capabilities not currently being funded or developed...