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

AI-Pathway Companion Prostate Cancer fro…

AI-Pathway Companion Prostate Cancer(2), a digital companion from Siemens Healthineers to support clinical decision-making, has recently received the CE mark for use in the clinical pathway of prostate cancer, the...

Philips Launches HealthSuite System of E…

Royal Philips (NYSE: PHG, AEX: PHIA), a global leader in health technology, today announced the HealthSuite System of Engagement, an integrated, modular set of standards-based capabilities that support the development...

AI may Help Spot Newborns at Risk for Mo…

An artificial intelligence (AI) device that has been fast-tracked for approval by the Food and Drug Administration may help identify newborns at risk for aggressive posterior retinopathy of prematurity (AP-ROP)...

Boehringer Ingelheim Launches Patient-Ce…

Boehringer Ingelheim and Carebox Healthcare Solutions announced the recent launch of MyStudyWindow, a digital platform empowering patients, families, caregivers, and doctors to learn about Boehringer Ingelheim's studies by offering information...

Best of Breed: Start with Data in Open P…

Better is attending this year's Digital Health Rewired conference and exhibition at Olympia London alongside Taunton and Somerset NHS Foundation Trust, which is using its open platform to develop an...

Highland Marketing is Sponsoring the Caf…

Highland Marketing will be returning to Digital Health Rewired this year, where it will be sponsoring the café that has been created with an expanded exhibition area. Digital Health Rewired launched...

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...

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...

Digital Heart Model will Help Predict Fu…

In recent times, researchers have increasing found that the power of computers and artificial intelligence is enabling more accurate diagnosis of a patient's current heart health and can provide an...