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

Researchers Capture First Images of Oxyg…

Oxygen in cancer tumors is known to be a major factor that helps radiation therapy be successful. Hypoxia, or starvation of oxygen, in solid tumors is also thought to be...

A New Method of Artificial Intelligence …

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...

PatchAi Startup has Arrived in the Marke…

PatchAi - a startup that offers, thanks to Artificial Intelligence and Machine Learning, an empathic virtual assistant to patients participating in clinical trials - announced that it has closed two...

FDA Authorizes Marketing of First Cardia…

Today, the U.S. Food and Drug Administration authorized marketing of software to assist medical professionals in the acquisition of cardiac ultrasound, or echocardiography, images. The software, called Caption Guidance, is...

Digital Health App Medicus AI Earns CE C…

Medicus AI, the Vienna-based health tech company, has received a ​Class I Medical Device CE Mark for its mobile application. The CE certification mark confirms that Medicus AI conforms to...

Portable Lab You Plug into Your Phone ca…

Engineers with the University of Cincinnati have created a tiny portable lab that plugs into your phone, connecting it automatically to a doctor's office through a custom app UC developed...

Helping Patients with Binge Eating Disor…

Behavioral therapy assisted by a smartphone app, delivered via telemedicine by a health coach, was an effective treatment for several symptoms of binge eating disorders, according to a study conducted...

SCCE's 8th Annual ECEI - European Compli…

16 - 18 March 2019, Amsterdam, The Netherlands. The European Compliance & Ethics Institute is the place to discuss compliance challenges and strategies with your peers from healthcare and across industry...

InterSystems Releases Novel Coronavirus …

InterSystems is releasing global functionality for its TrakCare® unified healthcare information system to screen and support patients with 2019-nCoV, the novel coronavirus infection that originated in Wuhan in China.

Telehealth Interventions Associated with…

Telehealth interventions are associated with improved obstetric outcomes, according to a review published from physician-researchers at the George Washington University. The article, published in the journal Obstetrics and Gynecology, presents...

CompuGroup Medical to Acquire Certain Ce…

CompuGroup Medical SE (CGM) and Cerner Corporation (NASDAQ: CERN), a global health care technology company, have entered into an agreement regarding the acquisition by CompuGroup Medical of a part of...