Brain Emotional Learning-Based AI Models | Research and Design 

We develop novel BEL/Brain Emotional Learning-based algorithms to address ever-increasing complex AI challenges, from Deepfake detection to computer vision, and from finance to mental health

Created with Sketch.
Limbic System and Amygdala

The limbic system is a group of brain regions, which includes amygdala, the hippocampus, thalamus, hypothalamus, basal ganglia, and cingulate gyrus. These structures are responsible for specific emotional learning and memory processing. 

Computational Models of Emotion

 Computational models of emotion are computer-based models that have been developed to simulate different aspects of the emotional system. The most famous emotion based model is called BELBIC.


BELBIC (Brain Emotional Learning Based Intelligent Controller) is not only a simple controller but also an adaptive controller with good performance. Different variations of BELBIC has been implemented in control, classification and prediction. 

Brain Emotional Learning

A revolutionary novel category of computational intelligence models. with unlimited power and customization possibilities

using the power of emotions in our brain, we can design a new set of models with faster, more reliable and more robust performance


Generally speaking, BELBIC is an error reduction system that can be incorporated to any system to reduce the system error. 

The emotional learning algorithm has three distinctiveproperties in comparison with other learning methodologies. Firstly, one can use very complicated definitions for emotional signal without increasing the computational complexity of algorithm or worrying about differentiability or renderability into recursive formulation problems. Secondly, the parameters can be adjusted in a simple intuitive way to obtain the best performance. Finally, the training is very fast and efficient. (TE Kalayci et al.)

belbic model belresearch

Join us! It will only take a minute

Latest News


Introducing BELDD (BEL-based Deepfake Detector)

Our team at BEL Research is working on the Deepfake Detection Challenge. It’s currently the biggest challenge in AI worldwide and the goal is to identify manipulated video content. It’s[…]

Read more
The New York University Tests ‘Radiology Assistant’ Powered by Artificial Intelligence

The New York University Tests ‘Radiology Assistant’ Powered by Artificial Intelligence

Combination of AI & Radiologists More Accurately Identified Breast Cancer There are several challenges for radiologists when screening mammography. For instance, some women develop breast cancer but are required to[…]

Read more

Physicists Train the Oscillatory Neural Network to Recognize Images

A new paper by physicists from Petrozavodsk State University proposes a novel method for oscillatory/spiking neural network (SNN) to recognize and categorize simple images. The advantage of oscillatory networks with[…]

Read more

Connect with us

Contact us

Please email us at email us at