AI Offers New Insights into Human Thought Processes

In a groundbreaking study published in NeuroImage, Dr. Patrick Krauss and Dr. Achim Schilling of the Cognitive Computational Neuroscience Group at Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) used artificial intelligence to gain major insights into brain function. Their findings have the potential to transform our comprehension of human thought processes and emotions.

What happens next in a sentence? What will be seen next? How will this affect the environment or the body? Predicting future events keeps the human brain engaged at all levels of complexity and abstraction. Predictive coding is one of the brain's primary functions, allowing adaptive behavior and helping us navigate our surroundings.

Dr. Patrick Krauss and Dr. Achim Schilling from FAU's Cognitive Computational Neuroscience Group at the Chair of Computer Science 5 (Pattern Recognition) have not only reinforced this widely accepted concept in their latest study but also introduced new insights into how predictive coding operates in the brain.

Collaboration with the Epilepsy Center at Uniklinikum Erlangen

The two physicists and neuroscientists examined the spontaneous activity of the human brain using auto-encoders—an advanced form of artificial intelligence that detects patterns and connections within the vast, complex data produced by the brain, which would be undetectable with traditional methods.

This breakthrough was made possible through collaboration with researchers from the Epilepsy Center at Uniklinikum Erlangen, led by Prof. Dr. Med. Hajo Hamer. At the Center, epilepsy patients have electrodes implanted in their brains before undergoing surgical removal of epileptogenic foci.

Using this exceptionally rare and valuable data, the researchers made a groundbreaking discovery: spontaneous brain processes, known as Local Field Potential events (LFPs), provide critical insights into how the brain functions. Remarkably, these spontaneous impulses seem to play a significant role in how the brain interprets information, even when no external stimuli are present.

New Avenues for Research

In our study, we realized that our brains are constantly progressing through active states defined by these LFPs. It is as if our brains are constantly playing through various options for what might happen next, even if we are not doing or perceiving anything in particular and not receiving any external stimuli at that moment in time.

Dr. Patrick Krauss, Lecturer, Friedrich-Alexander-Universität Erlangen-Nürnberg

“We have also discovered that the form of these LFPs can determine the direction of information flux within the brain. This could give us important insights into how thoughts and feelings are processed in our minds,” added Dr. Achim Schilling.

These findings open new avenues for research and may lead to improved methods for diagnosing and treating brain diseases. These AI-based approaches can also be used in conjunction with standard EEG or MEG studies, which involve attaching electrodes to the surface of the skull to record brain activity.

Dr. Schilling added, “Knowledge of what our brains usually do while we are at rest can be put to good use for diagnostic purposes. If we can gain an ever better understanding of how our brains work and process information, that will allow us to develop more specific methods of diagnosis and treatment for neurological diseases. If, for example, the brain enters a state that does not correlate with the external stimuli, that may be an indication of pathological changes.”

Increased Reciprocity Between Technology and Brain Research

While AI is being utilized as a tool, the findings of the study by the two FAU researchers may also help further improve AI. The ultimate goal is to develop AI inspired by neurology that can make predictions even when no information is actively being processed.

“This may be particularly useful in AI systems incorporated into vehicles, for example, especially when bearing safety in mind,” explained Dr. Achim Schilling.

Dr. Patrick Krauss stated, “Even if there is not much traffic and the car is only driving straight ahead on the highway, it would be beneficial for the AI to be considering in the background which traffic incidents could occur to which it may potentially have to react.”

Dr. Patrick Krauss and Dr. Achim Schilling's study highlights the potential of the synergistic relationship between AI and brain research to enhance the understanding of cognitive processes and brain function, potentially leading to innovative approaches in medical diagnosis and therapy.

The growing integration of technology and brain study demonstrates the need for multidisciplinary methods in deciphering nature's complex processes. The FAU researchers' discoveries are bringing them closer to a deeper understanding of the human brain, one of the most complex systems on the planet.

Journal Reference:

Schilling, A., et al. (2024) Deep learning-based decoding of single local field potential events. NeuroImage. doi.org/10.1016/j.neuroimage.2024.120696