Human brain is such a complex structure that we still don’t fully understand it even after centuries of research. However, new tools can improve our research process.
Scientists at UCL found that an artificial neural network (AI) is able to translate raw data from brain activity, which will not only help us understand our brain better, but will also improve technology and brain integration efforts.
Previously a lot of manual processing was needed to interpret brain activity, but AI can streamline this work. Image credit: Scientificanimations.com via Wikimedia (CC BY-SA 4.0)
An international research team designed this artificial neural network, which is basically a deep learning algorithm, to study brain activity in different species, including humans. It should speed up brain research, because it allows scientists to record larger and larger datasets from the brain. Furthermore, AI is able to interpret that data and basically read the neural code.
AI, which scientists named DeepInsight, was used to record neural signals from rats exploring an open arena. Researchers found that DeepInsight was able to precisely predict the position, head direction, and running speed of the animals. In other words, AI was reading brain signals and interpreting their meaning without the need for manual processing. DeepInsight was looking through the data that scientists don’t normally understand. Further testing showed that DeepInsight can predict human brain activity and its meaning as well.
Caswell Barry, senior author of the study, said: “Existing methods miss a lot of potential information in neural recordings because we can only decode the elements that we already understand. Our network is able to access much more of the neural code and in doing so teaches us to read some of those other elements.”
But what does this achievement actually mean? Well, scientists believe that AI could expand brain research possibilities. In the future algorithms like DeepInsight could be used to translate even more complex activities like reasoning and problem solving. In essence, AI streamlines the process of brain research. It automates the analysis of previously unprocessed data, which saves time and allows testing bigger, more advanced hypotheses quicker.
AI in this case is a very important research tool. It is quite interesting that the best way to study the organ of human intelligence is by using an artificial one. But AI is known for its ability to process huge pools of data very quickly and learn as it is going.