An artificial neural network (AI) designed by researchers at University College London, the Kavli Institute for Systems Neuroscience in Trondheim, and the Max Planck Institute for Human Cognitive and Brain Sciences Leipzig is able to translate raw neural data, paving the way for new discoveries and a closer integration between technology and the brain.
“Neuroscientists have been able to record larger and larger datasets from the brain but understanding the information contained in that data – reading the neural code – is still a hard problem. In most cases we don’t know what messages are being transmitted”, explained lead researcher, Markus Frey (Kavli Institute for Systems Neuroscience).
“We wanted to develop an automatic method to analyse raw neural data of many different types, circumventing the need to manually decipher them.”
The study published today in eLife and funded by the Wellcome Trust and the European Research Council shows that a convolutional neural network, a specific type of deep learning algorithm, is able to decode many different behaviours and stimuli from a wide variety of brain regions in different species, including humans.
They tested the network, called DeepInsight, on neural signals from rats exploring an open arena and found it was able to precisely predict the position, head direction, and running speed of the animals. Even without manual processing, the results were more accurate than those obtained with conventional analyses.
“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”, said senior author, Prof. Caswell Barry (UCL Cell & Developmental Biology).
“We are able to decode neural data more accurately than before but the real advance is that the network is not constrained by existing knowledge.”
The team found that their model was able to identify new aspects of the neural code, which they show by detecting a previously unrecognized representation of head direction, encoded by interneurons in hippocampal subfield CA1, a region that is among the first to show functional defects in Alzheimer patients.
Moreover, they show that the same network is able to predict behaviours from different types of recording across brain areas and can also be used to infer hand movements in human participants.”This approach could allow us in the future to predict more accurately higher-level cognitive processes in humans, such as reasoning and problem solving”, Christian Doeller (Kavli Institute for Systems Neuroscience and Max Planck Institute for Human Cognitive and Brain Sciences) adds.
“Our framework enables researchers to get a rapid automated analysis of their unprocessed neural data, saving time which can be spent on only the most promising hypotheses, using more conventional methods”, concluded Markus Frey.
Frey, M., Tanni, S., Perrodin, C., O’Leary, A., Nau, M., Kelly, J., Banino, A., Bendor, D., Lefort, J., Doeller, C. F., & Barry, C. (2021). Interpreting wide-band neural activity using convolutional neural networks. eLife, 10:e66551.
https://doi.org/10.7554/eLife.66551