Developed algorithm that can read the thoughts of mice

Swiss scientists have developed a new algorithm that can decipher and visualize what a mouse sees through brain signals.

According to news from the Medicalxpress site, researchers from the Swiss Federal Institute of Technology have found a new algorithm for the artificial neural network model that will be used to capture brain signals and dynamics. Using a machine learning algorithm called CEBRA, the researchers were able to crack the codes in the nerves of the brain.

In the rat experiment, a rat was shown a black and white video clip from the 1960s. In the experiment, using the newly developed algorithm, brain signals from the mouse were examined and the observed images were they were able to project onto another screen almost exactly the same as the original.

In the experiment, the mice’s brain signals were measured with electrode probes placed directly into the brain’s visual cortex and optical probes created with the help of genetically modified mice, while CEBRA was run using data on the mice’s brain activity. and the movies they watched. It has been reported that CEBRA is not capable of fully reconstructing what people see, but it represents an important step forward in this area.

Mackenzie Mathis, Bertarelli’s director of Integrative Neuroscience, who conducted the research, said the study will help enable high-performance brain-machine interfaces (BMIs) and develop algorithms needed in neurotechnology.

Mathis said the new algorithm’s success lies in its ability to combine brain signals with movie data. The results of the research were published in the journal “Nature”. (AA)