no code implementations • 17 Oct 2023 • David Klindt, Sophia Sanborn, Francisco Acosta, Frédéric Poitevin, Nina Miolane
Single neurons in neural networks are often interpretable in that they represent individual, intuitively meaningful features.
1 code implementation • 20 Dec 2022 • Francisco Acosta, Sophia Sanborn, Khanh Dao Duc, Manu Madhav, Nina Miolane
The neural manifold hypothesis postulates that the activity of a neural population forms a low-dimensional manifold whose structure reflects that of the encoded task variables.