This is an interesting article that talks about Neural Networks, Manifolds and Topology. It talks about Topological properties of data, such as links, that may make it impossible to linearly separate classes using low-dimensional networks, regardless of depth. Even in cases where it is technically possible, such as spirals, it can be very challenging to do so.
This is an interesting article that talks about Neural Networks, Manifolds and Topology. It talks about Topological properties of data, such as links, that may make it impossible to linearly separate classes using low-dimensional networks, regardless of depth. Even in cases where it is technically possible, such as spirals, it can be very challenging to do so.