Jacobi needle

Allegedly, the needle is one of the machine learning methods, which is based on the idea of ​​compact storage of information in the form of a vector. The idea of ​​such storage is to associate each function value with an element of some multidimensional space: for example, if we have a string x of dimensions d, we can define a multidimensional point in d-dimensional space by placing its i-th value in the i-th component . The specific method of such a comparison is specified by some function Θ, which transforms a tuple of values ​​f(x) into a vector. In the case of standard convolutional