How to implement a search engine-like function through a deep learning model?

Assume that there are

  • data set A (known sample information).
  • data set B (unknown sample information).

What I want to achieve is:

  1. Sort each sample of the data set A in a two-dimensional space according to a certain rule, that is, make it representable in two-dimensional coordinates.
    (According to the degree of similarity, correlation, etc. between the samples)

  2. When a sample is extracted from the data set B and input to the deep learning model, the model can search in the data set A to obtain a sample (set) that has a certain correlation with the input sample.

How can I achieve it? :thinking: :thinking:

You can use that as a starting point:


but for the embedding you could only use 2D instead of more dimensions.

However, I am not sure if this can work with only 2D, but I would be happy to know if you find out. :slight_smile:

1 Like

Not related to deeplearning but you can take a look at metric-learning http://contrib.scikit-learn.org/metric-learn/introduction.html . This kind of machine learning technique will try to reduce the distance of 2 similar samples and increase distance for different samples

1 Like