Using embedding functions with a deep network

A system comprising one or more computers and one or more storage devices storing instructions that when executed by the one or more computers cause the one or more computers to perform operations comprising:

• receiving an input comprising a plurality of sparse features, wherein each of the sparse features is of a different feature type;
• generating a numeric representation of the input, comprising processing each of the sparse features using a respective embedding function to generate one or more respective numeric values, wherein each of the embedding functions operates independently of each of the other embedding functions, and wherein each of the embedding functions is specific to features of a respective feature type;
• and
• providing the numeric representation of the input as input to a deep network comprising a plurality of neural network layers for classification of the input.

One or more non-transitory computer storage media storing instructions that when executed by one or more computers cause the one or more computers to perform operations comprising:

• receiving an input comprising a plurality of sparse features, wherein each of the sparse features is of a different feature type;
• generating a numeric representation of the input, comprising processing each of the sparse features using a respective embedding function to generate one or more respective numeric values, wherein each of the embedding functions operates independently of each of the other embedding functions, and wherein each of the embedding functions is specific to features of a respective feature type;
• and
• providing the numeric representation of the input as input to a deep network comprising a plurality of neural network layers for classification of the input.