Deep learning using large codeword model with homomorphically compressed data

A system for deep learning using a large codeword model with homomorphically compressed dyadically encrypted data, comprising:

• a computing device comprising at least a memory and a processor;
• a plurality of programming instructions stored in the memory and operable on the processor, wherein the plurality of programming instructions, when operating on the processor, cause the computing device to:
• receive a plurality of inputs;
• preprocess the inputs to generate a plurality of input data sets;
• compress and encrypt the input data sets by:
• analyzing the input data sets to determine their properties;
• creating transformation matrices based on the properties of the input data;
• transforming the input data into modified distributions;
• generating main data streams of transformed data and secondary data streams of transformation information;
• and
• compressing the main data streams;
• tokenize the compressed main data streams into a plurality of sourceblocks;
• assign the plurality of sourceblocks a plurality of codewords, where each sourceblock is mapped to a particular codeword through a codebook;
• process the plurality of codewords through a machine learning core to generate a codeword response;
• translate the codeword response into a translated response which matches the modality of the inputs;
• decompress and decrypt the translated response;
• and
• train the machine learning core using the decompressed and decrypted response and a plurality of training data.