2017/05/01 by Juan Andrés Laura, Laura, Juan Andrés, Gabriel Omar Masi +3
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Fuzzy Logic and Control Systems #Information Theory (cs.IT) #Natural Language Processing Techniques #Neural Networks and Applications
paper · pdf · doi:10.48550/arxiv.1705.00697
openalex publication_date 2017/05/01 · openalex created_date 2022/10/07 · openalex updated_date 2026/07/28
In recent studies [1][13][12] Recurrent Neural Networks were used for\ngenerative processes and their surprising performance can be explained by their\nability to create good predictions. In addition, data compression is also based\non predictions. What the problem comes down to is whether a data compressor\ncould be used to perform as well as recurrent neural networks in natural\nlanguage processing tasks. If this is possible,then the problem comes down to\ndetermining if a compression algorithm is even more intelligent than a neural\nnetwork in specific tasks related to human language. In our journey we\ndiscovered what we think is the fundamental difference between a Data\nCompression Algorithm and a Recurrent Neural Network.\n