From data to knowledge: Deep learning model compression, transmission and communication

With the advances of articial intelligence, recent years have witnessed a gradual transition from the big data to the big knowledge. Based on the knowledge-powered deep learning models, the big data such as the vast text, images and videos can be eciently analyzed. As such, in addition to data, the communication of knowledge implied in the deep learning models is also strongly desired. As a specic example regarding the concept of knowledge creation and communication in the context of Knowledge Centric Networking (KCN), we investigate the deep learning model compression and demonstrate its promise use through a set of experiments. In particular, towards future KCN, we introduce ecient transmission of deep learning models in terms of both single model compression and multiple model prediction. The necessity, importance and open problems regarding the standardization of deep learning models, which enables the interoperability with the standardized compact model representation bitstream syntax, are also discussed.