Abstract

The work “Residual data based weight correction in CNN applied to big data mining” is developed on the basis of Deep Learning. The basic concept of deep learning is implemented with different algorithms. The disease prediction work utilizes deep learning by adopting the convolution neural network. The basic convolution neural network is modified by implementing an algorithm to learn the residual data in each layer to layer transformation. To overcome the difficulty of incomplete data in existing system, we are doing experiments with modified model to reconstruct the missing data. To the best of my knowledge none of the existing works focused on both data types and learning from residual data in the area of medical big data analytics.