Abstract
Gigabytes of data is being generated now a days on daily basis which may possess some of the characteristics such as high speed, huge volume, uncertainty, non-stationary data, real time data etc. Conventional Machine Learning Techniques cannot be used for analysis of big data due to its above mentioned features. Also, traditional storage and processing techniques fails to meet the requirements. In this paper, we have discussed the various challenges that may occur while using traditional MLT for Big Data Analytics and its possible solutions. As per our survey, Parallel Processing, Dimensionality Reduction techniques, GPUs, Map reduce jobs, Deep learning, Online learning, Incremental learning are some of the possible solution to meet the challenges associated with big data analytics.
Modules
Algorithms
Deep Learning
Software And Hardware
• Hardware: Processor: i3 ,i5 RAM: 4GB Hard disk: 16 GB • Software: operating System : Windws2000/XP/7/8/10 Anaconda,jupyter,spyder,flask,hadoop Frontend :-python Backend:- MYSQL