Advanced analysis infrastructure for machine learning

Abstract

The invention discloses an advanced analysis infrastructure for machine learning. The advanced analysis infrastructure for machine learning comprises a machine learning system, wherein the machine learning system comprises a data input module, a machine learning algorithm library, a screening unit, a test module and a statistical module. According to the advanced analysis infrastructure for machine learning, the screening unit is added into the machine learning system for performing classification screening and data deviation screening on the input data and screening the data defects existingin a data set, thus preventing normal operation of the machine learning system from being influenced by poor quality of input data; and meanwhile, data defects in the data set are screened, and the screened data defects are displayed in time through the display module, so that related personnel can conveniently repair the defects existing in the machine learning system in time, and high economic losses brought to enterprises by some very small data defects are prevented.

Description

technical field [0001] The present invention relates to the related field of analysis infrastructure technology, in particular to an advanced analysis infrastructure for machine learning. Background technique [0002] Machine learning is the process of analyzing data by using a data set to determine a model (also called rules or functions). One type of machine learning is supervised learning, in which a model is trained with a data set that includes known output data for a sufficient amount of input data. Once a model is trained, it can be deployed, that is, applied to new input data to predict desired outputs. [0003] Poor data quality is one of the biggest risks of machine learning. If the data quality of machine learning is relatively poor, it may endanger the entire big data analysis work, leading to confusion in the entire machine learning model. At the same time, there will be many defects in poor data quality, often A small data flaw that goes unnoticed can lead t...

AI Technical Summary

Problems solved by technology

[0003] Poor data quality is one of the biggest risks of machine learning. If the data quality of machine learning is relatively poor, it may endanger the entire big data analysis work, leading to confusion in the entire machine learning model. At the same time, there are many defects in poor data quality, often A small data flaw that goes unnoticed can lead to costly mistakes that, if left unchecked, can send an entire machine learning initiative in the wrong direction

Images