Automatic machine learning method based on reinforcement learning

Abstract

The invention discloses an automatic machine learning method based on reinforcement learning, which comprises the following steps of: shielding heterogeneity among different machine learning algorithmlibraries by using a unified API (Application Program Interface) interface, and calling algorithms in the different machine learning algorithm libraries in the Python language by taking Python as a programming language; modeling an automatic machine learning problem as a reinforcement learning problem, carrying out state space division on a candidate machine learning algorithm, determining a transfer relation between states, and using the Q-Learning algorithm to complete the process of searching the machine learning assembly line; carrying out metafeature extraction on the data set, searchingthe most similar data set, and accelerating the convergence process of automatic machine learning through operation information on the most similar data set. The problems that an existing automatic machine learning system is low in convergence speed and poor in expandability, and the final prediction performance cannot reach the expectation are solved.

Description

technical field [0001] The invention relates to the field of automatic machine learning, in particular to an automatic machine learning method based on reinforcement learning. Background technique [0002] There are many algorithms to choose from in the field of machine learning, and each algorithm has its own applicable scenarios. For ordinary data analysts, how to choose the optimal algorithm model according to specific application scenarios is a task with high technical threshold. [0003] Most machine learning applications can be expressed as an end-to-end machine learning pipeline, which includes not only the algorithm selection stage, but also the data preprocessing and feature selection stages. Each stage contains a variety of optional processing methods. Therefore, how to design an efficient machine learning pipeline is more technically challenging. [0004] Grid search and random search are the original automated methods. Because of their simplicity, well-known ...

AI Technical Summary

Problems solved by technology

[0008] Purpose of the invention: Aiming at the problems and deficiencies in the above-mentioned prior art, the present invention provides an automatic machine learning method based on reinforcement learning, which solves the problems of existing automatic machines The learning system has slow convergence speed, poor scalability, and the final prediction performance is not as expected

Images