Constructing high-performance neural network model under TensorFlow

Source: Internet
Author: User

Typical data mining and machine learning processes

Figure 1 is a typical recommendation class application that needs to find a "qualified" potential person. To draw this list from the user data, we first need to dig out the customer characteristics, then select a suitable model to predict, and finally draw the result from the user data.

The user list acquisition process in the above example is subdivided into the following sections (see Figure 2):



Business Understanding: Understanding the business itself, what is its essence. Is the problem of classification or regression. How to get the data. Which models are applied to resolve.

Data understanding: After obtaining the data, analyze the data inside what content, the data is accurate, prepares for the next pretreatment.

Data preprocessing: The original data will be noisy, format is not good, so in order to ensure the accuracy of the prediction, the need for data preprocessing.

Feature extraction: Feature extraction is one of the most important and time-consuming stages of machine learning.

Model building: Use the appropriate algorithm to get the expected exact value.

Model evaluation: Evaluate the accuracy of the model according to the test set.

Model application: Deploy the model and apply it to the actual production environment.

Application Effectiveness Assessment: Evaluate the final application results based on the final business.


best practice of constructing high performance neural network model under 1.TensorFlow 2.TensorFlow Core Process Analysis-construction, segmentation and optimization of neural network model configuration under the 3.pycharm under TensorFlow

Contact Us

The content source of this page is from Internet, which doesn't represent Alibaba Cloud's opinion; products and services mentioned on that page don't have any relationship with Alibaba Cloud. If the content of the page makes you feel confusing, please write us an email, we will handle the problem within 5 days after receiving your email.

If you find any instances of plagiarism from the community, please send an email to: info-contact@alibabacloud.com and provide relevant evidence. A staff member will contact you within 5 working days.

A Free Trial That Lets You Build Big!

Start building with 50+ products and up to 12 months usage for Elastic Compute Service

  • Sales Support

    1 on 1 presale consultation

  • After-Sales Support

    24/7 Technical Support 6 Free Tickets per Quarter Faster Response

  • Alibaba Cloud offers highly flexible support services tailored to meet your exact needs.