Method and system for constructing neural network model

A neural network model and model training technology, applied in the field of building neural network models, can solve the problem of high professional requirements for algorithm engineers
CN110689124AInactive Publication Date: 2020-01-14DATACANVAS LTD
3 Cites 1 Cited by

Patent Information

Authority / Receiving Office
CN Β· China
Current Assignee / Owner
DATACANVAS LTD
Publication Date
2020-01-14
Estimated Expiration
Not applicable Β· inactive patent

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention provides a method and a system for constructing a neural network model. The method comprises the following steps: displaying a user interface comprising at least two components; receiving a first input executed by a user in the user interface; in response to the first input, constructing a first neural network model within the user interface. According to the method, the use threshold of the neural network can be reduced. The method is convenient for users to use, users who cannot write codes can also construct, train and use the neural network model, the users can have more intuitive understanding and deepen understanding on the neural network, and the users can conveniently and quickly master the neural network model.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the field of big data processing, in particular to a method and system for constructing a neural network model. Background technique

[0002] With the rise of deep learning, neural network has the advantages of not needing feature engineering for original data, short prediction time and high prediction accuracy of neural network model after full training. Problem areas, such as NLP (Natural Language Processing, natural language processing), CV (Computer Vision, computer vision), automatic driving, face recognition and other scenes have good performance. However, compared with traditional rule-based machine learning algorithms, neural network algorithms directly obtain "knowledge" from raw data, resulting in long model training time and relatively poor model interpretability.

[0003] In existing data analysis systems, relatively complex coding is required to construct a neural network, and complex parameters need to be adjuste...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More