Huawei technologies co., ltd. (20240135174). DATA PROCESSING METHOD, AND NEURAL NETWORK MODEL TRAINING METHOD AND APPARATUS simplified abstract
Contents
- 1 DATA PROCESSING METHOD, AND NEURAL NETWORK MODEL TRAINING METHOD AND APPARATUS
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 DATA PROCESSING METHOD, AND NEURAL NETWORK MODEL TRAINING METHOD AND APPARATUS - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Potential Commercial Applications
- 1.9 Possible Prior Art
- 1.10 Original Abstract Submitted
DATA PROCESSING METHOD, AND NEURAL NETWORK MODEL TRAINING METHOD AND APPARATUS
Organization Name
Inventor(s)
DATA PROCESSING METHOD, AND NEURAL NETWORK MODEL TRAINING METHOD AND APPARATUS - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240135174 titled 'DATA PROCESSING METHOD, AND NEURAL NETWORK MODEL TRAINING METHOD AND APPARATUS
Simplified Explanation
The application discloses a data processing method and a neural network model training method in the field of artificial intelligence. The data processing method involves processing data using a target neural network quantization model, which includes fusion parameters and a piecewise linear activation function. The method allows for quantization of a model using the piecewise linear activation function, improving the model's inference speed.
- Target neural network quantization model with fusion parameters
- Piecewise linear activation function for the target neural network model
Potential Applications
This technology can be applied in various fields such as image recognition, natural language processing, and speech recognition.
Problems Solved
This technology solves the problem of slow inference speed in neural network models by allowing for quantization using a piecewise linear activation function.
Benefits
The benefits of this technology include improved inference speed, reduced computational resources, and enhanced efficiency in neural network model training.
Potential Commercial Applications
Potential commercial applications of this technology include developing faster and more efficient AI systems for industries such as healthcare, finance, and autonomous vehicles.
Possible Prior Art
Prior art may include existing methods for quantizing neural network models and optimizing inference speed using different activation functions.
Unanswered Questions
How does this technology compare to existing quantization methods in terms of accuracy and efficiency?
This article does not provide a direct comparison with existing quantization methods to determine the accuracy and efficiency of the proposed technology.
What are the potential limitations or drawbacks of using a piecewise linear activation function in neural network quantization?
The article does not address any potential limitations or drawbacks of using a piecewise linear activation function in the quantization process.
Original Abstract Submitted
this application discloses a data processing method, and a neural network model training method and apparatus in the field of artificial intelligence. the data processing method includes: processing to-be-processed data by using a target neural network quantization model, where the target neural network quantization model includes a plurality of groups of fusion parameters, the target neural network quantization model is obtained by quantizing a target neural network model, an activation function of the target neural network model includes a piecewise linear function (pwl), the pwl includes a plurality of intervals, and there is a correspondence between the plurality of groups of fusion parameters and the plurality of intervals. according to the method in this application, a model that uses the pwl as an activation function can be quantized, thereby improving an inference speed of the model.
