18399715. DATA PROCESSING METHOD, AND NEURAL NETWORK MODEL TRAINING METHOD AND APPARATUS simplified abstract (Huawei Technologies Co., Ltd.)
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 18399715 titled 'DATA PROCESSING METHOD, AND NEURAL NETWORK MODEL TRAINING METHOD AND APPARATUS
Simplified Explanation
The patent application describes a data processing method and a neural network model training method in the field of artificial intelligence. The method involves processing data using a target neural network quantization model, which includes fusion parameters and a piecewise linear activation function. The model can be quantized to improve the inference speed.
- Neural network model training method and apparatus in the field of artificial intelligence
- Data processing method using a target neural network quantization model with fusion parameters
- Activation function of the model includes a piecewise linear function
- Quantization of the model to improve inference speed
Potential Applications
The technology can be applied in various fields such as image recognition, natural language processing, and autonomous driving systems.
Problems Solved
The technology addresses the issue of slow inference speed in neural network models, making them more efficient for real-time applications.
Benefits
- Improved inference speed - Enhanced efficiency of neural network models - Better performance in AI applications
Potential Commercial Applications
The technology can be utilized in industries such as healthcare, finance, and manufacturing for tasks like medical image analysis, fraud detection, and quality control.
Possible Prior Art
Prior art in neural network quantization methods and activation functions may exist, but specific examples are not provided in the patent application.
Unanswered Questions
How does this technology compare to existing quantization methods in terms of accuracy and speed?
The patent application does not provide a direct comparison with other quantization methods in terms of accuracy and speed. Further research or testing may be needed to evaluate the performance of this technology against existing methods.
What are the potential limitations or challenges in implementing this technology in real-world applications?
The patent application does not discuss potential limitations or challenges in implementing this technology in real-world applications. Factors such as hardware compatibility, training time, and resource requirements could be important considerations for adoption.
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.
