Neural network model processing method and device, reasoning method and device and electronic equipment
A neural network model and processing method technology, applied in the field of reasoning method and its device and electronic equipment, and the processing method of neural network model, can solve the problem that the processing performance of the neural network cannot be optimized by the processor, and the performance and power consumption cannot meet the actual requirements. needs, etc.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0060] The technical solutions in the present application will be described below in conjunction with the drawings.
[0061] In order to facilitate understanding, the following is first introduced in the following contemporary depth learning, neural network model and related terms such as the present application.
[0062] Deep learning is also known as the Deep Neural Network (DNN), essentially a multi-level artificial neural network (ANN) algorithm, that is, from the structural simulative mannequin operation mechanism, from the most basic The operation mechanism of the human brain is simulated on the unit. Deep learning is divided into three links and inference. Training requires massive data input, training a complex depth neural network model. Inference refers to the use of a well-trained model, use the data to be judged to "Inference" to draw a variety of conclusions.
[0063] figure 1 A schematic diagram of an artificial intelligence technology architecture based on deep lea...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap