20240054319. Data Flow Method and Apparatus for Neural Network Computation simplified abstract (Zhejiang Lab)
Contents
Data Flow Method and Apparatus for Neural Network Computation
Organization Name
Inventor(s)
Hongsheng Wang of Hangzhou (CN)
Data Flow Method and Apparatus for Neural Network Computation - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240054319 titled 'Data Flow Method and Apparatus for Neural Network Computation
Simplified Explanation
The patent application describes a data flow method and apparatus for neural network computation in a deep learning training system.
- Initializing the lifecycle of a variable in a computational graph.
- Defining a propagation rule for a variable in use to flow through a node in the computational graph.
- Producing a definition of a variable at a precursor node if the variable is used at a certain node in the computational graph.
- Potential Applications
- Deep learning training systems
- Neural network computation
- Data flow modeling
- Problems Solved
- Efficient management of variable lifecycles in computational graphs
- Improved propagation of variables through nodes in neural networks
- Benefits
- Enhanced performance in deep learning training systems
- More effective neural network computation
- Streamlined data flow modeling for complex systems
Original Abstract Submitted
disclosed are a data flow method and apparatus for neural network computation. the method includes: step 1, initializing the lifecycle of a variable in a computational graph, i.e., initializing a time period from the start of a definition of the variable to the end of use as the lifecycle of the variable in the computational graph; and step 2, defining a propagation rule for a variable in use to flow through a node, i.e., defining that in the case that a variable at a certain node in the computational graph is used, a definition of the variable is produced at a precursor node of the node, such that an input set of valid variables flowing through the node contains the variable. the application discloses a data flow modeling method and apparatus for neural network computation in a deep learning training system.
