Samsung electronics co., ltd. (20240346312). ELECTRONIC DEVICE AND CONTROLLING METHOD OF ELECTRONIC DEVICE simplified abstract
Contents
ELECTRONIC DEVICE AND CONTROLLING METHOD OF ELECTRONIC DEVICE
Organization Name
Inventor(s)
Parichay Kapoor of Suwon-si (KR)
Hyeonseok Lee of Suwon-si (KR)
ELECTRONIC DEVICE AND CONTROLLING METHOD OF ELECTRONIC DEVICE - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240346312 titled 'ELECTRONIC DEVICE AND CONTROLLING METHOD OF ELECTRONIC DEVICE
The abstract describes an electronic apparatus that stores data related to a neural network model and divides the learning step into multiple steps, including forward propagation, gradient calculation, and derivative calculation. It determines the execution order of these steps, integrates information on sensor usage, allocates data to tensors in memory, and trains the neural network model accordingly.
- Memory stores data related to a neural network model
- Processor divides learning step into multiple steps
- Steps include forward propagation, gradient calculation, and derivative calculation
- Determines execution order of steps
- Integrates sensor usage information
- Allocates data to tensors in memory
- Trains neural network model based on integrated execution order
Potential Applications: - Artificial intelligence - Machine learning - Data analysis - Pattern recognition - Robotics
Problems Solved: - Efficient training of neural network models - Optimized memory allocation - Improved performance of machine learning algorithms
Benefits: - Faster training process - Enhanced accuracy of neural network models - Reduced memory usage - Increased efficiency in data processing
Commercial Applications: Title: "Optimized Neural Network Training Apparatus for AI Applications" This technology can be used in various industries such as healthcare, finance, autonomous vehicles, and cybersecurity for improving data analysis, predictive modeling, and decision-making processes.
Prior Art: Researchers can explore prior studies on neural network training methods, memory optimization techniques, and sensor integration in machine learning systems to understand the evolution of this technology.
Frequently Updated Research: Stay updated on advancements in neural network training algorithms, memory management strategies, and sensor utilization in artificial intelligence systems to enhance the performance and efficiency of neural networks.
Questions about Neural Network Training Apparatus: 1. How does the integration of sensor usage information improve the training process of neural network models? 2. What are the potential challenges in allocating data to tensors in memory for training neural networks?
Original Abstract Submitted
an electronic apparatus may include a memory configured to store data related to a neural network model and at least one processor configured to divide a learning step performed through a plurality of layers of the neural network model into a plurality of steps including a forward propagation step, a gradient calculation step, and a derivative calculation step, and determine an execution order of the plurality of steps, obtain first information regarding in which step of a plurality of steps according to the determined execution order a plurality of sensors used in the plurality of layers are used, based on the determined execution order, integrate the determined execution order based on the first information and second information regarding whether tensors used in neighboring layers from among the plurality of layers are able to be shared, allocate the data to the plurality of tensors by minimizing a region of the memory for allocating data corresponding to the plurality of tensors, based on the integrated execution order, and train the neural network model according to the integrated execution order using the plurality of tensors and the data allocated to the plurality of tensors. various other embodiments are possible to be implemented.
