Amazon technologies, inc. (20240256636). ARTIFICIAL INTELLIGENCE SYSTEM FOR MEDIA ITEM CLASSIFICATION USING TRANSFER LEARNING AND ACTIVE LEARNING simplified abstract
ARTIFICIAL INTELLIGENCE SYSTEM FOR MEDIA ITEM CLASSIFICATION USING TRANSFER LEARNING AND ACTIVE LEARNING
Organization Name
Inventor(s)
Fedor Zhdanov of Seattle WA (US)
Emanuele Coviello of San Diego CA (US)
Benjamin Alexei London of Seattle WA (US)
ARTIFICIAL INTELLIGENCE SYSTEM FOR MEDIA ITEM CLASSIFICATION USING TRANSFER LEARNING AND ACTIVE LEARNING - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240256636 titled 'ARTIFICIAL INTELLIGENCE SYSTEM FOR MEDIA ITEM CLASSIFICATION USING TRANSFER LEARNING AND ACTIVE LEARNING
Simplified Explanation: The patent application describes a process where a machine learning model is trained using active learning to select data items and labels, generate feature sets, and store the trained model.
Key Features and Innovation:
- Implementation of active learning to select data items and labels for training.
- Generation of feature sets using feature processing elements from a different machine learning model.
- Storage of the trained machine learning model upon meeting a training completion criterion.
Potential Applications: This technology can be applied in various fields such as healthcare, finance, marketing, and more for improving predictive modeling and decision-making processes.
Problems Solved: This technology addresses the challenges of efficiently training machine learning models with limited labeled data and optimizing feature selection for improved model performance.
Benefits:
- Enhanced accuracy and efficiency in training machine learning models.
- Improved decision-making processes based on predictive modeling.
- Increased scalability and adaptability of machine learning systems.
Commercial Applications: The technology can be utilized in industries such as healthcare for disease diagnosis, finance for fraud detection, and marketing for customer segmentation to improve operational efficiency and decision-making processes.
Questions about the Technology: 1. How does active learning improve the training process of machine learning models? 2. What are the potential limitations of using feature processing elements from a different model in generating feature sets?
Frequently Updated Research: Stay updated on advancements in active learning techniques, feature selection methods, and model training algorithms to enhance the efficiency and performance of machine learning systems.
Original Abstract Submitted
at an artificial intelligence system, training iterations of a first machine learning model are implemented. in a particular iteration, a group of data items are selected from an item collection using active learning, and respective labels selected from a set of tags are obtained for at least some of the items of the group. using feature processing elements of a different machine learning model, a respective feature set corresponding to individual labeled items is generated in the iteration, and the feature sets are included in a training set used to train the first machine learning model. a trained version of the first machine learning model is stored after a training completion criterion is met.
