Microsoft technology licensing, llc (20240112032). TRANSFER-LEARNING FOR STRUCTURED DATA WITH REGARD TO JOURNEYS DEFINED BY SETS OF ACTIONS simplified abstract

TRANSFER-LEARNING FOR STRUCTURED DATA WITH REGARD TO JOURNEYS DEFINED BY SETS OF ACTIONS

Organization Name

microsoft technology licensing, llc

Inventor(s)

Kiran Rama of Bangalore (IN)

Ke Li of Redmond WA (US)

Sharath Kumar Rangappa of Bangalore (IN)

Shariq Ahmad of Kolkata (IN)

Akash Kodibail of Bengaluru (IN)

TRANSFER-LEARNING FOR STRUCTURED DATA WITH REGARD TO JOURNEYS DEFINED BY SETS OF ACTIONS - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240112032 titled 'TRANSFER-LEARNING FOR STRUCTURED DATA WITH REGARD TO JOURNEYS DEFINED BY SETS OF ACTIONS

Simplified Explanation

The patent application describes techniques for transfer-learning for structured data related to journeys defined by sets of actions. A first deep neural network (DNN) is trained for a first journey using structured data, and the weights of nodes in this DNN are transferred to a second DNN for a second journey using transfer-learning. An embedding layer replaces the final layer of the first DNN in the second DNN to provide an output with the same number of nodes as a pre-final layer of the first DNN. The weights of the nodes in the embedding layer are initialized based on the probability that a new feature of the second journey co-occurs with each feature in the structured data. A softmax function is applied on the final layer of the second DNN to indicate possible next actions of the second journey.

• Techniques for transfer-learning for structured data
• Training deep neural networks for different journeys
• Transferring weights between neural networks
• Using an embedding layer to replace the final layer
• Initializing weights based on feature co-occurrence probability
• Applying softmax function for predicting next actions

Potential Applications

This technology could be applied in various fields such as recommendation systems, personalized marketing, and predictive analytics.

Problems Solved

This technology helps in improving the efficiency and accuracy of predicting next actions based on structured data related to journeys.

Benefits

The benefits of this technology include enhanced prediction capabilities, improved decision-making processes, and better understanding of user behavior.

Potential Commercial Applications

One potential commercial application of this technology could be in the development of advanced recommendation systems for e-commerce platforms.

Possible Prior Art

Prior art in the field of transfer-learning for structured data and neural network training techniques may exist, but specific examples are not provided in the patent application.

How does this technology compare to existing transfer-learning methods for structured data?

This article does not provide a direct comparison with other transfer-learning methods in the field.

What are the computational requirements for implementing this technology in real-world applications?

The patent application does not delve into the computational resources needed for deploying this technology.

Original Abstract Submitted

techniques are described herein that are capable of performing transfer-learning for structured data with regard to journeys defined by sets of actions. a first deep neural network (dnn) for a first journey is trained using structured data. weights of nodes in the first dnn are transferred to nodes in a second dnn for a second journey using transfer-learning. an embedding layer replaces a final layer of the first dnn in the second dnn to provide an output with a same number of nodes as a pre-final layer of the first dnn. weights of the nodes in the embedding layer are initialized based at least on a probability that a new feature of the second journey co-occurs with each feature in the structured data. a softmax function is applied on a final layer of the second dnn to indicate possible next actions of the second journey.