18542424. ADAPTIVE ARTIFICIAL NEURAL NETWORK SELECTION TECHNIQUES simplified abstract (GOOGLE LLC)

ADAPTIVE ARTIFICIAL NEURAL NETWORK SELECTION TECHNIQUES

Organization Name

GOOGLE LLC

Inventor(s)

Matthew Sharifi of Kilchberg (CH)

Jakob Nicolaus Foerster of Zurich (CH)

ADAPTIVE ARTIFICIAL NEURAL NETWORK SELECTION TECHNIQUES - A simplified explanation of the abstract

This abstract first appeared for US patent application 18542424 titled 'ADAPTIVE ARTIFICIAL NEURAL NETWORK SELECTION TECHNIQUES

Simplified Explanation

The patent application describes a computer-implemented technique for processing digital media items using artificial neural networks (ANNs) to optimize resource utilization and network conditions.

• The client computing device obtains a digital media item and a processing task request.
• Operating parameters are determined based on available computing resources and network condition.
• A set of ANNs is selected to define processing tasks for client and server computing devices.
• Processing tasks are coordinated between devices based on the selected ANN.
• Final processing results are obtained and used to generate an output.

Potential Applications

This technology could be applied in content streaming services, image and video processing applications, and distributed computing systems.

Problems Solved

This technology addresses the challenge of efficiently processing digital media items by dynamically allocating tasks between client and server devices based on resource availability and network conditions.

Benefits

The benefits of this technology include improved processing efficiency, optimized resource utilization, and enhanced performance in processing digital media items.

Potential Commercial Applications

A potential commercial application of this technology could be in cloud computing services for media processing, where tasks can be distributed between client devices and servers based on real-time conditions.

Possible Prior Art

One possible prior art could be the use of distributed computing systems for processing tasks, but the specific use of ANNs to dynamically allocate tasks based on resource availability and network conditions may be a novel aspect of this technology.

What are the specific operating parameters used to determine the set of ANNs in the patent application?

The specific operating parameters used to determine the set of ANNs in the patent application are based on the available computing resources at the client computing device and the condition of the network.

How does the patent application ensure the coordination of processing tasks between client and server computing devices?

The patent application ensures the coordination of processing tasks between client and server computing devices by selecting one of a plurality of ANNs that define which portions of the processing task are to be performed by each device, and then coordinating the processing based on the selected ANN.

Original Abstract Submitted

Computer-implemented techniques can include obtaining, by a client computing device, a digital media item and a request for a processing task on the digital item and determining a set of operating parameters based on (i) available computing resources at the client computing device and (ii) a condition of a network. Based on the set of operating parameters, the client computing device or a server computing device can select one of a plurality of artificial neural networks (ANNs), each ANN defining which portions of the processing task are to be performed by the client and server computing devices. The client and server computing devices can coordinate processing of the processing task according to the selected ANN. The client computing device can also obtain final processing results corresponding to a final evaluation of the processing task and generate an output based on the final processing results.