Micron technology, inc. (20240161489). Quantization at Different Levels for Data Used in Artificial Neural Network Computations simplified abstract

From WikiPatents
Jump to navigation Jump to search

Quantization at Different Levels for Data Used in Artificial Neural Network Computations

Organization Name

micron technology, inc.

Inventor(s)

Saideep Tiku of Folsom CA (US)

Shashank Bangalore Lakshman of Folsom CA (US)

Poorna Kale of Folsom CA (US)

Quantization at Different Levels for Data Used in Artificial Neural Network Computations - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240161489 titled 'Quantization at Different Levels for Data Used in Artificial Neural Network Computations

Simplified Explanation

The patent application describes a pair of smart glasses with a digital camera and a processing device that uses an artificial neural network to analyze captured images. The processing device can apply different quantization levels to data from different regions of the image, adjusting the accuracy of the analysis to reduce energy consumption. Based on the neural network's output, the glasses can display virtual content overlaid on the user's view of reality.

  • Smart glasses with digital camera and processing device
  • Analysis of images using artificial neural network with weight data
  • Different quantization levels applied to data from different image regions
  • Adjusting accuracy of analysis to reduce energy consumption
  • Displaying virtual content overlaid on user's view of reality

Potential Applications

The technology described in the patent application could have various applications in fields such as augmented reality, healthcare, remote assistance, and navigation.

Problems Solved

This technology solves the problem of energy consumption in smart glasses by adjusting the accuracy of image analysis based on different regions of the image.

Benefits

The benefits of this technology include improved energy efficiency, enhanced user experience with virtual content, and potential applications in various industries.

Potential Commercial Applications

The technology could be commercialized for use in augmented reality glasses for consumers, healthcare applications for medical professionals, remote assistance tools for technicians, and navigation aids for travelers.

Possible Prior Art

One possible prior art for this technology could be the use of artificial neural networks in image analysis for augmented reality devices.

Unanswered Questions

How does the technology handle privacy concerns related to capturing and analyzing images?

The article does not address the potential privacy implications of capturing and analyzing images using the smart glasses.

What are the limitations of the artificial neural network in terms of accuracy and processing speed?

The article does not provide information on the specific limitations of the artificial neural network used in the processing device of the smart glasses.


Original Abstract Submitted

a pair of smart glasses having: a digital camera configured to capture an image of a field of view; and a processing device configured to perform an analysis of the image using an artificial neural network having weight data. the processing device can apply different quantization levels to data from different regions of the image, and apply the different quantization levels to the weight data in weighing on the data from the different regions respectively. for example, weighing image data from a peripheral region of the image with the weight data can be performed with a lower level of accuracy than weighing image data from a center region of the image with the weight data to reduce energy consumption. based on an output of the artificial neural network responsive to the image, the glasses can present virtual content superimposed on a view of reality seen through the glasses.