US Patent Application 17824306. NEUROMORPHIC COMPUTING DEVICE WITH THREE-DIMENSIONAL MEMORY simplified abstract

From WikiPatents
Jump to navigation Jump to search

NEUROMORPHIC COMPUTING DEVICE WITH THREE-DIMENSIONAL MEMORY

Organization Name

Taiwan Semiconductor Manufacturing Company, Ltd.


Inventor(s)

Chieh Lee of Hsinchu (TW)

Chia-En Huang of Xinfeng Township (TW)

Yi-Chang Liu of Hsinchu City (TW)

Wen-Chang Cheng of Richmond TX (US)

Yih Wang of Hsinchu City (TW)

NEUROMORPHIC COMPUTING DEVICE WITH THREE-DIMENSIONAL MEMORY - A simplified explanation of the abstract

This abstract first appeared for US patent application 17824306 titled 'NEUROMORPHIC COMPUTING DEVICE WITH THREE-DIMENSIONAL MEMORY

Simplified Explanation

The patent application describes a device for neuromorphic computing, which is a type of computing that mimics the structure and function of the human brain.

  • The device includes a three-dimensional memory array, which is a type of memory that can store multiple sets of weight values for a neural network model.
  • The device also includes a controller, which is responsible for applying input voltages to the memory array and receiving output voltages from the memory array.
  • The input voltages correspond to the inputs of the neural network model, and the output voltages are used to perform computations of the neural network model.
  • This device allows for efficient and parallel processing of neural network models, making it suitable for applications such as artificial intelligence and machine learning.


Original Abstract Submitted

Disclosed herein are related to a device for performing neuromorphic computing. In one aspect, a device includes a back end of line layer including a three-dimensional memory array. The three-dimensional memory array may include a plurality of memory cells to store a plurality sets of weight values of a neural network model. In one aspect, the device includes a front end of line layer including a controller. The controller may apply one or more input voltages corresponding to an input to the neural network model to the three-dimensional memory array, and receive one or more output voltages from the three-dimensional memory array to perform computations of the neural network model.