A coded flash memory system and method for realizing image convolution
A coding and convolution technology, applied to the details of image processing hardware, image memory management, information storage, etc., can solve the problems that cannot be practically applied, and the fluctuation of parameters is too large
Active Publication Date: 2020-01-03
PEKING UNIV
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, the inventors found that these new types of memory, such as resistive variable memory, still have problems such as excessive fluctuations in parameters during operation, and cannot be used in practical applications in a short period of time.
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0026] Other aspects, advantages and salient features of the present invention will become apparent to those skilled in the art from the following detailed description of exemplary embodiments of the present invention when taken in conjunction with the accompanying drawings.
[0027] In the present invention, the terms "include" and "comprising" and their derivatives mean to include but not limit; the term "or" is inclusive, meaning and / or.
[0028] In this specification, the various embodiments described below to describe the principles of the present invention are illustrative only and should not be construed as limiting the scope of the invention in any way. The following description with reference to the accompanying drawings is provided to assist in a comprehensive understanding of exemplary embodiments of the present invention as defined by the claims and their equivalents. The following description includes numerous specific details to aid in understanding, but these sh...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention provides an encoding-type flash memory system capable of achieving image convolution. The encoding-type flash memory system comprises an encoding-type flash memory array, the encoding-type flash memory array comprises n2 first encoding-type flash memory units, n2 second encoding-type flash memory units, a first word line, a second word line, n2 bit lines, a first wire, a second wire and an operational amplifier. Each encoding-type flash memory unit comprises a source terminal, a grid terminal and a drain terminal, and is used for storing convolution kernel data. The word lines are connected with the grid terminals of the encoding-type flash memory units, and are used for applying driving voltage. Each bit line is connected with the drain terminals of a corresponding pair of one first encoding-type flash memory unit and one second encoding-type flash memory unit, and is used for transmitting a corresponding element in a pixel matrix. The wires are connected with the source terminals of the encoding-type flash memory units. The operational amplifier comprises a positive input terminal, a negative input terminal and an output terminal, the positive input terminal is connected with the first wire, the negative input terminal is connected with the second wire, and the output terminal is used for outputting the convolution processing result.
Description
technical field [0001] The invention belongs to the technical field of semiconductor integrated circuits and its manufacture, and more specifically relates to a coded flash memory system and method for realizing image convolution. Background technique [0002] Convolutional neural network is an efficient recognition method developed in recent years. Its basic structure consists of two layers, one of which is the feature extraction layer, which mainly uses convolution to connect the input of each neuron with the local receptive field of the previous layer, and extracts the local features of the input image. The other layer is the feature mapping layer, which is responsible for mapping each feature into a plane, and the weights of all neurons on the plane are equal. This structure of local weight sharing can reduce the complexity of the network, so the convolutional neural network has significant advantages in speech recognition and image processing. In the application proce...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06T1/60G11C16/04G11C16/08
CPCG06T1/60G06T2200/28G11C16/0408G11C16/08
Inventor 康晋锋韩润泽黄鹏刘晓彦刘力锋
Owner PEKING UNIV