Semiconductor device and electronic device including the semiconductor device
A semiconductor device with a small circuit area that consumes low power is provided. The semiconductor device includes a shift register, a sample-and-hold circuit, a first buffer circuit, and a second buffer circuit. The sample-and-hold circuit includes a first input terminal, a second input terminal, and an output terminal. An output terminal of the first buffer circuit is electrically connected to the first input terminal. The shift register is electrically connected to the second input terminal. An input terminal of the second buffer circuit is electrically connected to the output terminal of the sample-and-hold circuit. In the semiconductor device, the potential of an input analog signal is retained in the sample-and-hold circuit and the analog signal is output from an output terminal of the second buffer circuit.
1. An electronic device comprising:
an encoder comprising:
a neural network configured to perform convolution using a weight filter,
a memory cell array; and
a shift register,
wherein the memory cell array is configured to store a filter value of the weight filter,
wherein a display portion comprises pixels arranged in n rows and m columns, where n and m are each an integer greater than or equal to 1,
wherein pixel regions each comprise pixels arranged in t rows and s columns among the pixels arranged in n rows and m columns, where t is an integer greater than or equal to 1 and less than or equal to n and s is an integer greater than or equal to 1 and less than or equal to m,
wherein the shift register comprises t×m stages of retention circuits, and
wherein the shift register is configured to output t×s sets of first image data to the memory cell array at a time.
2. The electronic device according to claim 1 ,
wherein the encoder is configured to convert first image data into second image data by feature extraction and output the second image data to a decoder,
wherein the decoder is configured to restore the second image data into the first image data and output the first image data to a source driver circuit, and
wherein the source driver circuit is configured to output the first image data to a display portion.
3. The electronic device according to claim 2 , wherein the shift register is configured to output the first image data in each of a plurality of pixel regions to the memory cell array sequentially.
4. The electronic device according to claim 1 , wherein the convolution comprises a product-sum operation using first image data and a filter value of the weight filter.
5. An electronic device comprising:
a neural network configured to perform convolution using a weight filter,
a memory cell array; and
a shift register,
wherein the memory cell array is configured to store a filter value of the weight filter,
wherein a display portion comprises pixels arranged in n rows and m columns, where n and m are each an integer greater than or equal to 1,
wherein pixel regions each comprise pixels arranged in t rows and s columns among the pixels arranged in n rows and m columns, where t is an integer greater than or equal to 1 and less than or equal to n and s is an integer greater than or equal to 1 and less than or equal to m,
wherein the shift register comprises t×m stages of retention circuits, and
wherein the shift register is configured to output t×s sets of first image data to the memory cell array at a time.
6. The electronic device according to claim 5 ,
wherein an encoder is configured to convert first image data into second image data by feature extraction and output the second image data to a decoder,
wherein the decoder is configured to restore the second image data into the first image data and output the first image data to a source driver circuit, and
wherein the source driver circuit is configured to output the first image data to a display portion.
7. The electronic device according to claim 6 , wherein a shift register is configured to output the first image data in each of a plurality of pixel regions to the memory cell array sequentially.
8. The electronic device according to claim 5 , wherein the convolution comprises a product-sum operation using first image data and a filter value of the weight filter.
9. An electronic device comprising:
a neural network configured to perform convolution,
a memory cell array; and
a shift register,
wherein the memory cell array is configured to store a filter value,
wherein a display portion comprises pixels arranged in n rows and m columns, where n and m are each an integer greater than or equal to 1,
wherein pixel regions each comprise pixels arranged in t rows and s columns among the pixels arranged in n rows and m columns, where t is an integer greater than or equal to 1 and less than or equal to n and s is an integer greater than or equal to 1 and less than or equal to m,
wherein the shift register comprises t×m stages of retention circuits, and
wherein the shift register is configured to output t×s sets of first image data to the memory cell array at a time.
10. The electronic device according to claim 9 ,
wherein an encoder is configured to convert first image data into second image data by feature extraction and output the second image data to a decoder,
wherein the decoder is configured to restore the second image data into the first image data and output the first image data to a source driver circuit, and
wherein the source driver circuit is configured to output the first image data to a display portion.
11. The electronic device according to claim 10 , wherein a shift register is configured to output the first image data in each of a plurality of pixel regions to the memory cell array sequentially.