Deep learning with vector output
조회 수: 5 (최근 30일)
이전 댓글 표시
I need to learn a mapping from 28x28 images into a vector of 45 floating-point numbers. This is not really classification as the numbers range between -1 and 1.
When designing a deep neural network, what output layer could I use?
Best,
Samuli Siltanen
댓글 수: 0
답변 (1개)
Asvin Kumar
2019년 8월 29일
You can use the tanhLayer to obtain output values in the range of –1 to 1.
Here’s the documentation for more information: https://www.mathworks.com/help/deeplearning/ref/nnet.cnn.layer.tanhlayer.html
댓글 수: 3
Asvin Kumar
2019년 8월 30일
For the output layer, you can use a regressionLayer after the tanhLayer. This will produce predictions in the required range and compute the half-mean-squared-error loss.
Here's a link to the documentation: https://www.mathworks.com/help/deeplearning/ref/regressionlayer.html
참고 항목
카테고리
Help Center 및 File Exchange에서 Image Data Workflows에 대해 자세히 알아보기
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!