Convolutional neural network long short-term memory (CNN + LSTM) for histopathology cancer image classification
Deep learning algorithm such as Convolutional Neural Networks (CNN) is popular in image recognition,object recognition, scene recognition and face recognition. Compared to traditional method in machine learning, Convolutional Neural Network (CNN) will give more efficient results. This is due to Conv...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Conference or Workshop Item |
| Published: |
2020
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/id/eprint/92265/ http://dx.doi.org/10.1007/978-981-15-1366-4_19 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Universiti Teknologi Malaysia |
| Summary: | Deep learning algorithm such as Convolutional Neural Networks (CNN) is popular in image recognition,object recognition, scene recognition and face recognition. Compared to traditional method in machine learning, Convolutional Neural Network (CNN) will give more efficient results. This is due to Convolutional Neural Network (CNN) capabilities in finding the strong feature while training the image. In this experiment, we compared the Convolutional Neural Network (CNN) algorithm with the popular machine learning algorithm basic Artificial Neural Network (ANN). The result showed some improvement when using Convolutional Neural Network Long Short-Term Memory (CNN + LSTM) compared to the multi-layer perceptron (MLP). The performance of the algorithm has been evaluated based on the quality metric known as loss rate and classification accuracy. |
|---|