Multi-class classification using deeping learning
Nowadays, with the fast development of the big data and artificial intelligent, deep learning plays a significant role in different fields and infrastructures. Deep learning is a new field in machine learning research. The motivation is to build and simulate a neural network for human brain analysis...
Saved in:
| 主要作者: | |
|---|---|
| 其他作者: | |
| 格式: | Final Year Project |
| 語言: | English |
| 出版: |
2019
|
| 主題: | |
| 在線閱讀: | http://hdl.handle.net/10356/78320 |
| 標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
| 總結: | Nowadays, with the fast development of the big data and artificial intelligent, deep learning plays a significant role in different fields and infrastructures. Deep learning is a new field in machine learning research. The motivation is to build and simulate a neural network for human brain analysis and learning. It mimics the mechanism of the human brain to interpret data such as images, sounds and texts. Multi-class classification algorithms like support vector machine (SVM), and convolutional neural networks (CNNs) using deep learning are used to analyse data for classification and regression analysis. They are commonly implemented in image classification. The aim of this project is to evaluate and compare three commonly used multiclass classification methods in image classification for future application. The project can be divided into three parts. In the first part, the project explains the working principle behind CNN. In the second part, Kaggle database images are used to conduct the experiment in Matlab2019a. The last part evaluates the experiment and discuss the future work and application. |
|---|