Learning deep neural networks: necessity and scope of prior knowledge, raw data, and labels
<p>The recent rise in machine learning has been largely made possible by novel algorithms, such as convolutional neural networks and large-scale labelled datasets. Yet obtaining labelled datasets is expensive, does not scale well, and should not be necessary for learning general representati...
| 主要作者: | |
|---|---|
| 其他作者: | |
| 格式: | Thesis |
| 語言: | English |
| 出版: |
2021
|
| 主題: |