图 书 馆
人工神经网络学习的不合理有效性Unreasonable Effectiveness of Learning Artificial Neural Networks |
|
| 课程网址: | http://videolectures.net/BIDSAconference2016_zecchina_neural_netw... |
| 主讲教师: | Riccardo Zecchina |
| 开课单位: | 都灵理工学院 |
| 开课时间: | 2016-09-28 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | Deep networks are some of the most widely used tools in data science. Learning is in principle a hard problem in these systems, but in practice heuristic algorithms often find solutions with good generalization properties. We propose an explanation of this good performance in terms of a novel large-deviation measure: we show that there are regions of the optimization landscape which are both robust and accessible, and that their existence is crucial to achieve good performance on a class of particularly difficult learning problems. Building on these results, we introduce basic algorithmic schemes which improve existing optimization algorithms and provide a framework for further research on efficient learning for huge data sets and for novel computational technologies. |
| 关 键 词: | 深度网络; 数据科学; 大型数据集 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2021-12-26：zkj |
| 最后编审: | 2021-12-26：zkj |
| 阅读次数: | 60 |