Deep Learning for AI
Deep Learning for AI
复制标题
DOI：
10.1145/3448250
复制
发表时间：
2021-07-01
影响因子：
22.7
通讯作者：
Hinton, Geoffrey
中科院分区：
文献类型：
--
作者：
Bengio, Yoshua;Lecun, Yann;Hinton, Geoffrey
人工神经网络研究的动机是，观察到人类智能是从相对简单的非线性神经元组成的高度并行的网络中产生的，这些网络通过调整连接的强度来学习。这一观察结果引出了一个核心的计算问题：这种一般类型的网络如何可能学习识别等困难任务所需的复杂内部表示。
RESEARCH ON ARTIFICIAL neural networks was motivated by the observation that human intelligence emerges from highly parallel networks of relatively simple, non-linear neurons that learn by adjusting the strengths of their connections. This observation leads to a central computational question: How is it possible for networks of this general kind to learn the complicated internal representations that are required for difficult tasks such as recognizing.