Deep Machine Learning - A New Frontier in Artificial Intelligence Research [Research Frontier] 论文
2010IEEE Computational Intelligence Magazine引用 1106
Anomaly Detection Techniques and ApplicationsGenerative Adversarial Networks and Image SynthesisNeural Networks and Applications
详细信息
- 发表期刊/会议
- IEEE Computational Intelligence Magazine
- 发表日期
- 2010-10-20
- 发表年份
- 2010
关键词
Anomaly Detection Techniques and ApplicationsGenerative Adversarial Networks and Image SynthesisNeural Networks and Applications
摘要
This article provides an overview of the mainstream deep learning approaches and research directions proposed over the past decade. It is important to emphasize that each approach has strengths and "weaknesses, depending on the application and context in "which it is being used. Thus, this article presents a summary on the current state of the deep machine learning field and some perspective into how it may evolve. Convolutional Neural Networks (CNNs) and Deep Belief Networks (DBNs) (and their respective variations) are focused on primarily because they are well established in the deep learning field and show great promise for future work.