Bay Area Vision Meeting: Unsupervised Feature Learning and Deep Learning
9 人推荐 · 跨 7 个月 · 2011–2013
中文导读
吴恩达（Andrew Ng）早期关于无监督特征学习与深度学习的奠基性讲座。他系统阐述了算法如何从无标签数据中自主学习高维表征，以替代传统人工特征工程，并通过图像和语音处理的可视化展示了各隐藏层的学习过程。
为什么 HN 推它
在深度学习浪潮兴起的那几年，HN 网友连续多年将其列为理解神经网络特征提取最平实清晰、最能唤起极客兴奋感的全景导论。
「他用最朴素易懂的方式讲清了这套架构在图像和音频处理中的底层工作机制。」HN 网友原话：he explains very simply how all this works for images and some examples about the audio case.
英文原摘要（HackerTube / Claude 整理）
Andrew Ng presents unsupervised feature learning and deep learning, showing how algorithms can learn representations from unlabeled data instead of hand-designed features. He gives examples in vision and audio, including visualizations of features learned by successive layers.
HN commenters recommended it for years as a simple, exciting overview of the deep learning wave.
HN 上的提及
Here's a great talk by Andrew Ng of Stanford
Here is a more in-depth presentation he gave on the same subject at a Google Tech Talk
Here's a video talking about current research into this at Stanford
Here is a reasonably approachable talk he gave about it.
he explains very simply how all this works for images and some examples about the audio case.