Unsupervised Feature Learning _介绍

Course Description

课程描述：

        Machine learning has proved a powerful tool for artificial intelligence and data mining problems. However, its success has usually relied on having a good feature representation of the data, and having a poor representation can severely limit the performance of learning algorithms. These feature representations are often hand-designed, require significant amounts of domain knowledge and human labor, and do not generalize well to new domains.

        机器学习已经被证明是解决人工智能和数据挖掘问题的强有力工具。但是，它的成功通常依赖于数据要有很好的特征表示，差的特征表示将会严重地限制学习算法的的功能。这些特征表示通常是手工设计的，需要丰富的领域知识，消耗大量的人物，而且并不能很了的扩展到新的领域。

        To address these issues, there has been much interest in algorithms that learn feature hierarchies from unlabeled data. For example, methods such as deep belief networks, sparse coding-based methods, convolutional networks, and deep Boltzmann machines, have shown promise and have been successfully applied to a variety of tasks in computer vision, audio processing, natural language processing, information retrieval, and robotics.

        为了解决特征表示的这个问题，目前，已经有许多研究者对从无标签的数据中学习特征层次结构图的算法感兴趣。这些算法已经显示了它们的广阔前景，并且已经成功地应用于各种各样的任务，机器视觉，声音处理，自然语言处理，信息检索和机器人，例如深度信念网络，稀疏基于编码方法，卷积网络和深度玻尔兹曼机等算法。

        In this seminar course, we will focus on reviewing principles and recent progress in unsupervised feature learning algorithms, with a goal of developing useful features for machine learning applications. Topics include clustering, sparse coding, autoencoders, restricted Boltzmann machines, and deep belief networks. The course will require an open-ended research project.
          在这个研究课程中，我们将重点放在简单的回顾算法的基本原理和无监督特征学习算法的最新进展，目标是为机器学习应该开发出有用的特征。 主题主要有聚类，稀疏编码，局限玻尔兹曼机和深度信念网络。该课程将需要一个开放式的研究项目。