前言:
Yann LeCun、Yoshua Bengio和Geoffrey Hinton在2015年《Nature》杂志合作发表了综述文章《Deep Learning》,深入浅出地介绍了深度学习的基本原理,核心优势和未来展望。英文链接:Deep learning
自己翻译并学习下,欢迎留言交流。
Deep learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These methods have dramatically improved the state-of-the-art in speech recognition, visual object recognition, object detection and many other domains such as drug discovery and genomics. Deep learning discovers intricate structure in large data sets by using the backpropagation algorithm to indicate how a machine should change its internal parameters that are used to compute the representation in each layer from the representation in the previous layer. Deep convolutional nets have brought about breakthroughs in processing images, video, speech and audio, whereas recurrent nets have shone light on sequential data such as text and speech.
深度学习可以让 由多个处理层的组成的计算模型 来学习 具有抽象多层次的代表性数据。
这些方法显著促进了目前前沿的的语音识别、视觉对象识别、目标检测以及诸如医药研发基因组学等领域的发展。
深度学习通过使用反向传播(BP)算法发现在大数据中的复杂结构来指导机器应该如何从前一层获取误差改变本层用计算表示的内部参数。
深度卷积网络在图像、视频、语音以及音频处理领域带来突破,而递归网络在像文本和语音的时序数据方面展现了闪亮的一面。
Machine-learning technology powers many aspects of modern society: from web searches to content filtering on social net- works to recommendations on e-commerce websites, and
it is increasingly present in consumer products such as cameras and smartphones. Machine-learning systems are used to identify objects in images, transcribe speech into text, match news items, posts or products with users’ interests, and select relevant results of search. Increasingly, these applications make use of a class of techniques called deep learning.
机器学习技术驱动了现代社会的诸多领域:从网络搜索、社交网络内容过滤到电子商务网站商品推荐等等,并越来越多的展现在像相机和智能手机一样的用户产品中。
机器学习系统被用于识别图像中的目标、语音文本转换、匹配新闻元素、根据用户偏好提供职位或产品、选择相关的搜索结果。
渐渐的这些应用使用了一种称为深度学习的技术。
Conventional machine-learning techniques were limited in their ability to process natural data in their raw form. For decades, con- structing a pattern-recognition or machine-learning system required careful engineering and considerable domain expertise to design a fea- ture extractor that transformed the raw data (such as the pixel values of an image) into a suitable internal representation or feature vector from which the learning subsystem, often a classifier, could detect or classify patterns in the input.
传统机器学习在处理原始数据中的能力有限。
几十年来,创建一个识别模式或者机器学习系统需要精细的设计以及大量专业知识去设计特征提取器来完成将原始数据(如图像的像素值)转换为一个合适的表征或者特征向量,在这个学习系统当中通常是一个分类器来完成对输入样本的检测和分类。
Representation learning is a set of methods that allows a machine tobe fed with raw data and to automatically discover the representationsneeded for detection or classification. Deep-learning methods arerepresentation-learning methods with multiple levels of representa-tion, obtained by composing simple but non-linear modules that eachtransform the representation at one level (starting with the raw input)into a representation at a higher, slightly more abstract level. With thecomposition of enough such transformations, very complex functionscan be learned. For classification tasks, higher layers of representationamplify aspects of the input that are important for discrimination andsuppress irrelevant variations. An image, for example, comes in theform of an array of pixel values, and the learned features in the firstlayer of representation typically represent the presence or absence ofedges at particular orientations and locations in the image. The secondlayer typically detects motifs by spotting particular arrangements ofedges, regardless of small variations in the edge positions. The thirdlayer may assemble motifs into larger combinations that correspondto parts of familiar objects, and subsequent layers would detect objectsas combinations of these parts. The key aspect of deep learning is thatthese layers of features are not designed by human engineers: theyare learned from data using a general-purpose learning procedure.
持续翻译更新中...