2024年Go最全【程序员读论文】LeCun, Y(2)，2024年最新2024年Golang开发陷入饱和,

2401_84911273

于 2024-05-14 00:05:54 发布

阅读量861

点赞数 9

分类专栏：程序员文章标签： go 学习面试

本文链接：https://blog.csdn.net/2401_84911273/article/details/138824998

版权

程序员专栏收录该内容

57 篇文章 0 订阅

订阅专栏

网上学习资料一大堆，但如果学到的知识不成体系，遇到问题时只是浅尝辄止，不再深入研究，那么很难做到真正的技术提升。

需要这份系统化的资料的朋友，可以添加戳这里获取

一个人可以走的很快，但一群人才能走的更远！不论你是正从事IT行业的老鸟或是对IT行业感兴趣的新人，都欢迎加入我们的的圈子（技术交流、学习资源、职场吐槽、大厂内推、面试辅导），让我们一起学习成长！

- 一、先看题目、摘要、结论
  - 二、文章主体
  - 三、总结

今天要读的论文是深度学习的里程碑之作，集齐了三位在深度学习领域举足轻重的人物。

论文名称：LeCun, Y., Bengio, Y. & Hinton, G. Deep learning. Nature 521, 436–444 (2015).

论文地址：LeCun, Y., Bengio, Y. & Hinton, G. Deep learning. Nature 521, 436–444 (2015).

论文百度网盘下载地址：https://pan.baidu.com/s/1V6tJvmRLSVtgyrOHH0Egvg，提取码：jh9o

一、先看题目、摘要、结论

题目：Deep learning

摘要：

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

深度学习允许由多个处理层组成的计算模型学习具有多个抽象级别的数据表示。这些方法极大地提高了语音识别、视觉对象识别、对象检测和许多其他领域（如药物发现和基因组学）的最新技术水平。深度学习通过使用反向传播算法来发现大数据集中的复杂结构，以指示机器应该如何改变用于计算每一层表示的内部参数，该参数是用来从上一层的表示计算本层的表示。深度卷积网络给处理图像、视频、语音和音频带来了重大的突破。而循环网络已经照亮了序列数据处理，比如文本和语音。

backpropagation ：反向传播

State of the art（没有"-" ）指的是“技术现状；技术发展水平 ”，state-of-the-art指的是“前沿技术的；技术先进的 ”。

摘要中透露出的关键词：处理层，反向传播算法，大数据，深度卷积网络，循环网络。

结论：

The future of deep learning

Unsupervised learning had a catalytic effect in reviving interest in deep learning, but has since been overshadowed by the successes of purely supervised learning. Although we have not focused on it in this Review, we expect unsupervised learning to become far more important in the longer term. human and animal learning is largely unsupervised：we discover the structure of the world by observing it, not by being told the name of every object .

Human vision is an active process that sequentially samples the optic array in an intelligent, task-specific way using a small, high-resolution fovea with a large, low-resolution surround. We expect much of the future progress in vision to come from systems that are trained end-to end and combine ConV Nets with RNNs that use reinforcement learning to decide where to look. Systems combining deep learning and rein forcement learning are in their infancy, but they already outperform passive vision systems at classification tasks and produce impressive results in learning to play many different video games .

Natural language understanding is another area in which deep learning is poised to make a large impact over the next few years. We expect systems that use RNNs to understand sentences or whole documents will become much better when they learn strategies for selectively attending to one part at a time.

Ultimately, major progress in artificial intelligence will come about through systems that combine representation learning with complex reasoning. Although deep learning and simple reasoning have been used for speech and handwriting recognition for a long time, new paradigms are needed to replace rule-based manipulation of symbolic expressions by operations on large vectors.

无监督学习在重振对深度学习的兴趣方面具有催化作用，但此后被纯监督学习的成功所掩盖。虽然我们在本篇论文中没有关注它，但我们预计无监督学习从长远来看会变得更加重要。人类和动物的学习在很大程度上是无监督的：我们通过观察来发现世界的结构，而不是通过被告知每个物体的名称。

人类视觉是一个主动过程，它使用具有大型低分辨率环绕声的小型高分辨率中央凹以智能、特定于任务的方式对光学阵列进行顺序采样。我们预计未来在视觉方面的大部分进展将来自端到端训练的系统，并将 ConV 网络与使用强化学习的 RNN 相结合来决定在哪里看。结合深度学习和强化学习的系统还处于起步阶段，但它们已经在分类任务上胜过被动视觉系统，并在学习玩许多不同的视频游戏时产生了令人印象深刻的结果。