成为深度学习专家的七个步骤

Posted 2022-11-22 Lyndon_zheng

tags:

篇首语：本文由小常识网(cha138.com)小编为大家整理，主要介绍了成为深度学习专家的七个步骤相关的知识，希望对你有一定的参考价值。

PS：早上看到的一篇不错的原文，因为自己也正在进行这些学习研究，一路走来，觉得总结不错。本想要翻译出来的，发现有人这么做了，就直接转过来，一方面是给自己更多资源，另一方面是希望分享给更多的人。

原文作者：Ankit Agarwal

译者：Angulia Chao

原文链接： https://www.linkedin.com/pulse/7-steps-becoming-deep-learning-expert-ankit-agarwal

Apologies for using Buzz feed like click bait as the title, but it worked and got you to reading this.

One of the frequent questions we get about our work is - "Where to start learning Deep Learning?” Lot of courses and tutorials are available freely online, but it gets overwhelming for the uninitiated. We have curated a few resources below which may help you begin your trip down the Deep Learning rabbit hole.

1. The first step is to understand Machine learning, the best resource for which is Andrew Ngs (Ex-Google, Stanford, Baidu), an online course at coursera. Going through the lectures are enough to understand the basics, but assignments take your understanding to another level.

2. Next step is to develop intuition for Neural Networks. So go forth, write your first Neural Network and play with it.

3. Understanding Neural networks are important, but simple Neural Networks not sufficient to solve the most interesting problems. A variation - Convolution Neural Networks work really well for visual tasks. Standord lecture notes and slides on the same are here:CS231n Convolutional Neural Networks for Visual Recognition(notes), and CS231n: Convolutional Neural Networks for Visual Recognition (lecture slides). Also here and here are two great videos on CNNs.

4. Next step is to get following for running your first CNN on your own PC.

Buy GPU and install CUDA
Install Caffe and its GUI wrapper Digit
Install Boinc (This will not help you in Deep Learning, but would let other researchers use your GPU in its idle time, for Science)

5. Digit provides few algorithms such as - Lenet for character recognition and Googlenet for image classification algorithms. You need to download dataset for Lenet and dataset for Googlenet to run these algorithms. You may modify the algorithms and try other fun visual image recognition tasks, like we did here.

6. For various Natural Language Processing (NLP) tasks, RNNs (Recurrent Neural Networks) are really the best. The best place to learn about RNNs is the Stanford lecture videos here. You can download Tensorflow and use it for building RNNs.

7. Now go ahead and choose a Deep Learning problem ranging from facial detection to speech recognition to a self-driving car, and solve it.

If you are through with all the above steps - Congratulations! Go ahead and apply for a position at Google, Baidu, Microsoft, Facebook or Amazon. Not many are able to achieve, what you just did. But, if you want to engage in cutting edge innovation with Deep Learning and work with us, please do connect.

We would try our best to answer your doubts and questions related to Deep Learning. Please do write to us at info@silversparro.com.

关于我们的工作最常被问到的一个问题就是-“我该如何开始深度学习呢？”现在网上已经有很多的免费教程以及学习指南作为学习资源，但是它们对于一个毫无经验的学者来说还是太具挑战性。我们将在下方列出一部分收藏的资源，它或许能够帮助你从零开始对深度学习的探险之旅。

1.第一步就是理解机器学习，最好的资源是吴恩达在coursera的机器学习在线课程（Andrew Ngs (Ex-Google, Stanford, Baidu), an online course at coursera）将课程整体过一遍足够你理解基础知识，但是课程任务能够让你在另一个层次上进行知识理解。

2.接下来就是开发你自己的神经网络。所以大胆向前尝试吧，写下你的第一个神经网络（first Neural Network ），并且尽情享受乐趣。

3.理解神经网络是非常重要的，但是简单的神经网络却不足以解决那些最有趣的实际问题。而变化的卷积神经网络在视觉任务的处理上表现非常出色。斯坦福大学的教程笔记和PPT都在这里提供大家参考：CS231n Convolutional Neural Networks for Visual Recognition(notes), and CS231n: Convolutional Neural Networks for Visual Recognition (lecture slides)。