Beginner's Guide to Machine/Deep Learning

Beginner’s Guide to Machine/Deep Learning

by

Click the above “Beginner’s Visual Learning” to choose to add “Starred” or “Pinned“.

Heavyweight content delivered to you firstBeginner's Guide to Machine/Deep Learning

Author: Song Gu Source: Zhihu Link: https://zhuanlan.zhihu.com/p/33194897 Editor: Wang Meng (Deep Learning Go Go Go public account) Copyright belongs to the author, this article is for academic sharing only. If there is any infringement, please contact the backend for deletion.Phase 1: Basics of Python

Video: (Choose one you like)

  • Morvan Python (https://morvanzhou.github.io/tutorials/python-basic/basic/)

  • Little Turtle Tutorial (https://www.bilibili.com/video/av4050443/?from=search&seid=15046721361172598574)

Documentation tutorials:

  • Liao Xuefeng Python (https://www.liaoxuefeng.com/wiki/1016959663602400)

  • Rookie Tutorial (https://www.runoob.com/python3/python3-tutorial.html)

Phase 2: Common Modules

  • numpy

  • matplotlib

  • pandas

Still recommend watching Morvan’s tutorials:

  • Numpy & Pandas (Morvan Python Data Processing Tutorial) (https://www.bilibili.com/video/av16378934/)

  • Matplotlib Python Plotting Tutorial (Morvan Python) (https://www.bilibili.com/video/av16378354/)

If you are looking for books, I recommend “Data Analysis with Python”.

Phase 3: Basics of Machine Learning

It is recommended to watch Andrew Ng’s course, you can watch it two or three times, there is a lot of content.

Machine Learning Practical: cuijiahua.com/blog/ml/

Reference books:

“Statistical Learning Methods” by Li Hang

Andrew Ng’s Machine Learning Notes: http://www.ai-start.com/ml2014/

Phase 4: Deep Learning

1. Andrew Ng’s Deep Learning

NetEase Cloud Classroom (with Chinese subtitles) portal: Micro-specialization in Deep Learning Engineering – Research by Leading AI Master Andrew Ng – NetEase Cloud Classroom – NetEase Cloud Classroom (https://mooc.study.163.com/smartSpec/detail/1001319001.htm)

Introduction: This should be the best introductory tutorial.

  1. Neural Networks and Deep Learning

  2. Improving Deep Neural Networks: Hyperparameter Tuning, Regularization, and Optimization

  3. Structuring Machine Learning Projects

  4. Convolutional Neural Networks

  5. Sequence Models

Andrew Ng’s Deep Learning Notes: http://www.ai-start.com/dl2017/

Reference answers and materials: https://github.com/fengdu78/deeplearning_ai_books

Chinese translation version of the homework: https://blog.csdn.net/u013733326/article/details/79827273

2. Stanford CS231n (Spring 2017)

CS231n: Convolutional Neural Networks for Visual Recognition (http://cs231n.stanford.edu/)

Introduction: A computer vision (CV) course brought to us by Professor Li Fei-Fei and her students.

[Chinese subtitles] 2017 Spring CS231n Stanford Deep Visual Recognition Course (https://mooc.yanxishe.com/course/268)

Pytorch Learning

Recommended book: Chen Yun “Deep Learning Framework PyTorch: Introduction and Practice”: https://zhuanlan.zhihu.com/p/31712507

Official tutorial: http://pytorch123.com/

Hands-On Deep Learning: https://zhuanlan.zhihu.com/p/85353963

Other open-source materials: https://github.com/zergtant/pytorch-handbook

https://github.com/TingsongYu/PyTorch_Tutorial

Object Detection: https://blog.csdn.net/songwsx/article/details/101753938

Beginner's Guide to Machine/Deep Learning

Improve a Little Every Day

What Role Do Weights and Biases Play in Neural Networks?

Beginner's Guide to Machine/Deep Learning

In simple terms, weights represent the importance of a certain factor, and the bias value is actually a threshold. Only when the left part is greater than or equal to this bias, will the neuron’s output be positive.It can also be understood that the bias here is the inherent error of the selected model, because the chosen model cannot be perfect, and the bias is independent of the data, being inherent to the model.Moreover, in some scenarios, the use of bias is also meaningless, such as in layers before the batch normalization layer, because it will be canceled out by normalization.

Good News!

Beginner’s Visual Learning Knowledge Planet

Is now open to the public 👇👇👇

Download 1: OpenCV-Contrib Extension Module Chinese Version Tutorial

Reply "Extension Module Chinese Tutorial" in the "Beginner's Visual Learning" public account backend to download the first OpenCV extension module tutorial in Chinese, covering installation of extension modules, SFM algorithms, stereo vision, object tracking, biological vision, super-resolution processing, and more than twenty chapters of content.

Download 2: Python Visual Practical Projects 52 Lectures

Reply "Python Visual Practical Projects" in the "Beginner's Visual Learning" public account backend to download 31 visual practical projects including image segmentation, mask detection, lane line detection, vehicle counting, eyeliner addition, license plate recognition, character recognition, emotion detection, text content extraction, face recognition, etc., to help quickly learn computer vision.

Download 3: OpenCV Practical Projects 20 Lectures

Reply "OpenCV Practical Projects 20 Lectures" in the "Beginner's Visual Learning" public account backend to download 20 practical projects based on OpenCV, achieving advanced OpenCV learning.

Group Chat

Welcome to join the public account reader group to communicate with peers. Currently, there are WeChat groups for SLAM, 3D vision, sensors, autonomous driving, computational photography, detection, segmentation, recognition, medical imaging, GAN, algorithm competitions, etc. (which will gradually be subdivided in the future). Please scan the WeChat number below to join the group, with the note: "nickname + school/company + research direction", for example: "Zhang San + Shanghai Jiao Tong University + Visual SLAM". Please follow the format, otherwise, you will not be approved. After successful addition, you will be invited to related WeChat groups based on your research direction. Please do not send advertisements in the group, otherwise you will be removed. Thank you for your understanding ~

Leave a Comment