返回到 Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization

4.9

星

43,022 個評分

•

4,618 條評論

This course will teach you the "magic" of getting deep learning to work well. Rather than the deep learning process being a black box, you will understand what drives performance, and be able to more systematically get good results. You will also learn TensorFlow.
After 3 weeks, you will:
- Understand industry best-practices for building deep learning applications.
- Be able to effectively use the common neural network "tricks", including initialization, L2 and dropout regularization, Batch normalization, gradient checking,
- Be able to implement and apply a variety of optimization algorithms, such as mini-batch gradient descent, Momentum, RMSprop and Adam, and check for their convergence.
- Understand new best-practices for the deep learning era of how to set up train/dev/test sets and analyze bias/variance
- Be able to implement a neural network in TensorFlow.
This is the second course of the Deep Learning Specialization....

Dec 24, 2017

Exceptional Course, the Hyper parameters explanations are excellent every tip and advice provided help me so much to build better models, I also really liked the introduction of Tensor Flow\n\nThanks.

Jan 14, 2020

After completion of this course I know which values to look at if my ML model is not performing up to the task. It is a detailed but not too complicated course to understand the parameters used by ML.

篩選依據：

創建者 Sinan G

•May 08, 2018

Nice breadth and depth of relevant topics in this course. Andrew Ng is as always very precise about the issues presented and helps build up our knowledge step-by-step in a super structured way. Nice to work with both Python (semi-raw) models and getting a similar introduction to TensorFlow.

創建者 Xiang J

•Oct 25, 2019

Really like the assignments in this course, which gives me hands-on experience with advanced knowledge such as Adam optimizer, gradient checking. Tensorflow v1 assignment is also good, but I am not sure whether API is still relevant as Keras based API for tensorflow v2 is already released.

創建者 Tarush S

•May 16, 2019

With this course, even the beginner can understand why what happens when tuning and optimizing a neural network model. With easy to understand methodology and great explanation, I highly recommend this course for anyone who wants to go deeper into deep learning and understand the workings.

創建者 Meghdad P

•Aug 06, 2018

Very helpful learning material.

I'm still a bit confused though, even after passing the exams and exercises, but I think its mostly because I've lost grasp on mathematics. So, the blame is on me not coursera.

Hopefully I would fit more in the Deep Learning world by finishing up the course ;)

創建者 Millard A C

•Feb 10, 2018

This is a great course and you get to do real programming and training of a Deep Neural network. Andrew Ng is an excellent instructor. The final assignment wasn't hard but the syntax was difficult to follow. Using the forum and the Tensorflow documentation you can make your way through.

創建者 Bill T

•Feb 04, 2018

This builds on the basics from the first course with some important techniques (such as Xavier initialization, Adam optimization, and batchnorm) and ends with an introduction to implementing these in TensorFlow. Fast-moving but well taught with a good mix of theory and hands-on exercises.

創建者 Sari S

•Jul 25, 2019

I am totally enlightened by this course. A lot of the concepts covered were completely new to me and very helpful in building a good performing neural network. The lectures were in depth and very well organized. The contents are not something you will come across in other tutorial sites.

創建者 Bryan W

•Jan 18, 2018

A great refresher to Andrew's original ML course at first, but also later is learning current deep learning current mindset at work. Great pace, great course, and great programming assignments. Makes me want to see the 3rd course for (i hope) more challenging programming assignments :) .

創建者 harm l

•Sep 03, 2017

Gave me a clear understanding on how to improve the calculus on a neural network. Computational software has advanced from programming in R of Python to software frameworks, hiding a lot of the math. Needs another study of the software frameworks though!

Thanks for the opportunity to join.

創建者 Maryam H

•Jun 19, 2019

prof. Ng's teaching was so great. some tricky details taught that I never considered them before. when I read the textbook, it was easy to understand and repetitive. I've learned simple and clean implementation. in overall it was important, simple, understandable, time efficient course.

創建者 Rahul K

•Feb 28, 2018

A very well structured course on some of the most overlooked (but critical) elements in Deep Learning. Prof. Andrew Ng definitely makes everything seem easy; he breaks down even the most complex of optimization algorithms and explains it with sheer simplicity. Would definitely recommend!

創建者 Pranaya M

•Aug 06, 2018

Course has been designed so well that even a aspiring beginner can learn the concepts very well.

Every student who wants to begin their career in the field of Deep Learning must follow this course.

Especially the tensor flow concept is taught very well with the help of exercise tutorial.

創建者 David J

•Jan 07, 2018

Thank you Andrew and Team for this course. I must say the course has surprised me and I have myself surprised my level of learning. But all credit to the way course is laid out and the step by step method of progress along with strong conceptual explanation helps a lot. Thank you again

創建者 Alejandro R V

•Jan 02, 2018

As usual, another incredible course taught by a really good teacher. I strongly recommend it to anyone who wants to get a firm garsp about optimization algorithms and how they really work, apart from hyperparameter tunning and regularization methods for bias/variance. Thank Andrew Ng!

創建者 Sanjay R B

•Jun 16, 2019

Very helpful in building on the foundation in neural networks and deep learning with practical experience. The programming assignments are reinforce key concepts and are a great asset to keep after the class and apply in projects. Andrew is doing great work bringing AI to the masses!

創建者 Dustin

•May 04, 2019

Nice illustration of the tricks including Batch-Norm, Optimization as well as Dropout, etc. Sometimes the lack of the theory is sort of unstatisfying, but considering the difficulty of a comprehensive intro for all of the above, it has been good enough for beginners to catch up with.

創建者 A S M A M

•Jan 01, 2018

While the first course in the specialization is the perfect introduction to the realm of NN, this course is the place where I learned to implement a true Deep Network. It talks about various optimizations and parameters of the DL models. Bonus, it introduces the tensorflow framework.

創建者 Ananth K

•Oct 24, 2017

Great course! Very well laid out approach to tuning a deep neural network. FInal introduction to Tensorflow was useful, but I think a lot of information was compressed into a single video. Suggest spreading this a little more. The Tensorflow programming assignment was pretty good.

創建者 Alberto B H

•Oct 07, 2017

Genial curso en el que aprender como optimizar tu red modificando una serie de parámetros y usando diferentes algoritmos. Ademas genial introducción a Tensorflow con el que avanzar en el montaje de redes de manera rápida. Recomendado totalmente tras realizar el curso anterior a este.

創建者 Anurag A

•Sep 10, 2017

This course is awesome. I never had this deep understanding of tuning hyperparameters, batch normalization and regularization before taking this course, though I went through several online material. The Tensorflow introduction and subsequent programming assignment is also excellent.

創建者 Prabhat K P

•Jan 10, 2020

The best course ever. I am highly impressed with the way Andrew Sir teaches and the depth of the topic, that he explains. You will never be left with a question unanswered. I am grateful to you sir, it made my life. Looking forward to complete the rest of the specialization courses.

創建者 Taras M

•Jul 26, 2018

It would be super cool if this course could be extended with pytorch just to compare with tensorflow. Usually courses are extended on udemy, for instance (not a marketing, just a comparison), even after all the materials are completed. It would be sand to have this course abandoned.

創建者 Nektarios K

•Jan 08, 2018

Really loved this course! I believe it is really important for anyone who completed the first one to enroll on this one as well as it goes over many important topics that are critical in implementing Neural Networks. And finally, it goes over Tensorflow which was really fun to do!

創建者 Emilio D P

•Sep 24, 2017

Fantastic course on Deep Learning. The concepts explained during the course are very useful, especially regularization (week 1) and optimization (week 2). The introduction to TensorFlow is great. This course has allowed me to read technical articles about DNN and understand them.

創建者 Timothy G

•Jul 15, 2019

This course was very helpful learn so additional information on hyperparameters which help me out at work. Where I was tuning my own and was able to get 88%. After taking this course and implementing what I learned into auto tune my hyperparameters my accuracy went up to 91.33%.