Chevron Left
返回到 Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization

學生對 deeplearning.ai 提供的 Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization 的評價和反饋

4.9
57,409 個評分
6,595 條評論

課程概述

In the second course of the Deep Learning Specialization, you will open the deep learning black box to understand the processes that drive performance and generate good results systematically. By the end, you will learn the best practices to train and develop test sets and analyze bias/variance for building deep learning applications; be able to use standard neural network techniques such as initialization, L2 and dropout regularization, hyperparameter tuning, batch normalization, and gradient checking; implement and apply a variety of optimization algorithms, such as mini-batch gradient descent, Momentum, RMSprop and Adam, and check for their convergence; and implement a neural network in TensorFlow. The Deep Learning Specialization is our foundational program that will help you understand the capabilities, challenges, and consequences of deep learning and prepare you to participate in the development of leading-edge AI technology. It provides a pathway for you to gain the knowledge and skills to apply machine learning to your work, level up your technical career, and take the definitive step in the world of AI....

熱門審閱

AM
2019年10月8日

I really enjoyed this course. Many details are given here that are crucial to gain experience and tips on things that looks easy at first sight but are important for a faster ML project implementation

XG
2017年10月30日

Thank you Andrew!! I know start to use Tensorflow, however, this tool is not well for a research goal. Maybe, pytorch could be considered in the future!! And let us know how to use pytorch in Windows.

篩選依據:

5626 - Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization 的 5650 個評論(共 6,521 個)

創建者 Lester A S D C

2019年6月21日

The course teaches you well on how to optimize your neural network. The only problem I had was with week 2's programming assignment because the grader had problems with the "-=" operation. The lecture I enjoyed the most was the Adam Optimizer lecture.

創建者 Nicolas B

2019年7月24日

This is a very interresting course that go past basic deep neural network knowledge. I learned a lot. Still I would have like a bit more programming exercices to have more part of the theoretical course covered (batch norm, hyper parameters tunning).

創建者 Tanay G

2020年1月26日

This course taught me a lot of new concepts and tricks to speed up the training process as well as ways to reduce overfitting and biasing in a neural network. I would've liked the course even more if the instructors took a deeper dive in frameworks.

創建者 Akshay G

2020年8月11日

I learned a lot in this course but I feel like the assignments should be little big and less informative. The assignments are designed are good for then who are at base level but too short for someone who had their hands on once in neural networks.

創建者 Joao N

2019年11月4日

One again the course is a great follow up from the previous one. The only little detail I wish had been done was for the assignment to cover a scenario where we had to improve some hyperparameters by applying different approaches covered in class.

創建者 戚运动 B Q

2018年4月14日

The course itself is great, but something out of the course is not so good, e.g. I can't see the video easily in China, and also the pictures in the exam can't be shown always, so I must take some guess to pass the exams, which is really a regret!

創建者 Hanan S

2017年12月16日

Not like the first course which was kind of "trying not to touch the details", this course is more organized and I felt I've learned something. Still I would improve TF training to get more into the details (what does reset global variables do?!)

創建者 Davy C

2017年10月2日

Interesting, but the quality of the exercises in not so good. There are at least 3-4 mistakes in the expected output that make you loose time double verifying. Mentor only seems to reply it is know, sounding like it has been like this for long...

創建者 Nacho C

2017年11月9日

It mixes a review of Neural Network tuning techniques, and brief intro to TensorFlow. Those are really two very different topics, but I guess it's just designed to fill about a month of the specialization.

NOT recommended as a standalone course!

創建者 杨鹏程

2018年7月3日

This is a very good course, but the content of the hyperparameter adjustment mostly stays in the theoretical analysis. The latter experimental course does not involve how to implement the program. I hope that it will be improved in the future.

創建者 Martin K

2017年12月13日

Great course. I learnt a lot again. Perhaps the programming exercises can be a little harder. Some things were quite literally spelled out which meant that you could theoretically copy/paste them into your code with only trivial adjustments.

創建者 Mihajlo

2018年2月1日

I liked the optimization lectures, and Andrew's style of teaching. Anyway, I feel that I didn't learn enough in this course, and that it is not on the same level of previous courses we got used to, like the original Machine Learning course.

創建者 Faisal A

2018年8月11日

This course was better than the first course in the specialization. The assignments were more sophisticated (though repetitive at times) and required more thought and work. The only down side is the monotone way of presenting the material.

創建者 Prashant M

2017年10月25日

Some lectures seem to have inconsistent/unexplained differences in the math written. For example, I am a bit confused as to whether normalization is done as (x - mean)/variance or (x - mean)/std.dev. Otherwise, excellent content as always!

創建者 Tianyi L

2017年11月19日

In overall, the course content is helpful and inspiring as normal, and can be used to real life straight away. However there are several typos/mistakes in the assignment, especially in assignment 3 which I had bad time to experience with.

創建者 Rahul K

2018年7月24日

The best course in deep learning: Hyperparameter tuning, regularization and Optimization. The course is best among all the available courses over internet but it lacks availability of study materials (or reference to reading materials).

創建者 Jairo L D A

2018年4月24日

Very good content. Professor Ng covers a lot of material in a gentle and steady way. A few errors in the assignment and less clarity on some texts and quiz make me give 4 stars, but overall it's a very useful, important course, I think.

創建者 Jason A B

2017年9月30日

Great course for in-dept understanding of parameter tuning and optimization, +tensorflow. I would recommend increasing the complexity of the programming assignments. At this point we should be controlling more of the basic python setup.

創建者 Giordano S

2017年9月28日

Maybe not as exciting as the first course of this series (Neural Networks and Deep Learning) as this one delves more in the "technicalities" of NN. The presentation of the topics, however, is always very clear and easily understandable.

創建者 srinivasan v

2018年1月8日

Struggled a bit to grasp the batch nomalization, Initially Regularization was also hard to grasp the first time, subsequent viewing made it clear though but batch norm still is a bit hazy. I am happy though we are in to Tensorflow now.

創建者 P.C. C

2021年2月27日

The material was excellent for this class and so were the lectures. I think more programming assignments could have been optimal though. There are so many concepts, and I think there are several pieces we didn't implement in practice.

創建者 Tristan C

2020年4月4日

There were still a few times where I felt some clever editing could have hidden math errors but I felt the second part was already more polished and accessible than the first. I hope the rest of the series continues in this direction.

創建者 daniele r

2019年7月15日

One of the best and most technical course in this Specialization: I enjoyed learning a lot on optimization algorithms. Really good practical hints on tuning and on bias variance analysis, that are very difficult to find in textbooks

創建者 Anwesh J

2020年7月18日

Indeed this is an awesome course for any beginners in deep learning.One suggestion could be is why you have selected Tensorflow framework.Will it be possible to get same assignment in Pytorch framework which out institiute follows.

創建者 Charles S

2017年11月24日

This course was excellent, however the Tensor flow at the end feels a little bit like the ML field is quickly being overtaken by the frameworks, and the Tensor flow section is a little bit tacked onto this course, maybe in a hurry.