Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization(으)로 돌아가기

4.9

별점

50,728개의 평가

•

5,725개의 리뷰

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....

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.

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.

필터링 기준:

교육 기관: Mojtaba H

•Feb 11, 2020

It covers very good tips and tricks to build and enhance deep learning model.

Andrew is the best teacher for ML and Deep Learning, he covers all theory and practice simultaneously.

In this course you can understand all mathematical intuitions and implementation of neural network from scratch by your own codes.

교육 기관: Juan C B

•Mar 08, 2020

Good second course to understand how we can improve our deep learning models with a good hyperparameter selection, some regularization techniques to reduce overfitting such as dropout, l2, early stopping and some optimization techniques for when we have a large datasets like momentum, RMS prop, adam, etc..

교육 기관: Rob v P

•Oct 02, 2017

This second course in the specialization is really great. I have gained a lot of insight in hyperparameter tuning and the reason why they work (or don't ;-). It is much easier now to understand what models are doing and why we need certain techniques. This is again one of the best courses for deep learning.

교육 기관: Abdallah D

•Feb 03, 2020

Fantastic course providing a broad overview of hyperparameter tuning in deep neural networks. The introduction on TensorFlow is informative. Looking forward to the three remaining courses of this great specialization on machine leaning. Thanks Andrew and their assistants for putting those courses together!

교육 기관: Daniel R B

•Jun 06, 2018

I really liked the course. The forum is very helpful navigating programming errors during the assignments.

A thing to improve would be to get the feedback from the forums to the lectures. Specially in corrections that should be made to the programming assignments that don't match the expected result. Thanks

교육 기관: Steve S

•Dec 11, 2017

Provided a lot of deeper insights passed over in the previous course in the specialization. Between this course and the previous course, you feel like you have a very solid beginner's understanding of deep learning, but one that is also practical enough and comprehensive enough to start coding on your own.

교육 기관: Marcin G

•Oct 15, 2017

Andrew Ng is a great teacher and will get you excited about improving deep networks. In this course you will get to know how to increase performance of your network. Essential course for deep networks specialists and amateurs. Additionally you will get to know most influential people befind the technology.

교육 기관: Shashank S S

•Jul 08, 2019

All possible area of Improving Deep Learning models got covered in detail. I liked the lucid and intelligible way of explanation . Since the topics were vast to cover , I would recommend to get the course extended by 1 week with one more programming assignment on using tensor-flow with a capstone project.

교육 기관: Vincenzo M

•Sep 11, 2017

This course will becoma a foundamental course for people that aim to work in the machine learning / deep learning area because it presents clearly the recent innovations in the deep learning. For production environment people will probably use open source framework, but this course clarify what is behind.

교육 기관: JOSHY J

•Oct 03, 2019

Excellent course if you are passioned about Deep Learning. Walk you through the most basics on how to tune the model parameters so that you can reach the highest accuracy for the model. The lecture is simple and well ordered. The TensorFlow introduction part is more exciting. Overall a wonderful course.

교육 기관: Dimitrios L

•Feb 18, 2018

Excellent course! Not only does it address critical deep-NNs training issues providing a clear exaplanation around why these tunings are needed, but also provides some empirical advices (e.g. on level of importance on the hyper-parameters, typical values etc) that can be valuable when training depp NNs.

교육 기관: Aaron B

•Oct 28, 2018

The only thing I wish for is a 'live chat' when an instructor is available, a IRC/slack/chat room for students to help each other, or faster response time when posting to the forums. Also the forums are a bit clunky (I don't remember all the reasons why), but the search allowed me to find useful posts.

교육 기관: Shashank M

•Oct 10, 2018

This course offers a very quick introduction to methods that could be used to improve usage of deep nets from a practitioner's perspective. Although the mathematical details are not covered in depth, the material furnishes concise list of topics that could be researched upon for in-depth understanding.

교육 기관: Sachin G W

•Dec 11, 2018

Amazing course, starts right off the bat with hyperparameters, regularization and tunings.

Studied about various optimization algorithms and normalization alongwith mini batches, also the TensorFlow framework.

Thank you to everyone involved in making this course. I highly appreciate what you've made us.

교육 기관: Muhammad s k

•Dec 03, 2019

I always held an opinion that highly qualified instructors, specifically those holding doctorate degrees are not the good teachers because they can't teach students at their levels. But Sir Andrew Ng proved me wrong, he is a wonderful teacher and tries to explain the minute details.

Salute to you sir.

교육 기관: Edoardo S

•Jan 20, 2019

Very impressive course, really well done and interesting. One suggestion: apart from the modelling part in the programming assignment, I would also introduce some coding about the computing of the results and the final cost plot (in all the programming assignment these parts are already pre-compiled)

교육 기관: Shabie I

•Feb 18, 2018

Concepts buried deep in technical jargon and seemingly complex mathematical notation are laid out bare for everyone to understand.

Mr. Andrew Ng is a very special teacher. The humility and down-to-earth character also add immense value to the course. He makes you believe truly that you too can do it.

교육 기관: Brandon E

•Sep 26, 2017

An excellent continuation of the series. I particularly liked the in-depth discussion of Adam's optimization and the introduction to TensorFlow at the end of the course. The course does a great job of targeting specific concepts with practical advice related to tuning and optimization on real models.

교육 기관: Kwan T

•Sep 28, 2017

It is amazingly rewarding to learn from Andrew, who is able to articulate so much insights into so many complicated refinements of Deep Neural Networks from so many different research papers. The Tensorflow programming assignment is one of best tutorials I have seen. Thank you for your great effort.

교육 기관: Zhiming C

•Apr 18, 2020

A very good organize course! The knowledge is step by step introduced. From Python can one from scratch a learning code establish. And then the course turns into Tensorflow. Only with this method can man have good feeling about how Tensorflow is processed. Very good course, I strongly recommend it!

교육 기관: Benjamín M

•Apr 19, 2020

Concepts very well introduced and explained, with really good explanations about the intuition behind every topic. It's perfect to be able to apply different techniques knowing what they are good for and when to apply them, and at the same time it also shows where to delve deeper if needed/wanted.

교육 기관: Nityesh A

•Oct 08, 2017

Andrew Ng gives a good satisfactory explanation of the techniques covered in this course. He explains when to use the technique, how to use the technique and how one can implement it in Python and then goes on to give an intuition behind it. I think it should work well for newbies (worked for me).

교육 기관: Tejaswini

•May 25, 2020

I've really enjoyed this course. It gives you a great deal of knowledge and I recommend this to anyone who wants to get an intuition of how to optimise, regularise and perform hyper parameter tuning to make your model learn efficiently. The variety of topics and depth offered was good. Thank you.

교육 기관: Rujuta V

•May 18, 2020

This was an extremely informative course which provided an in-depth knowledge of how Hyper-parameters of Neural Network affect the results and methods of tuning those parameters from improving results. The Programming Assignment provides deeper insights of applying the taught methods effectively.

교육 기관: Gary N

•Mar 05, 2020

This course adds to the first with what you need to make models perform well and fast in practice. Each part of the learning process has possible tuning, tweaks, optimizations to improve performance. The material explains why each tweak works, at least at an intuition level. I have learned a lot.