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

学生对 DeepLearning.AI 提供的 Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization 的评价和反馈

4.9
63,489 个评分

课程概述

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....

热门审阅

DD

Mar 28, 2020

I have done two courses under Andrew ng and I am grateful to Coursera for their highly optimised and easily learning course structure. It has greatly help me gain confidence in this field. Thank you.

AM

Oct 8, 2019

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

筛选依据:

1176 - Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization 的 1200 个评论(共 7,283 个)

创建者 Bakyt

Jun 22, 2018

Provides a good understanding how better initialize & make basic fine-tuning of parameter sets as well as a gentle introduction to TensorFlow framework

创建者 Ahmad A

Dec 19, 2017

Very good course, like it. It gave me lot of understanding of what NN is and some background over the hyper params.

I would expect more sessions with TF

创建者 Siamak S

Oct 29, 2017

I think this course is the most import one in the specialization because it gathers a lot of practical tips and tricks to improve deep learning models.

创建者 김희묵

Aug 31, 2024

This course taught me how to improve my models instead of just learning about deep learning. In fact, in some ways, this is the more important course.

创建者 Jeremy V

Jun 12, 2021

very instructive. The only negative point, is that the introduction to Tensorflow is very light and quick. I hope to see more during the next classes

创建者 Bo L

Mar 25, 2021

All the deep learning .ai was set up very organized. Future suggestions would be to make it more academically and look like a university-level course.

创建者 Ishan D

Jun 1, 2020

The course material and assignment is in sync with each other. I like the way it is organized. Thank you to the team for coming up with this offering!

创建者 Yagyesh T

May 18, 2020

Once a legend said that AI is the new electricity and we all know who Nikola Tesla is ! It's always a pleasure of studying all these under Andrew Sir.

创建者 David P

May 18, 2020

I found this course very interesting, incrementally building on previous courses in depth and breath, while preparing me for the Tensorflow framework.

创建者 Densen P

Apr 21, 2020

The video tutorials couldn't be more informative. Loved the programming assignments. Made me realize the importance of doing the work systematically.

创建者 Ned C

Nov 25, 2019

Professor Ng is just an incredible teacher. This is one of the best organized series of courses I've ever taken (including undergrad and grad school)

创建者 PRIYANK U P

Oct 10, 2018

Awesome course! It has open up my thought and approach in deep learning. The professors lectures were awesome and helped me a lot. Thank You Coursera!

创建者 Raed C

Oct 2, 2018

Awesome!.... I'm feeling getting more in shape with this specialization. Andrew lectures and the video series of Heroes of Deep Learning are the best!

创建者 Pathairush S

Apr 17, 2018

This is superb. It teach you to tune the model and focus only important part. it prevent you from wasting the time to learn everything from a scratch.

创建者 Krishna B

Mar 11, 2018

Great course. The lectures are very helpful. And really the course assignments are the best thing. The assignments really helped reinforce the theory.

创建者 Sahil S

Dec 19, 2017

Great Course!!! Gave a lot of insight in tuning the hyperparameters which play an important part in the formation of a formidable deep learning model.

创建者 Melike İ

Oct 11, 2017

Andrew Ng is a great instructor and the lecture material is created

attentively. I recommend this specialization to anyone interested in deep learning.

创建者 Chris R

Sep 20, 2017

Great course, can't wait to work through the rest of the courses in this specialization. The course is a lot of fun and helping me build a new skill.

创建者 Chi H T T

May 18, 2021

Really like Andrew's drawing of the horse (for the saddle explanation) haha, he should do more artistic expression like that when given the chance!!!

创建者 David E C G

Sep 11, 2020

Genial, this course give me a lot of theory and practice of how I can optimize Neural Network's for optimize the train time and get better results.

创建者 indavarapu a

Jul 13, 2020

course was very good. Understood the basics of the most used optimizers. Got to know about batch norm and why it works.Also learned about tensorflow.

创建者 RISHAV D

May 27, 2020

During Batch Normalisation if the Formulas to calculate the gradients of the various parameters were given then it would ave been a great experience.

创建者 Suchir B

May 8, 2020

This is a really good and informative course. It explains the concepts well and also gives one an opportunity to practice and do the work themselves.

创建者 Irvin

Oct 22, 2019

Great course, super motivated that we've started using Tensorflow. I feel like I can start playing around with a personal project to learn some more.