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

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

57,892 個評分
6,657 條評論


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....



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.


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.


6476 - Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization 的 6500 個評論(共 6,582 個)

創建者 Ignacio L


dint like that the tensor flow that we used for the lab is an old one. Specially after I did the tensorflow specialization , the old version is nothing like the newer one.

創建者 John D


The content was solid, but some of the labs seemed a bit buggy (getting full credit even though my code didn't run). I also wish the TensorFlow tutorial used TensorFlow 2.0

創建者 Debjit G


The course was amazing as expected. But the quality of videos needs improvement. Also if programming part was explained in the videos then that would be great. Thank you.

創建者 Sagar B


Too many issues with the auto grader system. Need to improve the know errors and save the time pf users. I spent more than 3 hours total just to fix the grader bugs.

創建者 Yogeshwar j


It could have been more detailed and interesting. Compared to the first course of the specialization, This course's material didn't clear all the concepts clearly.

創建者 Madhur S


Great course for a beginner like me. I wish however that sizing of hidden layers/units should have been addressed as it is very difficult to achieve the optimum

創建者 Aniruddh B


Docked one star because of using Tensorflow 1.4 instead of 2.0. Docked another star because I found the course content less interesting than the first course.

創建者 Kishore K


Some of the videos are very abstract and needs a bit of mathematical intuitions. These intuitions are best obtained by calculations rather than a lecture :)

創建者 Yazid H


A bit too theoretical for my taste, lacks practical homework and getting our hands dirty. Really appreciated the final week's structure and topics.

創建者 harmouchi m


ike usual andrew ng perfect explanation simple go to essential stuff.

the minus points some troubles with notebook

big thanks for andrew ng's team.

創建者 Marco B


There are errors on some exercises (adam of week 2) still unsolved after over 1 year (found same error reported on the forum/discussion)

創建者 Christian K


The lecture videos are good but the assignments are not that useful as they provide th answers within them and are somehow repetitive.

創建者 Pavel K


Lectures are good. Programming exercises are too easy. Too mechanical, no much thinking required, à la "fill the gaps" exercises.

創建者 Rupamita S


I would give five starts if not for that grade error issue. I hope it gets resolved for good. Otherwise. Great course as usual.

創建者 Carsten B


Interesting, but not nearly as good as the first one. Disjointed topics, unconnected exercises made this less digestable.

創建者 Tan K L


I think more should be done regarding the TensorFlow framework with more explanations given to what the functions did

創建者 Moustafa A M


Lake of practice, Lake of intimations with good examples

Less in Ternsorflow don't know how to implement and deploy it

創建者 Mohammad E


The course and the material are great. However, the codes in the labs have serious problems which should be solved.

創建者 Lucas N A


Really helpful advises. I felt it was too focus on the implementation side but I liked the intuitions parts better.

創建者 Rishabh G


Week 3 of the course does not have a practice problem for batch normalization. Wanted to implement it and learn.

創建者 Ramachandran C


I found the video lectures useful to understand the concepts, but the programming exercises are over-simplified.

創建者 Carlos V


Would give more stars if the final assignment used Tensorflow@ and not an outdated version that is not in use.

創建者 Pranshu D


More tensorflow related tutorials should have been there. The lectures turned a little boring and redundant.

創建者 Adrian C


So far, I think this course is weak on theory, seems rushed and should provide more in depth lecture notes.

創建者 Vincent D W


Encounter Error in the final assignment, cannot complete the model, but the grader gives 100/100 anyway.