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

56,647 個評分
6,498 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....



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


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.


5826 - Improving Deep Neural Networks: Hyperparameter Tuning, Regularization and Optimization 的 5850 個評論(共 6,429 個)

創建者 Mads E H


Nice and practical. The assignments could go a step further in trying out different things to get better results.

創建者 Zechen Y


The contents are explicit and adequate but I think It would be better if I could get more exercise about coding.

創建者 Jayanthi A


It was great course, however, I would have liked it to be a lot slower with more time being spent on Tensorflow.

創建者 Johannes C d M


Very well explained, but the Tenserflow explanation is shallow for those that have less programming experience.

創建者 Dilip V


This Course Helped me a lot in learning how to get best-optimized models by tuning Hypermeters.I really like it

創建者 Joshua S


A good course that provided more intuition on which models to work with and how to tune parameters effectively.

創建者 Aayush A


The Jupyter notebooks had a lot of mistakes which wasted a lot of my time otherwise the course content was good

創建者 Corbin C


Good lectures, but the jupyter notebook examples are inconsistent and sometimes use deprecated Tensorflow code.

創建者 Srikanth C


I particularly benefited from the explanations of dropout, batch normalization and the RMSProp/Adam optimisers.

創建者 Narendran S


TensorFlow needs more time dedicated to it. I didn't completely understand the concepts behind this framework.

創建者 Arun J


really loved the course material but would have loved it more if it gave more in depth tutorials on tensorflow

創建者 Hector D M P


Nice and clean; with nice focus in the framework; but they also could be more in depth regarding the exercises

創建者 Shailesh


Really helpful in terms of practical application and tricks/tuning for DNN. Also starts on TF which is bonus!

創建者 Raman J M


Quizes as part of middle of lectures help to check the understandings. For many lectures quizzes are missing.

創建者 Pabbisetty S R


explanation is very good but assignments need to be done comletely by student not like filling missing parts

創建者 Rohit G


The tensorflow portions need to be updated. Otherwise it's a great module, building on the previous courses.

創建者 Yunhao Z


-1 : Serveral bugs inside the assignments, causing 0 grades in auto grader

That said, a perfect intro to DNN.

創建者 Qihong L


sometimes the teacher speaks too fast to follow, but the content itself is very good and easy to understand

創建者 Gustave G


Very good videos but programming exercises are way too easy and some written material would be appreciated.

創建者 Donguk L


Maybe providing some video or reading resource for back propagation processes for batch norm would be good?

創建者 Parjanya P P


The answer in the last assignment was wrong, wasting a lot of my time. But otherwise the course was great.

創建者 Aaron E


its a good intro, if not a little simplistic with the coding exercises, bring back the quizzes mid lecture

創建者 Oleksiy S


A small validation output error that is still not fixed prevent to rate all stars for the exellent course.

創建者 苑思域


This one is actually a little bit better than the first one, maybe less content, maybe more understandable