Chevron Left
Retour à Apprentissage mechanique pratique

Avis et commentaires pour d'étudiants pour Apprentissage mechanique pratique par Université Johns-Hopkins

4.5
étoiles
2,846 évaluations
539 avis

À propos du cours

One of the most common tasks performed by data scientists and data analysts are prediction and machine learning. This course will cover the basic components of building and applying prediction functions with an emphasis on practical applications. The course will provide basic grounding in concepts such as training and tests sets, overfitting, and error rates. The course will also introduce a range of model based and algorithmic machine learning methods including regression, classification trees, Naive Bayes, and random forests. The course will cover the complete process of building prediction functions including data collection, feature creation, algorithms, and evaluation....

Meilleurs avis

JC

Jan 17, 2017

excellent course. Be prepared to learn a lot if you work hard and don't give up if you think it is hard, just continue thinking, and interact with other students and tutors + Google and Stackoverflow!

AD

Mar 01, 2017

Issues of every stage of the construction of learning machine model, as well as issues with several different machine learning methods are well and in fine yet very understandable detail explained.

Filtrer par :

326 - 350 sur 530 Avis pour Apprentissage mechanique pratique

par Charles W

Dec 08, 2019

I think some material might need to be revised, but I thought it was very interesting to see everybody's model building code (and perhaps that can also help me in the future).

While it is mixed with other notes, I have more detailed thoughts in this blog post: http://cdwscience.blogspot.com/2019/12/experiences-with-on-line-courses.html

par Jorge E M O

Sep 07, 2018

The course rushes over a lot of concepts and it already shows its age - however, it's a pretty solid introduction to machine learning from a practical perspective. It will provide you with a lot of ideas for further investigation and exploration and in the end you'll end up with a wide vision of the machine learning process.

par Brandon K

Mar 30, 2016

The lectures were great and engaging. I felt like they went too fast. Jeff says at the beginning that this is just an overview and points to some other resources. As an overview, this class works well. You can expect to learn a bit about what machine learning is and how to to do it using the caret package in R.

par Oliver S

Jul 26, 2019

A reference solution for the quiz questions as there are in some other courses in this specialization would have been nice, since I got sometimes very different results using the newest versions of the libraries and I'd really like to know, if I made any big mistakes and it's not only because of my setup.

par Lukas M

Oct 06, 2017

The lectures are very good to get the basic knowledge about machine learning. One suggestion is that the lectures can be longer, covering more detailed stuff and a little bit more advanced materials. Moreover, some codes are not explained clean and clear for me. Hope it would be better in the future.

par Robert S

Sep 16, 2019

The lecture material is great, but the quiz material is in need of updating. R and it's packages have gone through many updates since the problems were written so it is sometimes difficult to reproduce their results even with running the sample codes given after getting the answer correct.

par Lucas

Jun 03, 2016

This course allows you to implement practical solutions using machine learning algorithms without having to know the mechanisms behind the calculations in detail. Unfortunately questions in the discussion forum were quite rare and many questions were not resolved during this course.

par Swapnil A

Jun 09, 2017

The course covers few important topics in R like cross validation, decision trees, random forest etc. which comes in very handy for a data science aspirant. It expects the participant to have a descent knowledge in R. Overall, I am pretty satisfied with this course. Thanks!

par Simon

Oct 25, 2017

This course is brief but it has the 2 best ingredients for having a really decent first step in Machine Learning:

1) It covers a broad group of different algorithms

2) It provides reference material for those in which you want to get deeper.

Really good job in this course.

par Yuriy V

Mar 10, 2016

I liked the course and found it informative, but wish there were more stuff on unsupervised learning neural network algorithms (SOMs). Learning about most used algos are great, but would also like to know other machine learning algos that are used concurrently.

par Marcus S S

Feb 25, 2017

Great course! The hands-on approach make it very useful for one to start doing some very interesting analysis in real life! Thanks a lot! You guys could only make some efforts in updating some classes and packages used in quizzes. But the rest was great!

par Rohit P

Nov 13, 2016

Lectures were not very detailed.

Quizzes were good and challenging, but too many times the results didn't match the answers even when the random seed was set right

Final project should have been more challenging with more models to build and compare

par Subrata S

Mar 09, 2017

Very good course. The content can be enriched with some more technical details behind the various techniques. There needs to be 1 more course on Practical Machine Learning in the specialization as 1 course is far too less for such a vast topic.

par Samuel Q

Oct 24, 2018

Good course to get only the basics of machine learning. The assignments and quizzes are great but the lecture material is very brief and short. The references provided throughout the lectures are probably the best source of more information.

par Robert W S

Nov 22, 2016

Great intro to machine learning. Several algorithms with some ideas on sampling and pre-processing techniques are covered. Adding a textbook as done with some of the other data science classes would help, but other resources are referenced.

par Sabawoon S

Sep 14, 2017

Excellent course, very practical. Found the project challenging as preprocessing data required some knowledge of the limitation of the RandomForest method i.e. both train and test needs to have same classes of data with similar levels.

par Kalle H

Jun 25, 2018

Nice course that tries to fit a lot of material into four weeks. Due to this, the material is not so deep, although pointers are given to where the student can find additional information related to each subject covered by the course.

par Kamran H

Feb 18, 2016

Pretty good overview of how to build some types of machine learning models through the caret library in R, but not much in terms of the theoretical underpinnings or why one method is better than the other or where it is most suitable.

par Brynjólfur G J

Sep 25, 2017

Some problems with current and old versions of packages and problems with using other packages on different operating systems. Though that did also help foster an independent research style which will help me in the future.

par Chonlatit P

Oct 20, 2018

GREAT course! There are all base of machine learning field. The limitation is blur between basic and detail especially maths. This course, sometimes , show the maths that make you confuse if you're not familiar with them.

par Emily M

Mar 12, 2018

This course gives an overview of a broad subject. My personal feeling is that there could have been some more indepth examples/case studies to demonstrate how to apply these methods and analyse /interpret the outcomes.

par Orest

Jan 22, 2018

It needs more mathematical detail. Otherwise is a fairly comprehensive class, and a great tutorial on the caret package. I recommend it, if you need to refresh concepts and get some practical exposure to caret.

par Bruce I K

Oct 20, 2016

It's a great course but I hope you add a few things. The course about the machine learning algorithm is so basic. Please get deep into the machine learning algorithm. Then it would become the perfect course.

par Aashaya M

May 29, 2016

In my opinion this course is highly technical and demanding in nature compared with the others. The learning experience is good and coursera.org has given a opportunity for customization ! thank you Coursera

par Paul K

Apr 08, 2017

Very good summary of strengths/weaknesses of various machine learning algorithms. This lecturer's style and production quality is much higher than in the previous two courses in the specialization series.