Chevron Left
Вернуться к Machine Learning Foundations: A Case Study Approach

Отзывы учащихся о курсе Machine Learning Foundations: A Case Study Approach от партнера Вашингтонский университет

Оценки: 13,206

О курсе

Do you have data and wonder what it can tell you? Do you need a deeper understanding of the core ways in which machine learning can improve your business? Do you want to be able to converse with specialists about anything from regression and classification to deep learning and recommender systems? In this course, you will get hands-on experience with machine learning from a series of practical case-studies. At the end of the first course you will have studied how to predict house prices based on house-level features, analyze sentiment from user reviews, retrieve documents of interest, recommend products, and search for images. Through hands-on practice with these use cases, you will be able to apply machine learning methods in a wide range of domains. This first course treats the machine learning method as a black box. Using this abstraction, you will focus on understanding tasks of interest, matching these tasks to machine learning tools, and assessing the quality of the output. In subsequent courses, you will delve into the components of this black box by examining models and algorithms. Together, these pieces form the machine learning pipeline, which you will use in developing intelligent applications. Learning Outcomes: By the end of this course, you will be able to: -Identify potential applications of machine learning in practice. -Describe the core differences in analyses enabled by regression, classification, and clustering. -Select the appropriate machine learning task for a potential application. -Apply regression, classification, clustering, retrieval, recommender systems, and deep learning. -Represent your data as features to serve as input to machine learning models. -Assess the model quality in terms of relevant error metrics for each task. -Utilize a dataset to fit a model to analyze new data. -Build an end-to-end application that uses machine learning at its core. -Implement these techniques in Python....

Лучшие рецензии


16 окт. 2016 г.

Very good overview of ML. The GraphLab api wasn't that bad, and also it was very wise of the instructors to allow the use of other ML packages. Overall i enjoyed it very much and also leaned very much


18 авг. 2019 г.

The course was well designed and delivered by all the trainers with the help of case study and great examples.

The forums and discussions were really useful and helpful while doing the assignments.

Фильтр по:

76–100 из 3,064 отзывов о курсе Machine Learning Foundations: A Case Study Approach

автор: Peter F

30 мар. 2020 г.

This course would be okay if it weren't for turicreate, a Python package that's supposed to simplify things. If you have Linux or a Mac, it will do just that, but if you have Windows steer well clear of this course. The lecturers haven't considered the possibility that anyone might not have Linux or a Mac. All the faffing around getting turicreate to work (I did it once and I'm not doing it again) wasn't worth my trouble so I ended up guessing the answers to the quiz questions (you're allowed three attempts every eight hours) just to get this course out of the way. I'll use something actually accessible for the remaining courses, namely R.

автор: David Y

3 окт. 2021 г.

Content is not updated, 3 years old, they tell you that the course will cover TuriCreate but all the videos show GraphLab content. Syntax is for Python 2, and although this last one is not supercomplicated it shows the lack of interest for the students from the University because after 3 years they haven't updated the content!

Go to the forums and see how many people are stuck in Week 1, just trying to install the tools requested, which require plenty of workarounds to be installed in windows.

автор: Rithik S

26 мая 2020 г.

The files that are given in readings are unable to open and turicreate cannot read that files also. I cant complete my assignments without reading those files. They haven't given any detailed explanation about how to read those files. In videos they had explained through csv files but in assignments they had given sframe file which are unable to read

автор: Yakubu A

23 дек. 2020 г.

The learning tools and environment is not friendly. The use of graph lab seem outdated since python 3.7 does not seem to support the module. I suggest the course be reviewed. Python 2.7 seem to be going out of the system so something should be done about this

автор: ye

31 янв. 2021 г.

The course is limited to use special package - turicreate, sframe, no detailed explanation of how to install that. Packages used are very out dated

автор: Jitendra S

29 апр. 2016 г.

Dato tool does not even install properly.. so n´makes no sense to continue with the course. The support team fail to help in installing ... :-(

автор: Ashutosh N

30 мая 2020 г.

The course is explained using turicreate , which does not work in windows properly. It should have been explained using open source libraries.

автор: Krupesh A

15 февр. 2019 г.

Uses very old versions of libraries. Many students are facing issues which remains unsolved. Not recommended to pursue it.

автор: Rolando J R I

14 февр. 2022 г.

They are using python 2, It is very out-of-date.

After the first week, I count not pass the first test...

автор: Shreyash N S

20 мая 2020 г.

graphlabcreate creates many problem while should be changed

автор: Japman S

6 июня 2020 г.

Based on Python 2 libraries not working on python 3. Obsolete Course

автор: YM C

6 сент. 2019 г.

Too old, bad packages, not much to learn. too basic.

автор: Darren R

13 окт. 2015 г.

Thoroughly disappointed to see this course based on

автор: Kaushik M

1 мая 2016 г.

Too many videos and not cluttered assignment codes

автор: D. F

2 февр. 2021 г.

Out of date material. Poor instruction

автор: Rohit

19 апр. 2020 г.

This course is pretty good for beginners. All domains are explained briefly as an introduction. The best part about this course is very good hands-on sessions which are really helpful to understand concepts. The course is not very detailed but it's very good to start with. Looking forward to quality courses ahead in this specialization.

автор: Shibhikkiran D

13 апр. 2019 г.

This is course is very informative for a beginner. It helps you to get up and running quick provided you have little basics on Python. You should( sideline on your own interest) also pickup Statistics/Math concepts along each module to make a rewarding experience as you progress through this course.

автор: Diogo P

15 февр. 2016 г.

With a funny and welcoming look and feel, this course introduces machine learning through a hands-on approach, that enables the student to properly understand what ML is all about. Very nicely done!

автор: Karthik M

27 дек. 2018 г.

A good course to understand the basics of Machine Learning. The only issue is the use of Graphlab library. Since it only works on Python 2.7, it is not convenient for people who prefer Python 3

автор: Alexandru B

21 янв. 2016 г.

Great course. Very informative and inspirational. I got tons of ideas from it! Thank you

автор: Mallikarjuna R V

17 янв. 2019 г.

Wonderful opportunity to learn and execute hands on coding of Machine Learning. The amazing task that Machine Learning methods and algorithms does behind scene is understood for the following cases / intelligent applications:

1. Regression (e.g. Predicting House Price etc.)

2. Classification (e.g. Product review sentiment, Spam detection, Medical diagnosis etc.)

3. Clustering and Similarity (e.g. Grouping news articles)

4. Recommender (e.g. Amazon personalized product recommendations, Netflix personalized Movie recommendations etc.)

5. Deep Learning and Deep Features (e.g. Google image search, Image-based filtering etc.)

The main challenge for me was to code using “Python3, Pandas and SciKit-Learn” instead of “Python2, GraphLab Create and SFrame”. I am now confident to develop intelligent applications based on Machine Learning. Thanks to Professors (Emily and Carlos) and to Ashok Leyland-HR for giving me this opportunity.

автор: Sundar R

19 авг. 2020 г.

The teaching is of good quality and the lectures are easy to follow along. The only downside I thought was week 6 where I felt the topics weren't covered in enough detail in order to clear the quiz. Lastly, very disappointed by the exclusion of courses 5 and 6 which would've made this specialization a complete package.

автор: akashkr1498

18 янв. 2019 г.

lacture was good but one point i want to share to you don't use rare tools for assignment personally i faced lots of problem while installing graphlab better to switch to some common tools like sklearn python platform .

автор: Yuvraj S

1 февр. 2019 г.

It is a good course if we take into account the foundational part. But since only one library has been used to solve the issues, one does not explore and write their own functions.

автор: Sijith K

5 авг. 2021 г.

The course is good. Very well taught. The issue is with Turicreate. Im not sure why we have to use Turicreate. Looks like its being promoted. Thats ok, but the real issue is installing it. I lost nearly a week on that. To figure out what to do and how to use it. It was so frusterating to start the course like this. But then, I found a solution in the discussion forum by Thet oo Zin, who has converted all the SFrames that can be used in Google Colab. That was helpful.

Then, many commands are in Turicreate. After this course I have to go figure out how those commands are written outside of Turicreate. For example:

1 - Load_Data = turicreate.SFrame('path of dataset')

2 - knn_model = turicreate.nearest_neighbors.create(x, y, z)

But the course is amazing, interesting and easily understandable for a newbee to python/ML like me.