Chevron Left
Voltar para Fundações do aprendizado de máquina: uma abordagem por estudo de caso

Comentários e feedback de alunos de Fundações do aprendizado de máquina: uma abordagem por estudo de caso da instituição Universidade de Washington

13,204 classificações

Sobre o curso

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....

Melhores avaliações


18 de ago de 2019

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.


16 de out de 2016

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

Filtrar por:

101 — 125 de 3,063 Avaliações para o Fundações do aprendizado de máquina: uma abordagem por estudo de caso

por Adrian M

25 de set de 2021

The good part is the very good and simple introduction of ML concepts, which are assesed during quizes. It makes you thinking and understanding the concepts of ML.

The less good part - the course should be updated in such way that video material fit the assignments. The usage of graphlab during presentations and turi create during assignments is not a good way to ensure complete understanding of materials.

The recording conditions were poor sometime ( police sirene or landing plane can be heard ). Some URL links on readings before quizes are not working and one assignment still has wrong answer considered as correct even the students posted clear messages toward mentors months ago.

por Ghassan M

11 de nov de 2021

Generally speaking the course is well taught and exposes the student to introductory level concepts in machine learning. My problem with the course is that it promotes the Turicreate machine learning library. For one thing, this library is not supported on windows. For another, the vast majority of machine learning professionals use an assortment of Tensorflow, Keras, PyTorch, etc... It would have been more proper to use one of those libraries.

por Jaime R

17 de dez de 2018

Great introduction course. However, getting the notebooks to work with Graphlab is a real pain. The notebook exercises are also mostly make-work rather than real explorations. The explanations and the notebooks themselves are pretty good though

por Ezequiel P

7 de nov de 2020

Excellent Theory. Very clear explanations with simple yet powerful examples. Sadly the practical part is not nearly as good. Mainly because of the tool used. If this was implemented in Scikit-Learn, the course would be excellent overall.

por Ayush G

5 de jun de 2020

the course seems outdated in many aspects, the support isn't available to clarify doubts and the documentation isn't updated either. Moreover, the software support has ended.

por Cranchian P

22 de mar de 2022

There are still many errors and corrections to be made in practical application part and reading parts.

The conversion from graphlab to turicreate is not complete at all.

por Nouf A

26 de mai de 2022

some of the video content is old, and some of python functions explained gives errors as it have changed and command is updated

por Jefferson N

13 de fev de 2019

A good course, but the tools are a bit dated and it's showing its age.

por Seong H M

25 de set de 2021

Problems and files and videos not updated base on the changes

por Himanshu R

16 de abr de 2020

It uses turicreate which is not available for windows .

por Faik N

14 de jan de 2022

A lot of good info but the code they used wasn't the same as the code in the notes (e.g. Graphlab vs Turicreate) which was confusing. In the last quiz they had us build models to find the knn cat to a specific cat photo that was supposed to be the first in the image dataset. Unfortunately that photo was no longer in the dataset so I did the code just to learn it, then I had to eyeball guess which of the quiz options matched their cat photo the most closely. In the fourth quiz we were expected to do coding that was never presented in lecture, and the documentation they linked to was bad. With regular python documentation I'm able to learn how to code in new ways because they give examples. Not so with the turicreate documentation. Another issue was that in one of the quizzes they threw in the vaguery of normalizing to either 0 or 1 in a neural net logic gate question. I found two correct answers where one normalized to 0 and the other to 1 yet was still marked incorrect. Online courses will eventually replace in-person classes but not when they're so filled with errors and students are unable to clarify these errors with faculty. The learning process itself can't progress efficiently because it's unclear if we're wrong because we require more learning or because the information presented has errors or is in a different format. The most frustrating class I've ever taken.

por Craig G

5 de ago de 2020

It is interesting, but turicreate isn't compatible with current version of python (3.8) and there's little/no support as the forum is not curated and not much student interaction. The problems seem to be only loosely related to the material. Many questions in the problems aren't discussed in the lectures and turicreate isn't widely used so it is difficult to find explanations or clues on how to proceed.

por Farid A

29 de ago de 2022

Very good course with detailed teoritical explanations but the assignments are quite outdated since nowadays "in 2022" people normally use Pandas and scikit-learn for ML instead of library used during this course!

I highly recommend the instructors to update the course material to match it with new tools used in today's world!

That lady was quite educated and explained stuff very well!

por Waqar H

31 de mar de 2020

I think this course is outdated as they are using python 2 also the platform they use for machine learning only supported by python 2. Due to these limitations, I too was unable to continue this course. Because every time you have to work with new libraries you have to uninstall python 2 and reinstall python 3.

por Aravind R

28 de dez de 2015

Instructors or TAs are not available in discussion forums. and the course is focussed on promoting "graph lab" proprietary package of the course sponsor. Maybe you can have a look, not beneficial if you are serious about learning ML.

por Ujwal A

27 de mar de 2020

This course has used windows OS and application built for it. But the library/application is no longer supported on windows. So this is really a big problem for windows users.

por Joseph C

29 de jul de 2018

Overly relies on a paid software (free for the course) called GraphLab. The course can be completed without GraphLab, but expect little / no responses to questions.

por Kishore Y

25 de set de 2021

This is a good idea to use the case study approach. However, there are issues with files and program setup that stopped me from continuing with the course.

por De V d P

13 de mar de 2022

outdated nightmare to get started. unusable practicals outside of learning sand box.

por Jason S

24 de ago de 2021

great professors, great setup. Just extremely outdated software is used.

por Daniel J

7 de jan de 2017

excessive use of GraphLab create which is not an industry standard.

por Jianfeng G

28 de mai de 2022

Well designed, but too outdated. No learning support at all.

por Keith P D C

28 de out de 2019

Two stars because of GraphLab! Otherwise great concepts!

por Keneshia E

7 de jun de 2022

This is out of date. I cannot get week one to work.

por M D 1

27 de fev de 2022

This course defenitely needs a major overhaul. While both the Lecturers did an amazing job in handling lectures, the programming assignemets were a nightmare to me. For instance, this course was designed in python 2xx and used certain libraries that were once accessible to everyone. However, they are now propreitry and cannot be accessed witout buying them. So had to use packages like pandas and numpy in python 3xx. So anyone thinking of doing this course, make sure u have adequate support using these packages in python 3xx. Defenitely not a course for beginner.