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

4.6
estrelas
13,086 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

PM

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.

BL

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:

2876 — 2900 de 3,043 Avaliações para o Fundações do aprendizado de máquina: uma abordagem por estudo de caso

por Yuliana F N

22 de dez de 2020

Me pareció algo confusa la explicación de los modelos de recomendación, creo que debió ser más clara y y práctica.

por Ajay S

4 de mar de 2019

Good for beginner level, not for intermediate or advance level. I learned more about graphlab than anything else.

por Serban C S

11 de fev de 2018

Using a proprietary library for a paid course is not really a big issue but some people will be turned off by it.

por Pēteris K

23 de set de 2017

Definitely a good intro to the richness of ML, but would have preferred more rigorous assignments and evaluation.

por Luca

10 de nov de 2016

not using scikit and assigment way too easy, not challenging, but high quality video, very easy to understand .

por Pubudu W

10 de jul de 2017

Good survey course on ML techniques. Not very detailed and the exercises are too simplistic for real learning.

por Nguyễn T T

13 de out de 2015

the lectures are pretty great, engaging. the assignments stick with the lab exercise. the forum pretty active.

por ADNAN A G

9 de out de 2020

old and bad quality but very good explanation half of the course is programming there is no machine learning.

por Nebiyou T

7 de jun de 2017

Some of the modules lacked polish and have not been updated since initial recording!

But they were practical.

por Thomas M G

21 de fev de 2018

In my view, too much focus on GraphLab.

This is a problem because GraphLab doesn't seem to be open source.

por Zizhen W

16 de out de 2016

Some instructions of the programming assignments are not all that clear, which wasted me a lot of time.

por Rajdeep G

7 de set de 2020

They should upgrade the course in respect to python 3. Irrespective of that the theory part was great

por Tilo L

20 de mai de 2022

I​ntresting topics get broadly introduced, sadly the course it outdated at a number of occasions...

por adam h

8 de fev de 2016

would vastly prefer if this was taught using sckit-learn and pandas, given their broader use.

por Reem N

23 de jun de 2022

It is very general however it gave me an insight to different machine learning applications.

por Cameron B

20 de abr de 2016

The course is ok, the instruction was very poor for the deep learning section of the course.

por Uday K

1 de mai de 2017

The theories for the models should be explained in more detail and with few more examples.

por Alexander B

4 de nov de 2015

lectures were well done, but the strong focus on using graphlab ruined this course for me

por Naveen M N S

7 de fev de 2016

Decent course. Not very satisfied with the assignments as they are suited for graphlab

por Carlos A C L

25 de jan de 2021

all lectures are obsoleta, and it's neccesary to install a WSL, the rest very well.

por Saket D

28 de fev de 2018

Would have been great if anything compatible with python 3 was used in the course.

por kaushik g

25 de mar de 2018

Content was good but was few years old and things are pacing up a bit these days.

por amin s

29 de mai de 2019

primitive course, didn't expect this low standard from university of Washington

por Rajiv K

20 de jun de 2020

Have to improve for other environment.

have to explain other alternative too.

por Vamshi S G

27 de jun de 2020

i think the course should be updated, graphlab and some other are outdated.