Chevron Left
Voltar para Launching into Machine Learning

Comentários e feedback de alunos de Launching into Machine Learning da instituição Google Cloud

4.6
estrelas
4,172 classificações

Sobre o curso

The course begins with a discussion about data: how to improve data quality and perform exploratory data analysis. We describe Vertex AI AutoML and how to build, train, and deploy an ML model without writing a single line of code. You will understand the benefits of Big Query ML. We then discuss how to optimize a machine learning (ML) model and how generalization and sampling can help assess the quality of ML models for custom training....

Melhores avaliações

OD

30 de mai de 2020

Amazing course. For a beginner like me, it was a shot in the arm. Excellent presentation very lively and engaging. Hope to see the instructor soon in a another course. Thanks so much. I learned a lot.

PT

1 de dez de 2018

This is an awesome module. It will open up so much inside story of ML process which is core of the topic with such a simplicity. It greatly increases my interest into this topic and this course :)

Filtrar por:

426 — 450 de 476 Avaliações para o Launching into Machine Learning

por Rocco R

10 de jul de 2019

Contingency tables and ROC graphs were poorly characterized and presenter resorted to obfuscation to mask his unfamiliarity with this basic statistical concept. Furthermore, when the proposed task is to "Identify pictures containing house cats", correctly identifying a picture that does not contain a house cat (True Negative) does NOT count as a successful prediction. You are confusing sensitivity with specificity in your so-called confusion matrix.

With respect to labs, you should warn students to leave their notebooks open so we do not have to reload everything. Also in the cab fare exercise the presenter did not elaborate on the fact that the RMSE's were higher than the predicted fare and mistakenly excluded time of day when in fact fares increase during rush hour.

por Breght V B

22 de mai de 2018

Using hash function doesn't seem a good way to split the dataset:

-You could discard a relevant feature

-You will group data on a similar characteristic, which might not represent the population well

-You don't have control over the size of your split since the feature will not likely be uniformly distributed

Can't we add an index feature/column and do a modulo on the index?

por Tomomasa T

23 de set de 2018

In The last lab, teacher says that there is 100,000 in data set , then we extract 10,000 from data set.

But there is 1,000,000,000( I checked by

'''SELECT

COUNT(vendor_id)

FROM

`nyc-tlc.yellow.trips`'''9

SELECT

COUNT(vendor_id)

FROM

`nyc-tlc.yellow.trips)

In that context, I think MOD(...) meaning is totally different ?

por Anubhav S

27 de jul de 2019

I feel that the flight and taxi cost estimation was kinda rushed. It was hard for me to follow. Ii having less knowledge about SQL was finding it to be tough. Before that, everything was clean and awesome. I think I have to revisit these courses after learning SQL better.

por Venkata S S G

10 de ago de 2019

good course. but it is just like an intro regarding how to use google cloud platform. but theory part was decent. can give it a try. but lectures were really indulging

por Matthew R

14 de nov de 2018

Some good material here, but at times it feels like an ad for GCP. And the labs are not very inventive. You just run a python notebook with canned stuff in them.

por Anand H

7 de out de 2018

While the concepts covered were good and very valuable, I didn't like the lab sessions. Just having to walk through code is not a good way to get hands-on.

por José C L A

18 de abr de 2020

Too much content for just one week. Exercises solved and not made for students to resolve them. Suggesting more complicated tasks is not teaching.

por Anupam S

29 de nov de 2019

I could only sustain it because I have completed basic ML courses earlier. Too many tech concepts & jargons overloaded in a very short time.

por David N

14 de jun de 2019

Learning the approach was very valuable. The exercises were just copy and paste of a bunch of code that it isn't expect we understand.

por Nour L

29 de ago de 2018

It felt too hard. I liked because it gives a very good idea but the concept was too hard especially with the math involved

por Cooper C

15 de jan de 2020

This course is just ok. It is not interactive and I don't feel that I learned much when compared with other ML courses.

por Nils W

28 de set de 2019

The course is good, but I missed the hands on part. You really do not need to code. That should be changed.

por Pravin A J D

5 de jan de 2019

not enough practical content such as types of machine learning and different algorithms to be used etc

por Srinivasan D

27 de jul de 2020

In the labs, I kept getting disconnected from the Jupyter notebooks, and had to keep reloading them.

por Jon B

11 de jun de 2018

Course includes good presentation material which unfortunately is not available to download.

por Aseem B

23 de ago de 2018

If you already know ML there isn't much in this course that will be value addition for you.

por Fabrizio F

29 de jul de 2018

The course is very well explained, but I was already aware of most subjects.

por Kevin C

15 de jul de 2018

There is a little more content here than in the 1st course.

por Prateek D

11 de ago de 2018

Please add more content, don't make it just intro types

por Manuele I

29 de abr de 2020

Talked too much...more practical example step by step

por Shawn W

19 de set de 2019

A bit difficult when introducing the ML history

por vishnu p T

23 de mai de 2020

quiet difficult to undertand

por Saurav K

21 de jul de 2019

It's not much helpful

por Vinit K

22 de jan de 2019

Very Basic again