Chevron Left
Retour à Launching into Machine Learning

Avis et commentaires pour l'étudiant pour Launching into Machine Learning par Google Cloud

4.6
3,036 notes
342 avis

À propos du cours

Starting from a history of machine learning, we discuss why neural networks today perform so well in a variety of data science problems. We then discuss how to set up a supervised learning problem and find a good solution using gradient descent. This involves creating datasets that permit generalization; we talk about methods of doing so in a repeatable way that supports experimentation. Course Objectives: Identify why deep learning is currently popular Optimize and evaluate models using loss functions and performance metrics Mitigate common problems that arise in machine learning Create repeatable and scalable training, evaluation, and test datasets COMPLETION CHALLENGE Complete any GCP specialization from November 5 - November 30, 2019 for an opportunity to receive a GCP t-shirt (while supplies last). Check Discussion Forums for details....

Meilleurs avis

PT

Dec 02, 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 :)

PA

Aug 04, 2018

Good course, covering all the basics about machine learning and most importantly, everything that surrounds an ml project and you need to take into account to make your ml project successful.

Filtrer par :

301 - 325 sur 340 Examens pour Launching into Machine Learning

par Tom

Aug 21, 2018

The course is ok. Several complicated concepts are expected to be known, other very easy ones are explained in detail. However in some phases too high level, I am definitely missing some course resources to work with.

Was hoping for more hands-on experience.

par Aseem B

Aug 23, 2018

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

par Tomomasa T

Sep 23, 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 ?

par Anand H

Oct 08, 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.

par Nour L

Aug 29, 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

par Kevin C

Jul 15, 2018

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

par Jeremy N B

Jun 09, 2018

I've spent the past three years studying ML and AI starting from the ground up with Calculus, Linear Algebra, basic data science techniques and eventually Deep Learning. I am primarily interested in this specialization because I would like to begin using GCP professionally. This course provides a very quick surface level overview of the "history" of ML and the techniques that have been aggregated to make up the current cutting edge of AI in practice. Already having a grasp on many of the concepts, I was able to zip through this course in a few hours and found it basic. If you're looking for something a bit more challenging, I would recommend the DeepLearning.ai specialization also available on Coursera. This course works well as a refresher and a high level overview. If you are completely new to the field, be warned that there is quite a terminology to be unpacked that is covered more thoroughly in other courses on Coursera. The University of Washington machine learning specialization (though sadly cut short) would be a much better starting place, if you are completely new to the topic.

par Jon B

Jun 11, 2018

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

par Breght V B

May 22, 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?

par KimNamho

Apr 12, 2019

thank you

par Rocco R

Jul 10, 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.

par Saurav K

Jul 21, 2019

It's not much helpful

par Anubhav S

Jul 27, 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.

par venkata s s g

Aug 10, 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

par David N

Jun 14, 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.

par Shawn W

Sep 19, 2019

A bit difficult when introducing the ML history

par Nils W

Sep 28, 2019

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

par Sean S

Jan 28, 2019

The labs really just lay everything out for you, and don't challenge you to learn anything for yourself.

par Ligeng X

Nov 09, 2018

Barely learn anything

par Soroosh R

Feb 15, 2019

The instructors were talking most of the time in a monotonous way without showing proper slides or elaborating the materials. Overall it was a very poor introduction of the ML. The two labs were good, however it was surprising to me that they did not commented out the notebook codes!

par Ragy I

Mar 20, 2019

Maths and ML stuff are explained very poorly... very rushed and people speaking are clearly reading from a script which makes it difficult to understand and follow on =

par Thomas V

Nov 15, 2018

No real implementation

par Francesco C

Jul 12, 2018

labs not really useful

par Srikar K

May 01, 2018

The LABs in this course did not work for me. I was not able to open DataLab in my Lab sessions. This is quite frustrating to me.

par Brennon B

May 28, 2018

Google has clearly put a great deal of effort into constructing and polishing this course. However, the certificate is really nothing more than a participation trophy. I understand that putting the course materials (videos, demos, etc.) are time-consuming. An exceptional course, though, needs to actually test that the learner has, indeed, learned. When all of the labs/assignments require nothing more than clicking through them, they fall far short in this respect.