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.
Ce cours fait partie de la Spécialisation Machine Learning with TensorFlow on Google Cloud Platform
Offert par
À propos de ce cours
64,632 consultations récentes
Résultats de carrière des étudiants
40%
ont commencé une nouvelle carrière après avoir terminé ce cours
38%
ont bénéficié d'un avantage concret dans leur carrières grâce à ce cours
24%
a obtenu une augmentation de salaire ou une promotion
Certificat partageable
Obtenez un Certificat lorsque vous terminez
100 % en ligne
Commencez dès maintenant et apprenez aux horaires qui vous conviennent.
Cours 2 sur 5 dans le
Dates limites flexibles
Réinitialisez les dates limites selon votre disponibilité.
Niveau intermédiaire
Approx. 20 heures pour terminer
Anglais
Sous-titres : Anglais
Compétences que vous acquerrez
TensorflowBigqueryMachine LearningData Cleansing
Résultats de carrière des étudiants
40%
ont commencé une nouvelle carrière après avoir terminé ce cours
38%
ont bénéficié d'un avantage concret dans leur carrières grâce à ce cours
24%
a obtenu une augmentation de salaire ou une promotion
Certificat partageable
Obtenez un Certificat lorsque vous terminez
100 % en ligne
Commencez dès maintenant et apprenez aux horaires qui vous conviennent.
Cours 2 sur 5 dans le
Dates limites flexibles
Réinitialisez les dates limites selon votre disponibilité.
Niveau intermédiaire
Approx. 20 heures pour terminer
Anglais
Sous-titres : Anglais
Offert par
Google Cloud
We help millions of organizations empower their employees, serve their customers, and build what’s next for their businesses with innovative technology created in—and for—the cloud. Our products are engineered for security, reliability, and scalability, running the full stack from infrastructure to applications to devices and hardware. Our teams are dedicated to helping customers apply our technologies to create success.
Programme du cours : ce que vous apprendrez dans ce cours
8 minutes pour terminer
Introduction to Course
In this course you’ll get foundational ML knowledge so that you understand the terminology that we use throughout the specialization. You will also learn practical tips and pitfalls from ML practitioners here at Google and walk away with the code and the knowledge to bootstrap your own ML models.
8 minutes pour terminer
2 vidéos (Total 8 min)
4 heures pour terminer
Improve Data Quality and Exploratory Data Analysis
In this module, we will introduce data quality issues and how to improve them. We will then look at exploratory data anlaysis.
4 heures pour terminer
5 vidéos (Total 29 min), 1 lecture, 4 quiz
5 vidéos
Introduction45s
Improve Data Quality13 min
Lab Intro Improve Data Quality1 min
Exploratory Data Anlaysis13 min
Lab Intro Exploratory Data Analysis46s
1 lecture
Resources10 min
2 exercices pour s'entraîner
Practice Quiz on Improve Data Quality30 min
Practice Quiz on Exploratory Data Analysis30 min
8 heures pour terminer
Practical ML
In this module, we will introduce some of the main types of machine learning and review the history of ML leading up to the state of the art so that you can accelerate your growth as an ML practitioner.
8 heures pour terminer
13 vidéos (Total 63 min), 1 lecture, 11 quiz
13 vidéos
Introduction1 min
Supervised Learning5 min
Regression and Classification11 min
Short History of ML: Linear Regression7 min
Short History of ML: Perceptron5 min
Short History of ML: Neural Networks7 min
Lab Intro: Introduction to Linear Regression26s
Lab Intro: Introduction to Logistic Regression21s
Short History of ML: Decision Trees5 min
Short History of ML: Random Forests4 min
Lab Intro: Decision Trees and Random Forests in Python30s
Short History of ML: Kernel Methods4 min
Short History of ML: Modern Neural Networks8 min
1 lecture
Resources10 min
8 exercices pour s'entraîner
Supervised Learning30 min
Regression and Classification30 min
Linear Regression30 min
Perceptron30 min
Neural Networks30 min
Decision Trees 30 min
Kernel Methods30 min
History of ML: Modern Neural Networks30 min
3 heures pour terminer
Optimization
In this module we will walk you through how to optimize your ML models.
3 heures pour terminer
13 vidéos (Total 61 min), 1 lecture, 4 quiz
13 vidéos
Introduction42s
Defining ML Models4 min
Introducing the Course Dataset6 min
Introduction Loss Functions6 min
Gradient Descent5 min
Troubleshooting Loss Curves2 min
ML Model Pitfalls6 min
Lecture Lab: Introducing the TensorFlow Playground6 min
Lecture Lab: TensorFlow Playground - Advanced3 min
Lecture Lab: Practicing with Neural Networks6 min
Loss Curve Troubleshooting2 min
Performance Metrics3 min
Confusion Matrix5 min
1 lecture
Resources10 min
4 exercices pour s'entraîner
Lesson Quiz 30 min
Lesson Quiz30 min
Lesson Quiz30 min
Module Quiz30 min
4 heures pour terminer
Generalization and Sampling
Now it’s time to answer a rather weird question: when is the most accurate ML model not the right one to pick? As we hinted at in the last module on Optimization -- simply because a model has a loss metric of 0 for your training dataset does not mean it will perform well on new data in the real world. You will learn how to create repeatable training, evaluation, and test datasets and establish performance benchmarks.
4 heures pour terminer
9 vidéos (Total 64 min), 1 lecture, 4 quiz
9 vidéos
Introduction1 min
Generalization and ML Models6 min
When to Stop Model Training5 min
Lecture Creating Repeatable Samples in BigQuery6 min
LectureDemo: Splitting Datasets in BigQuery8 min
Lab Introduction Creating Repeatable Dataset Splits in BigQuery1 min
Lab Solution Walkthrough Creating Repeatable Dataset Splits in BigQuery9 min
Lab Introduction Exploring and Creating ML Datasets2 min
Lab Solution Walkthrough Exploring and Creating ML Datasets23 min
1 lecture
Resources10 min
2 exercices pour s'entraîner
Generalization and ML Models30 min
Module Quiz30 min
1 heure pour terminer
Summary
1 heure pour terminer
1 vidéo (Total 4 min), 2 lectures, 1 quiz
1 vidéo
Course Summary3 min
2 lectures
Resources - Readings Compiled as PDF10 min
Quiz Questions as a PDF10 min
1 exercice pour s'entraîner
Course Quiz30 min
Avis
Meilleurs avis pour LAUNCHING INTO MACHINE LEARNING
par OD30 mai 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.
par PT1 déc. 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 :)
par PA3 août 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.
par KT8 avr. 2019
My favourite course in the specialisation. I think it's a great idea to use historic time-frame to explain the advances in ML and why there is so much hype around deep learning.
À propos du Spécialisation Machine Learning with TensorFlow on Google Cloud Platform
What is machine learning, and what kinds of problems can it solve? What are the five phases of converting a candidate use case to be driven by machine learning, and why is it important that the phases not be skipped? Why are neural networks so popular now? How can you set up a supervised learning problem and find a good, generalizable solution using gradient descent and a thoughtful way of creating datasets? Learn how to write distributed machine learning models that scale in Tensorflow, scale out the training of those models. and offer high-performance predictions. Convert raw data to features in a way that allows ML to learn important characteristics from the data and bring human insight to bear on the problem. Finally, learn how to incorporate the right mix of parameters that yields accurate, generalized models and knowledge of the theory to solve specific types of ML problems. You will experiment with end-to-end ML, starting from building an ML-focused strategy and progressing into model training, optimization, and productionalization with hands-on labs using Google Cloud Platform.
Foire Aux Questions
Puis-je prévisualiser un cours avant de m'inscrire ?
À quoi ai-je droit si je m'inscris ?
Quand recevrai-je mon Certificat de Cours ?
Pourquoi ne puis-je pas assister à ce cours en auditeur libre ?
Is financial aid available?
D'autres questions ? Visitez le Centre d'Aide pour les Etudiants.
