À propos de ce cours : Starting from a history of machine learning, we discuss why neural networks today perform so well in a variety of 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
Les destinataires de ce cours : This course is aimed at data scientists, data engineers and programmers interested in learning how to apply machine learning in practice.
Créé par : Google Cloud
| Informations de base | Cours 2 de 5 dans Machine Learning with TensorFlow on Google Cloud Platform Specialization |
| Niveau | Intermediate |
| Langue | English |
| Matériel requis | You'll need to use a desktop web browser to access labs. |
| Comment réussir | Réussissez tous les devoirs notés pour terminer le cours. |
| Notes des utilisateurs |
Prévisualiser
Programme de cours
SEMAINE 1
Introduction
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.
1 vidéo
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.
10 vidéos
- Vidéo: Supervised Learning
- Vidéo: Regression and Classification
- Vidéo: Short History of ML: Linear Regression
- Vidéo: Short History of ML: Perceptron
- Vidéo: Short History of ML: Neural Networks
- Vidéo: Short History of ML: Decision Trees
- Vidéo: Short History of ML: Kernel Methods
- Vidéo: Short History of ML: Random Forests
- Vidéo: Short History of ML: Modern Neural Networks
- Discussion Prompt: Modern Neural Networks
Noté: Module Quiz
Optimization
In this module we will walk you through how to optimize your ML models.
13 vidéos
- Vidéo: Defining ML Models
- Vidéo: Introducing the Natality Dataset
- Vidéo: Introducing Loss Functions
- Vidéo: Gradient Descent
- Vidéo: Troubleshooting a Loss Curve
- Vidéo: ML Model Pitfalls
- Vidéo: Lab: Introducing the TensorFlow Playground
- Vidéo: Lab: TensorFlow Playground - Advanced
- Vidéo: Lab: Practicing with Neural Networks
- Vidéo: Loss Curve Troubleshooting
- Vidéo: Performance Metrics
- Vidéo: Confusion Matrix
Noté: Module Quiz
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.
9 vidéos
- Vidéo: Generalization and ML Models
- Vidéo: When to Stop Model Training
- Vidéo: Creating Repeatable Samples in BigQuery
- Vidéo: Demo: Splitting Datasets in BigQuery
- Vidéo: Lab Introduction
- Vidéo: Lab Solution Walkthrough
- Vidéo: Lab Introduction
- Vidéo: Lab Solution Walkthrough
Noté: Lab: Creating Repeatable Dataset Splits in BigQuery
Noté: Lab: Exploring and Creating ML Datasets
Noté: Module Quiz
Summary
1 vidéo
FAQ
Comment cela fonctionne
Coursework
Each course is like an interactive textbook, featuring pre-recorded videos, quizzes and projects.
Help from Your Peers
Connect with thousands of other learners and debate ideas, discuss course material, and get help mastering concepts.
Certificates
Earn official recognition for your work, and share your success with friends, colleagues, and employers.
Créateurs
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.
Tarification
| Acheter le cours | |
|---|---|
| Accéder au contenu du cours | Disponible |
| Accéder au contenu noté | Disponible |
| Recevoir une Note Finale | Disponible |
| Obtenir un Certificat de Cours partageable | Disponible |
Notation et examens
Nice introduction course!
Excellent articulation of the material. Well thought of labs. Thank you for a great introduction
The technical knowledge is introduced very progressively. You understand the historic evolution and practical usage of models. Great content!
Coursera propose un accès universel à la meilleure formation au monde,
en partenariat avec des universités et des organisations du plus haut niveau, pour proposer des cours en ligne.
© 2018 Coursera Inc. Tous droits réservés.
AK
Very useful intro to data processing, specially the hashing mechanism to partition the datasets.
The last lab was confusing because the data might have some invalid value. in the jupyter notebook, the sin, and arcsin values were not getting computed (probably?) as I got warning from python .