Art and Science of Machine Learning
- Offered byCoursera
Art and Science of Machine Learning at Coursera Overview
Duration | 19 hours |
Start from | Start Now |
Total fee | Free |
Mode of learning | Online |
Difficulty level | Intermediate |
Official Website | Explore Free Course  |
Credential | Certificate |
Art and Science of Machine Learning at Coursera Highlights
- Shareable Certificate Earn a Certificate upon completion
- 100% online Start instantly and learn at your own schedule.
- Course 5 of 5 in the Machine Learning with TensorFlow on Google Cloud Platform Specialization
- Flexible deadlines Reset deadlines in accordance to your schedule.
- Intermediate Level
- Approx. 19 hours to complete
- English Subtitles: English
Art and Science of Machine Learning at Coursera Course details
- Welcome to the Art and Science of machine learning. This course is delivered in 6 modules. The course covers the essential skills of ML intuition, good judgment and experimentation needed to finely tune and optimize ML models for the best performance. You will learn how to generalize your model using Regularization techniques and about the effects of hyperparameters such as batch size and learning rate on model performance. We?ll cover some of the most common model optimization algorithms and show you how to specify an optimization method in your TensorFlow code.
Art and Science of Machine Learning at Coursera Curriculum
Introduction
Course Introduction
Getting Started with Google Cloud Platform and Qwiklabs
Introduction
Regularization
L1 & L2 Regularizations
Lab Intro: Regularization
Lab: Regularization
Learning rate and batch size
Optimization
Lab Intro: Reviewing Learning Curves
Resources Readings - 1 - The Art of ML (The Art of ML)
Resources Readings - 2 - The art of ML (Learning rate and batch size)
The Art of ML: Regularization
Hyperparameter Tuning
Introduction
Parameters vs Hyperparameters
Think Beyond Grid Search
Lab Intro: Export data from BigQuery to Google Cloud Storage
Lab Intro: Performing Hyperparameter Tuning
Resources Readings - 3 - Hyperparameter Tuning
Hyperparameter Tuning
Introduction
Regularization for sparsity
Lab: L1 Regularization
Lab Solution: L1 Regularization
Logistic Regression
Resources Readings - 4 - A Pinch of Science (Regularization for sparsity)
Resources Readings - 5 - A Pinch of Science (Logistic regression)
L1 Regularization
Logistic Regression
The Science of Neural Networks
Introduction to Neural Networks
Neural Networks
Lab: Neural Networks Playground
Training Neural Networks
Lab Intro: Build a DNN using the Keras Functional API
Lab Intro: Training Models at Scale with AI Platform
Multi-class Neural Networks
Resources Readings - 6 - The Science of Neural Networks
Training Neural Networks
Multi-class Neural Networks
Introduction to Embeddings
Review of Embeddings
Recommendations
Data-driven Embeddings
Sparse Tensors
Train an Embedding
Similarity Property
Lab Intro: Introducing the Functional API
Resources Readings - 7 - Embedding
Embeddings
Course Summary
Resources - Compiled List of Readings
All Quiz Questions as on PDF
Course Slides
Art and Science of Machine Learning at Coursera Admission Process
Important Dates
Other courses offered by Coursera
Student Forum
Anything you would want to ask experts?
Data ScienceMachine LearningMachine Learning and Pattern RecognitionArt and Science of Machine Learning