IBM - AI Workflow: Machine Learning, Visual Recognition and NLP
- Offered byCoursera
AI Workflow: Machine Learning, Visual Recognition and NLP at Coursera Overview
Duration | 14 hours |
Start from | Start Now |
Total fee | Free |
Mode of learning | Online |
Difficulty level | Advanced |
Official Website | Explore Free Course  |
Credential | Certificate |
AI Workflow: Machine Learning, Visual Recognition and NLP at Coursera Highlights
- Shareable Certificate Earn a Certificate upon completion
- 100% online Start instantly and learn at your own schedule.
- Course 4 of 6 in the IBM AI Enterprise Workflow Specialization
- Flexible deadlines Reset deadlines in accordance to your schedule.
- Advanced Level
- Approx. 14 hours to complete
- English Subtitles: English
AI Workflow: Machine Learning, Visual Recognition and NLP at Coursera Course details
- This is the fourth course in the IBM AI Enterprise Workflow Certification specialization. You are STRONGLY encouraged to complete these courses in order as they are not individual independent courses, but part of a workflow where each course builds on the previous ones.
- Course 4 covers the next stage of the workflow, setting up models and their associated data pipelines for a hypothetical streaming media company. The first topic covers the complex topic of evaluation metrics, where you will learn best practices for a number of different metrics including regression metrics, classification metrics, and multi-class metrics, which you will use to select the best model for your business challenge. The next topics cover best practices for different types of models including linear models, tree-based models, and neural networks. Out-of-the-box Watson models for natural language understanding and visual recognition will be used. There will be case studies focusing on natural language processing and on image analysis to provide realistic context for the model pipelines.
- By the end of this course you will be able to:
- Discuss common regression, classification, and multilabel classification metrics
- Explain the use of linear and logistic regression in supervised learning applications
- Describe common strategies for grid searching and cross-validation
- Employ evaluation metrics to select models for production use
- Explain the use of tree-based algorithms in supervised learning applications
- Explain the use of Neural Networks in supervised learning applications
- Discuss the major variants of neural networks and recent advances
- Create a neural net model in Tensorflow
- Create and test an instance of Watson Visual Recognition
- Create and test an instance of Watson NLU
- Who should take this course?
- This course targets existing data science practitioners that have expertise building machine learning models, who want to deepen their skills on building and deploying AI in large enterprises. If you are an aspiring Data Scientist, this course is NOT for you as you need real world expertise to benefit from the content of these courses.
- What skills should you have?
- It is assumed that you have completed Courses 1 through 3 of the IBM AI Enterprise Workflow specialization and you have a solid understanding of the following topics prior to starting this course: Fundamental understanding of Linear Algebra; Understand sampling, probability theory, and probability distributions; Knowledge of descriptive and inferential statistical concepts; General understanding of machine learning techniques and best practices; Practiced understanding of Python and the packages commonly used in data science: NumPy, Pandas, matplotlib, scikit-learn; Familiarity with IBM Watson Studio; Familiarity with the design thinking process.
AI Workflow: Machine Learning, Visual Recognition and NLP at Coursera Curriculum
Model Evaluation and Performance Metrics
Course Objectives
Evaluation Metrics
Introduction to Predictive Linear and Logistic Regression
Linear Models
Watson Natural Language Understanding Service Overview
Case Study Introduction
Evaluation Metrics: Through the Eyes of our Working Example
Evaluation Metrics
Regression Metrics
Classification Metrics
Multi-class and Multi-label Metrics
Model Performance: Through the Eyes of our Working Example
Generalizing Well to Unseen Data
Model Plots, Bias, Variance
Relating the Evaluation Metric to a Business Metric
Linear Models: Through the Eyes of our Working Example
Generalized Linear Models
Linear and Logistic Regression
Regularized Regression
Stochastic Gradient Descent Classifier
Watson Natural Language Understanding: Through the eyes of our Working Example
Watson Developer Cloud Python SDK
Performance and Business Metrics: Through the Eyes of our Working Example
Getting Started with Performance and Business Metrics Case Study (Hands-on)
Summary/Review
Check for Understanding
Check for Understanding
Check for Understanding
Check for Understanding
Check for Understanding
End of Module Quiz
Building Machine Learning and Deep Learning Models
Tree Based Methods
Introduction to Tree Based Methods
Neural Networks
Introduction to neural networks
IBM Watson Visual Recognition Overview
Tree-based Methods: Through the Eyes of our Working Example
Decision Trees
Bagging and Random Forests
Boosting
Ensemble Learning
Neural networks: Through the eyes of our Working Example
Multilayer perceptron (MLP)
Neural network architectures
On interpretability
Watson Visual Recognition: Through the Eyes of our Working Example
Watson Developer Cloud Python SDK
TensorFlow: Through the Eyes of our Working Example
Getting Started with Convolutional Neural Networks and TensorFlow (Hands-on)
Summary/Review
Check for Understanding
Check for Understanding
Check for Understanding
Check for Understanding
End of Module Quiz
AI Workflow: Machine Learning, Visual Recognition and NLP at Coursera Admission Process
Important Dates
Other courses offered by Coursera
Student Forum
Anything you would want to ask experts?
Data ScienceDeep LearningArtificial IntelligenceAI Workflow: Machine Learning, Visual Recognition and NLP