Machine learning/AI Training Course duration|
Machine learning/AI Training Course Objectives
How you can use Watson APIs and services
- Learn to translate business problems into machine learning algorithms.
- Know how to treat unstructured and semi structured data, such as text, time series, spatial, graph data, and images.
- Understand the generalization error of the model before deployment
- Ensure proper handling of training and testing data so the testing data mimics incoming data when the model is deployed in production
- Selecting the appropriate objective/loss function inspired by the business value is important for ultimate success in the application
- Understanding features in the data and improving upon them (by creating new features and eliminating existing ones) has a high impact in terms of predictability
- Selecting the machine learning method that works best for the given problem is key and often determines success or failure
Machine learning/AI Training Course outline
- Build a cognitive search and content analytics engine
- Use Watson Discovery to quickly create cognitive applications that extract value from large amounts of structured and unstructured data.
- Teach your apps to listen and speak
- Use Speech to Text to embed speech understanding within new or existing applications, in a variety of languages, such as US and UK English, Spanish, Japanese and more.
- Extract breakthrough insights from texts
- Use natural language understanding to analyze large volumes of texts in natural language - whether short-form social content or lengthy essays - to understand concepts, entities, keywords, sentiment, and more, quickly and easily.
- Automate customer interactions
- Use Watson Conversation to create a bot powered by natural language understanding in minutes, then deploy via multiple channels and devices, such as messaging platforms like Slack, mobile devices/SMS, and even physical robots.
- Train apps to see like a human expert
- Use Visual Recognition to answer the question, "What's in these images?" by analyzing and classifying the content of pictures.
Lesson 1: Python Ecosystem for Machine Learning.
Lesson 2: Python and SciPy Crash Course.
Lesson 3: Load Datasets from CSV.
Lesson 4: Understand Data With Descriptive Statistics.
Lesson 5: Understand Data With Visualization.
Lesson 6: Pre-Process Data.
Lesson 7: Feature Selection.
Lesson 8: Resampling Methods.
Lesson 9: Algorithm Evaluation Metrics.
Lesson 10: Spot-Check Classification Algorithms.
Lesson 11: Spot-Check Regression Algorithms.
Lesson 12: Model Selection.
Lesson 13: Pipelines.
Lesson 14: Ensemble Methods.
Lesson 16: Model Finalization.