Course Outline
Introduction
- Predictive analytics applications in finance, healthcare, pharmaceuticals, automotive, aerospace, and manufacturing sectors
Overview of Big Data concepts
Strategies for capturing data from diverse sources
Understanding data-driven predictive models
Survey of statistical and machine learning techniques
Case study: predictive maintenance and resource planning
Implementing algorithms on large-scale datasets using Hadoop and Spark
Predictive Analytics Workflow
Accessing and exploring data
Data preprocessing
Designing a predictive model
Training, testing, and validating datasets
Implementing various machine learning approaches (e.g., time-series regression, linear regression)
Integrating models into existing web applications, mobile devices, and embedded systems
Matlab and Simulink integration with embedded systems and enterprise IT workflows
Generating portable C and C++ code from MATLAB scripts
Deploying predictive applications to large-scale production environments, clusters, and cloud platforms
Acting upon analytical results
Next steps: Automatically responding to insights using Prescriptive Analytics
Closing remarks
Requirements
- Experience with Matlab
- No prior background in data science is required
Testimonials (2)
basics and loved the prepared documents and exercises
Rekha Nallam - GE Medical Systems Polska Sp. z o.o.
Course - Introduction to Predictive AI
The many examples and the building of the code from start to finish.
