WHAT YOU WILL LEARN
Design an ML manufacturing system end-to-end: undertaking scoping, knowledge wants, modeling methods, and deployment necessities.
Set up a mannequin baseline, deal with idea drift, and prototype learn how to develop, deploy, and repeatedly enhance a productionized ML software.
Construct knowledge pipelines by gathering, cleansing, and validating datasets. Set up knowledge lifecycle through the use of knowledge lineage and provenance metadata instruments.
Apply greatest practices and progressive supply strategies to take care of and monitor a repeatedly working manufacturing system.
SKILLS YOU WILL GAIN
- Managing Machine Studying Manufacturing Programs
- Deployment Pipelines
- Mannequin Pipelines
- Information Pipelines
- Machine Studying Engineering for Manufacturing
- Human-level Efficiency (HLP)
- Idea Drift
- Mannequin baseline
- Venture Scoping and Design
- ML Deployment Challenges
- ML Metadata
- Convolutional Neural Community
About this Specialization
Understanding machine studying and deep studying ideas is important, however should you’re trying to construct an efficient AI profession, you want manufacturing engineering capabilities as nicely.
Successfully deploying machine studying fashions requires competencies extra generally present in technical fields comparable to software program engineering and DevOps. Machine studying engineering for manufacturing combines the foundational ideas of machine studying with the purposeful experience of contemporary software program improvement and engineering roles.
The Machine Studying Engineering for Manufacturing (MLOps) Specialization covers learn how to conceptualize, construct, and keep built-in techniques that repeatedly function in manufacturing. In placing distinction with normal machine studying modeling, manufacturing techniques must deal with relentless evolving knowledge. Furthermore, the manufacturing system should run continuous on the minimal value whereas producing the utmost efficiency. On this Specialization, you’ll discover ways to use well-established instruments and methodologies for doing all of this successfully and effectively.
On this Specialization, you’ll turn out to be aware of the capabilities, challenges, and penalties of machine studying engineering in manufacturing. By the tip, you’ll be able to make use of your new production-ready abilities to take part within the improvement of modern AI expertise to unravel real-world issues.
Utilized Studying Venture
By the tip, you’ll be able to
• Design an ML manufacturing system end-to-end: undertaking scoping, knowledge wants, modeling methods, and deployment necessities
• Set up a mannequin baseline, deal with idea drift, and prototype learn how to develop, deploy, and repeatedly enhance a productionized ML software
• Construct knowledge pipelines by gathering, cleansing, and validating datasets
• Implement characteristic engineering, transformation, and choice with TensorFlow Prolonged
• Set up knowledge lifecycle by leveraging knowledge lineage and provenance metadata instruments and comply with knowledge evolution with enterprise knowledge schemas
• Apply strategies to handle modeling assets and greatest serve offline/on-line inference requests
• Use analytics to deal with mannequin equity, explainability points, and mitigate bottlenecks
• Ship deployment pipelines for mannequin serving that require totally different infrastructures
• Apply greatest practices and progressive supply strategies to take care of a repeatedly working manufacturing system
0 Comments