AWS Certified Machine Learning - Specialty (MLS-C01) Cert Prep: 3 Modeling
32mIntermediate2023-03-01
Authors
Noah Gift
MLOps Expert | Solopreneur | Author | Adjunct Professor | CTO
Course details
Join MLOps expert and CTO Noah Gift to learn all about data engineering and prepare for the modeling portion of the AWS Certified Machine Learning – Specialty (MLS-C01) certification. Noah explains when to use machine learning, the difference between supervised and unsupervised learning, and the types of models that are available. He shows you how to train the model using the appropriate data. This process includes splitting the data into training and validation sets, choosing the right optimizer and loss function, and understanding the trade-offs between different model choices. After the model is trained, Noah guides you through how to evaluate it to ensure that it is performing well. This evaluation includes choosing the right metrics, understanding the confusion matrix, and performing cross-validation. Finally, Noah goes over how to interpret the model to understand what it is doing and how it can be improved.
Skills covered
Data ModelingMachine LearningAmazon Web Services (AWS)AmazonCloud ServicesCloud PlatformsCert PrepArtificial Intelligence (AI)Cloud ComputingData ScienceOne-Off
Concepts
0. Introduction
- 01 - Overview
1. Frame Business Problems as Machine Learning Problems
- 02 - Determine when to use and when not to use ML
- 03 - Know the difference between supervised and unsupervised learning
- 04 - Select from among classification, regression, forecasting, clustering, recommendation, and more
2. Select the Appropriate Model(s) for a Given Machine Learning Problem
- 05 - Select models
- 06 - SageMaker Canvas demo
3. Train Machine Learning Models
- 07 - Train validation test split, cross-validation
- 08 - Optimization
- 09 - Compute choice
4. Perform Hyperparameter Optimization
- 10 - Neural network architecture
5. Evaluate Machine Learning Models
- 11 - Avoid overfitting and underfitting
- 12 - Select metrics
- 13 - Compare models using metrics
Conclusion
- 14 - Conclusion