Automating Machine Learning on AWS
The course provides a comprehensive guide on how to build and manage a Machine Learning (ML) pipeline on Amazon Web Services (AWS). Students will gain practical skills through a series of modules covering introduction to ML and ML Pipeline, using Amazon SageMaker, problem formulation, data pre-processing, model training, model evaluation , feature engineering and model tuning, as well as model deployment. The course will conclude with a wrap-up session to review the key concepts covered during the course.
CODE: DSAI208
Category: Artificial Intelligence Course
DESCRIPTION
COURSE CONTENT
COURSE OBJECTIVES
ADDITIONAL INFORMATION
DESCRIPTION
Teaching methodology
The course includes educational laboratories in which each student will be able to carry out training exercises that will provide practical experience in the use of the tool, for each of the topics covered during the course.Prerequisites
- Basic knowledge of AWS
- Basic knowledge of Python
COURSE CONTENT
Below is an overview of the course contents:
- Introduction to ML and ML Pipeline: This module provides an overview of the fundamental concepts of machine learning (ML) and introduces students to the concept of machine learning pipelines, illustrating the typical steps involved in development and in the implementation of machine learning models.
- Introduction to Amazon SageMaker: Students will become familiar with Amazon SageMaker, a fully managed service that simplifies the process of developing, training, and deploying machine learning models on AWS.
- Problem Formulation: This module focuses on formulating and understanding the machine learning problem, helping students clearly define project objectives and model evaluation metrics.
- Data Pre-processing: Students will learn techniques and best practices for data pre-processing, including dealing with missing values, data normalization, and variable encoding categorical.
- Model Training: This module explains the various machine learning algorithms available and guides students through the process of training a model using labeled training data.
- Model Evaluation: Students will learn to evaluate the performance of a machine learning model using different evaluation metrics, such as accuracy, precision, recall and F1-score.
- Feature Engineering and Model Tuning: This module focuses on optimizing model performance through feature engineering and model tuning techniques, including hyperparameter tuning.
- Model Deployment: Students will gain hands-on skills in implementing and deploying machine learning models using Amazon SageMaker, preparing them for integrating the model into production applications.
COURSE OBJECTIVES
At the end of the course, participants will be able to:
- Select and justify the most correct ML approach to a problem
- Build, train, evaluate, deploy, and fine-tune an ML model on AWS
- Describe best practices for building and managing a Machine Learning pipeline on AWS
- Identify steps to apply Machine Learning to real-world problems using services and tools on AWS
ADDITIONAL INFORMATION
Duration – 1 day
Delivery – in the classroom, on site, remotely
PC and SW requirements:
- Internet connection
- Web browser, Google Chrome
- Zoom
- Instructor: Italian
- Laboratories: English
- Slides: English