Certified Artificial Intelligence (AI) Practitioner

Course details

Overview

Artificial intelligence (AI) and machine learning (ML) have become essential parts of the toolset for many organizations. When used effectively, these tools provide actionable insights that drive critical decisions and enable organizations to create exciting, new, and innovative products and services. This course shows you how to apply various approaches and algorithms to solve business problems through AI and ML, all while following a methodical workflow for developing data-driven solutions.

Objective

• Solve business problems with AI and ML
• Prepare and process data for ML
• Train, evaluate, and tune ML models
• Build and deploy various ML models (regression, classification, clustering, neural networks)
• Operate and maintain ML models in production

Who Should Attend

This course is suitable for anyone looking to expand their knowledge of machine learning algorithms and how they can help create intelligent decision-making products that bring value to the business

Outlines

Day 1: Solving Business Problems Using AI and ML including Preparing Data, Training, Evaluating, and Tuning a Machine Learning Model

• Identify AI and ML Solutions for Business Problems
• Formulate a Machine Learning Problem
• Select Approaches to Machine Learning
• Collect DataTransform DataEngineer Features
• Work with Unstructured Data
• Train a Machine Learning Model
• Evaluate and Tune a Machine Learning Model

Day 2: Building Linear Regression Models including, Building Forecasting Models

• Build Regression Models Using Linear Algebra
• Build Regularized Linear Regression Models
• Build Iterative Linear Regression Models
• Build Univariate Time Series Models
• Build Multivariate Time Series Models

Day 3: Building Classification Models Using Logistic Regression and k-Nearest Neighbor, including Building Clustering Models

• Train Binary Classification Models Using Logistic Regression
• Train Binary Classification Models Using k-Nearest Neighbor
• Train Multi-Class Classification Models
• Evaluate Classification ModelsTune Classification Models
• Build k-Means Clustering Models
• Build Hierarchical Clustering Models

Day 4: Building Decision Trees and Random Forests including Building Support-Vector Machines

• Build Decision Tree ModelsBuild Random Forest Models
• Build SVM Models for ClassificationBuild SVM Models for Regression

Day 5: Building Artificial Neural Networks including Operationalizing Machine Learning Models, Maintaining Machine Learning Operations

• Build Multi-Layer Perceptrons (MLP)
• Build Convolutional Neural Networks (CNN)
• Build Recurrent Neural Networks (RNN)
• Deploy Machine Learning Models
• Automate the Machine Learning Process with MLOps
• Integrate Models into Machine Learning Systems
• Secure Machine Learning Pipelines
• Maintain Models in Production

Updated on 20 August, 2024