AI and Machine Learning: Code, Train, & Deploy

Course Description

This comprehensive 16-week course provides a deep dive into the fundamentals and advanced concepts of Artificial Intelligence and Machine Learning. Students will begin with foundational AI/ML principles, Python programming, and essential tools before progressing to data preprocessing, exploratory data analysis, and classical machine learning techniques. The course then covers deep learning fundamentals, including neural networks, CNNs, RNNs, and transformers for NLP. Advanced topics such as reinforcement learning and generative models are explored, followed by practical deployment strategies using MLOps, cloud platforms, and Docker. The course culminates with a hands-on capstone project, integrating ethical considerations and responsible AI development practices.

Course Goals

In this Course, you'll learn the following:

  • Fundamentals of AI and machine learning
  • Data preprocessing and exploratory data analysis
  • Supervised and unsupervised learning techniques
  • Deep learning with TensorFlow and PyTorch
  • Natural language processing (NLP) and transformers
  • Reinforcement learning and its applications
  • Model deployment using cloud platforms and MLOps
  • Ethical considerations in AI and responsible development

Week
1
( 18 Hours )
Introduction to Data Science and Review of Programming Fundamentals

• Introduction to Data Science

• Python Review

• Variables and Data Types

• Conditional Statements and Loops

• Functions and Modules

Week
2
( 18 Hours )
Data Manipulation with Pandas

• Introduction to Pandas

• Loading Data with Pandas

• Data Manipulation with Pandas

• Aggregating and Grouping Data with Pandas

• Data Cleaning and Preprocessing with Pandas

Week
3
( 18 Hours )
Working with Databases and APIs

• Introduction to Databases

• SQL Review

• Introduction to APIs

• Accessing Web APIs with Python

• Processing JSON Data

Week
4
( 18 Hours )
Project 1 - Data Wrangling and Analysis

• Working with a real-world dataset using Pandas and Python

• Data Cleaning and Preprocessing

• Exploratory Data Analysis

Week
5
( 18 Hours )
Review of Descriptives and Inferential Statistics

• Descriptive Statistics

• Probability Theory

• Common Probability Distributions

• Statistical Inference

• Hypothesis Testing

Week
6
( 18 Hours )
Experimental Design

• Introduction to Experimental Design

• Types of Experimental Designs

• Sampling Techniques

• Power Analysis

• A/B Testing

Week
7
( 18 Hours )
Data Visualization with Matplotlib and Seaborn

• Introduction to Data Visualization

• Introduction to Matplotlib

• Introduction to Seaborn

• Basic Plots and Customizations

• Advanced Plots and Customizations

Week
8
( 18 Hours )
Regression

• Introduction to Linear Regression

• Simple Linear Regression

• Simple Logistic Regression

• Multiple Linear Regression

• Model Selection and Evaluation

• Regularization Techniques (L1, L2, Elastic Net)

Week
9
( 18 Hours )
Project 2 - Exploratory Data Analysis and Visualization

• Working with a real-world dataset using Python

• Data Cleaning and Preprocessing

• Exploratory Data Analysis

• Data Visualization

Week
10
( 18 Hours )
Classification

• Introduction to Classification

• Logistic Regression

• Decision Trees and Random Forests

• Naive Bayes

• Model Selection and Evaluation

Week
11
( 18 Hours )
Machine Learning with Scikit-Learn

• Introduction to Scikit-Learn

• Supervised Learning

• Unsupervised Learning

• Model Selection and Evaluation

• Putting it All Together: Real-World Machine Learning

Week
12
( 18 Hours )
Project 3 - Machine Learning Modeling and Evaluation

• Working with a real-world dataset using Scikit-Learn

• Data Cleaning and Preprocessing

• Feature Engineering

• Model Selection and Evaluation

• Model Deployment

Week
13
( 18 Hours )
Deep Learning and Neural Networks

• Introduction to Neural Networks

• Implementing Neural Networks using TensorFlow and Keras

• Training Deep Learning Models

• Hyperparameter Tuning

• Model Deployment

• Introduction to Prompt Engineering

Week
14
( 18 Hours )
Advanced Topics in Data Science

• Time Series Analysis

• Natural Language Processing

• Reinforcement Learning

• Ethical AI and Bias in Machine Learning

Week
15
( 18 Hours )
ML Ops for ML Model Deployment

• Introduction to ML Ops

• Model Versioning and Reproducibility

• Continuous Integration and Deployment (CI/CD) for ML

• Model Monitoring and Maintenance

Week
16
( 18 Hours )
Final Capstone Project Presentation

• Finalizing Project Report

• Presentation of Findings

• Feedback and Iteration

• Career Pathways and Job Readiness