Deep Learning and Generative AI: Data Prep, Analysis, and Visualization with Python

Course details

If you’re looking to keep up with the rapid advancements and applications of deep learning techniques, this course provides a comprehensive guide that can help you stay relevant and competitive in the evolving landscape of AI and data-driven technologies. Instructor Gwendolyn Stripling shows you how to transform raw data into valuable insights and build the foundation for cutting-edge AI applications. The course focuses on the concepts, with minimal coding required, so even if you’re not an experienced coder, Gwendolyn shows you how to use simple Python code to work with data. Test your learning with a series of challenges, and cap off the course with building and evaluating a predictive and generative model.

Learning objectives
Identify common applications of deep learning and generative AI in various fields such as computer vision, natural language processing, and healthcare.
Evaluate the quality of a dataset and make informed decisions about data preprocessing strategies based on factors such as data distribution, imbalance, and outliers.
Understand data preprocessing, cleaning, transformation, exploratory data analysis, feature engineering, and data augmentation in training effective generative AI models.
Distinguish between the goals of predictive AI and generative AI, understand the methodologies employed in each paradigm, and identify the unique outputs generated by predictive models versus generative models.
Create data visualizations using Python libraries like Matplotlib and Seaborn, depicting data distributions, trends, and relationships.
Explore data analysis techniques, such as statistical analysis and visualizations, to structured and unstructured data to understand data distributions, identify outliers, and detect correlations.

Concepts

0. Introduction

01 - Leverage generative AI for analytics and insights
02 - What you should know
03 - How to use the challenge exercise files

1. Why Process and Why Visualize Data

04 - We live in a data-driven world
05 - Our use case
06 - Raw data is messy
07 - Role of data in the machine learning workflow

2. Understanding Data

08 - Data with a structure
09 - Data without a structure
10 - Using simple Python code to check your data
11 - Python for data preprocessing with Pandas and Matplotlib
12 - Challenge - Load and check the data using Python
13 - Solution - Load and check the data using Python

3. Data Preprocessing

14 - Data preprocessing the telecom dataset
15 - Introduction to text preprocessing
16 - Challenge - Data preprocessing the telecom dataset
17 - Solution - Data preprocessing the telecom dataset

4. Exploratory Data Analysis

18 - Exploratory data analysis (EDA)
19 - Challenge - Perform exploratory data analysis
20 - Solution - Perform exploratory data analysis

5. Predictive and Generative AI

21 - Overview of predictive and generative AI
22 - What is deep learning
23 - Generative modeling use cases
24 - Predictive modeling use cases

6. Deep Learning - Build and Evaluate a Predictive Model

25 - Deep learning - Predict customer lifetime value
26 - Challenge - Predict customer lifetime value
27 - Solution - Predict customer lifetime value

7. Capstone - Build and Evaluate a Predictive and Generative Model

28 - Introduction to capstone and use case
29 - Challenge - Predict media channel sales using Keras
30 - Solution - Predict media channel sales using Keras
31 - Optional challenge - Generate sentiments using BERT
32 - Solution - Generate sentiments using BERT

Conclusion

33 - Next steps