AI & Machine Learning Foundations

Curriculum

Industry-approved curriculum to support your journey into data and AI

‍

Foundations I 

Cloud Computing, Generative AI, & Dashboards - 3 weeks

This course dives into cloud computing's cost-effective, scalable ecosystem for distributed data processing. Master technical components like PySpark to bridge Python, SQL, and Spark, to manipulate structured and semi-structured data. Leverage libraries to Numpy, Pandas, and PySpark to pull in "big data". You will craft stunning visualizations with Python libraries like Seaborn. Finally, explore the cutting-edge of data analysis with generative AI and advanced dashboards, culminating in a project that brings big data to life through interactive visualizations.

What you'll learn:

• Create a dashboard using data science methodologies with industry standard tool(s)
• Model exploratory data analysis with tools for multiple data sets with SQL and SQL table relations
• Utilize programming techniques to process large data samples with large-scale processing like PySpark with big data

‍

Inferential Statistics - 3 weeks

In this course you will perform statistical inference with Python. This course equips you with the foundational theory and practical skills to analyze data. Learn about probability distributions, confidence intervals, hypothesis testing, and more. Apply these techniques to single proportions, means, and categorical data. Explore advanced methods for two or more groups and tackle multivariate datasets. This culminates with your final project where you'll showcase your ability to use a multivariate dataset and perform a myriad of the appropriate methods of statistical inference.

What you'll learn:

• Integrate statistical inference of data using the technical programming
• Implement methodologies for statistical inference
• Utilize mathematics, statistics, and probability for data science methodologies to derive insights

‍

Regression - 3 weeks

This course equips you with the skills to tackle real-world datasets with regression. Master linear regression, exploring diagnostics to ensure model validity. Delve into multiple linear regression, learning to evaluate, diagnose, and leverage its predictive power. Discover advanced techniques like transformations, interactions, and model selection. Explore bias-variance tradeoff and master regularization methods like Lasso and Ridge regression. Finally, in the culminating project, showcase your expertise by building and interpreting a powerful multiple linear regression model.

What you'll learn:

• Perform logistic regression with data sets using programming techniques, lasso, and ridge
• Compare statistical results for different types of regression with data sets, linear, transformations of linear, and multiple linear regressions
• Utilize mathematics, statistics, and probability for data science methodologies to derive insights

‍

Foundations II

Introduction to Machine Learning - 3 weeks

In this course you will begin to learn the fundamentals of AI, machine learning models. Explore core concepts like statistical learning theory and supervised learning. Delve into diverse models like logistic regression, decision trees, and support vector machines. Learn to evaluate and compare their performance using metrics like ROC AUCs. Finally, in the culminating project, showcase your mastery of the data science pipeline by selecting and deploying the ideal model for a specific task.

What you’ll learn:

• Utilize foundational machine learning modeling like decision trees and supervised learning
• Prepare data for machine learning modeling with preprocessing (feature extraction) and normalization
• Utilize mathematics, statistics, & probability for data science methodologies to derive insights

‍

Machine Learning with Scikit-Learn - 3 weeks

In this course you will be introduced to a range of supervised and unsupervised machine learning models. You will explore distance metrics and the foundation for k-Nearest Neighbors, a popular supervised learning model for classification. Dive into recommender systems, leveraging SVD for both supervised and unsupervised learning tasks. Learn clustering techniques like k-means, and explore dimensionality reduction with Principal Component Analysis (PCA) for an unsupervised learning model. Finally, conquer the culminating project: build both a supervised (k-Nearest Neighbors) and unsupervised (k-means) learning model, showcasing your ability to tackle classification and clustering tasks.

What you’ll learn:

• Utilize foundational machine learning modeling like decision trees and supervised learning
• Prepare data for machine learning modeling with preprocessing (feature extraction) and normalization
• Integrate mathematics, statistics, & probability for data science methodologies to derive insights

‍

Natural Language Processing, Time Series & Neural Networks - 3 weeks

This course equips you with the skills to build cutting-edge models. Master natural language processing (NLP), exploring techniques like text classification, and vectorization. Delve into time series analysis, learning to manage, visualize, and model trends in data. Finally, dive into the fascinating world of neural networks, understanding their theory and implementation with Keras. In the culminating project, showcase your mastery by building three distinct models: a language model, a time series model, and a basic neural network.

What you’ll learn:

• Develop insights from language, time, and image data using neural networks and Natural Language Processing (NLP)
• Integrate mathematics, statistics, & probability for data science methodologies to derive insights

‍

Neural Networks & Similar Models - 3 weeks

In this course you will learn how to build upon your neural network foundation. Master normalization and regularization techniques to optimize your models. Delve into Convolutional Neural Networks (CNNs) for powerful image classification. Explore Recurrent Neural Networks (RNNs) and unlock their potential for forecasting and sequence data analysis. Finally, unveil the cutting-edge world of transformers and BERT, culminating in a project that showcases your expertise in building an advanced neural network application.

What you’ll learn:

• Create an advanced neural network application
• Integrate mathematics, statistics, & probability for data science methodologies to derive insights