Artificial Intelligence Foundations: Getting Started with Intelligent Systems
1h 21mBeginner2026-05-11
Authors
Laurence Moroney
Course details
Most engineers work alongside AI systems every day without fully understanding how those systems function—and that gap creates real challenges when evaluating solutions, building pipelines, or collaborating with data science teams. In this course, join instructor and AI expert Laurence Moroney as he outlines the core technical foundations you need to work confidently with AI. Learn how to distinguish between AI paradigms, recognize when a problem requires a learning-based approach versus traditional code, and evaluate AI systems using proper metrics and risk frameworks. Along the way, build your vocabulary for the core concepts that drive modern machine learning, including probabilistic models, optimization, and generalization. By the end of this course, you'll be equipped with in-demand skills to make informed technical decisions about AI—whether you're an early-career engineer, an aspiring ML practitioner, or just curious to learn more about how AI works.
Learning objectives
Classify problems correctly and recommend whether they require traditional programming, machine learning, or deep learning approaches based on data characteristics and task requirements.
Navigate the AI data workflow from feature extraction through model evaluation, identifying potential failure points like bias, overfitting, and inappropriate metrics.
Communicate effectively with AI specialists using proper vocabulary to discuss model architectures, training paradigms, and performance trade-offs in technical contexts.
Evaluate AI use cases critically by analyzing cost-benefit ratios, regulatory implications, and explainability requirements before committing to AI-based solutions.
Learning objectives
Classify problems correctly and recommend whether they require traditional programming, machine learning, or deep learning approaches based on data characteristics and task requirements.
Navigate the AI data workflow from feature extraction through model evaluation, identifying potential failure points like bias, overfitting, and inappropriate metrics.
Communicate effectively with AI specialists using proper vocabulary to discuss model architectures, training paradigms, and performance trade-offs in technical contexts.
Evaluate AI use cases critically by analyzing cost-benefit ratios, regulatory implications, and explainability requirements before committing to AI-based solutions.
Concepts
Introduction
- Why AI literacy matters for engineers
The AI Landscape
- Your AI career path - From code to intelligence
- Deterministic vs. probabilistic - Traditional vs. generative AI
- The AI taxonomy - AI, ML, and deep learning explained
- Narrow AI vs. AGI - What engineers should know
- The AI data workflow - From raw data to predictions
Knowledge Representation and Reasoning
- Search algorithms - How machines find solutions
- Knowledge graphs and ontologies - Structuring intelligence
- Logic- and rule-based systems - The original AI
- Why explicit programming falls short
The Shift to Machine Learning
- What is a model The core of ML
- Feature extraction and vectors - Turning reality into data
- Supervised learning - Teaching with labels
- Unsupervised learning - Discovering hidden patterns
- Reinforcement learning - Learning through rewards
- Training vs. inference - Building vs. using models
The Neural Revolution and GenAI
- Deep learning - Power through layers
- The perceptron - Birth of neural networks
- Generative AI - Machines that create
- Large language models - Why they matter
- Diffusion models - Generating images with math
Evaluating and Deploying AI
- Metrics that matter - Beyond accuracy
- Overfitting and underfitting - Avoiding model pitfalls
- Bias in, bias out - Detecting and mitigating bias
- Explainability and trust - Making AI transparent
- Choosing the right use case - When AI makes sense
Conclusion
- Your next steps in AI engineering