Topics
CMSC 170: Introduction to Artificial Intelligence
Embedded Files
::: Home > Topics
Mapping the Journey of Artificial Intelligence. AI is not just about coding smart systems—it’s about understanding the many ways intelligence can emerge, evolve, and interact with the world. The topics in this course are designed to help you discover how computation, data, and perception come together to create intelligent behavior. Through this journey, we explore how machines can learn from experience, reason about uncertainty, and respond to real-world challenges.
Whether you are curious about the logic behind intelligent decision-making, the mathematics of machine learning, or the engineering of interactive systems, this course will guide you through the key ideas that define modern AI.
Your AI Superpowers: Learning Outcomes
Your AI Superpowers: Learning Outcomes
By the time we wrap this course, we’ll be able to:
Break down the core ideas behind Artificial Intelligence – what it is, how it works, and why it’s kind of a big deal.
Use logic like pros, repping facts and rules in a way machines can actually understand (no vibes-only reasoning here).
Talk through where AI shows up in the real world – from smart assistants to game bots to self-driving cars (and yes, our TikTok algorithm too).
Code up smart search strategies that help machines solve problems faster than our average human guessing game.
Get real about the ethics – AI bias, big data drama, surveillance creep, and all the wild skibidi ways tech impacts society.
Do a deep dive into current AI research by flexing our lit review skills on a topic we actually care about (because as a true Iskolar ng Bayan, we’re not just here for surface-level takes just so we can rizz our future employers).
Note that the above learning outcomes is the verbatim statement as presented in the most recent course guide.
The AI Topics: A Map of the AI Mind
The AI Topics: A Map of the AI Mind
The course is divided into three major parts—each exploring a different lens through which intelligence can be understood. From the algorithms that power decision-making to the data that fuels machine learning and the systems that interact with the world, each part builds on the last to form a complete picture of artificial intelligence in action.
Thinking in Code: Intelligence from Computation
How do we formalize reasoning and decision-making into algorithms?
This part introduces the computational foundations of AI — the algorithms and representations that allow machines to reason, plan, and make decisions.
What is AI?
History and definitions of AI
Symbolic vs. sub-symbolic methods
AI paradigms: agents, rationality, and environment types
Intelligent Agents
Agent architectures and environments
Performance measures
PEAS framework
Uninformed (Blind) Search
State space and search trees
BFS, DFS, UCS
Search complexity and completeness
Informed (Heuristic) Search
Best-first search, A*
Heuristics and admissibility
Local search: hill climbing, simulated annealing
Genetic algorithm, ant colony optimization, artificial chemistry
Adversarial Search
Game trees and minimax
Alpha-beta pruning
Evaluation functions and cutoff
Propositional Logic
Syntax and semantics
Inference rules and models
Forward and backward chaining
First-order Logic
Quantifiers, variables, and inference
Knowledge bases
Unification and resolution
Planning
STRIPS representation
Forward and backward planning
Heuristics in planning
Probability in AI and Probabilistic Reasoning
Probability basics and Bayes' Rule
Conditional independence
Bayesian networks
Inference in Bayesian Networks
Exact and approximate inference
Sampling methods
Hidden Markov Models
Learning from the World: Intelligence from Data
How do machines learn and adapt from examples, patterns, and experience?
This part explores machine learning — how systems build knowledge from data rather than explicit programming.
Machine Learning
Supervised vs. unsupervised learning
Hypothesis spaces, generalization
Decision Trees & Naive Bayes
ID3, entropy, information gain
Naive Bayes classifier
Neural Networks & Perceptrons
Perceptron learning rule
Multi-layer networks
Overfitting and regularization
AI in the Wild: Intelligence Meets Reality
How do intelligent systems sense, act, and behave responsibly in the real world?
This part situates AI within its social and ethical contexts, focusing on how intelligence interacts with people, policy, and society.
AI Safety, Bias, and Policy
Bias and fairness
Autonomous agents and ethical concerns
AI and the future of work
The Journey Doesn’t End Here. The study of Artificial Intelligence is a study of ourselves—how we reason, learn, and create. As you move through these topics, you’ll see how each concept builds toward a broader understanding of intelligence as both a computational and human phenomenon. Whether you continue into research, industry, or interdisciplinary fields, the insights you gain here will prepare you to engage critically and creatively with the AI systems shaping our world.
Intelligence takes many forms—let’s explore how to build them.
Intelligence takes many forms—let’s explore how to build them.
Page updated
Report abuse