INTRO-AI.AU1
Artificial Intelligence: Logic, Learning, and Problem Solving
Master AI logic, learning, and problem-solving. Develop robust intelligent systems with practical, hands-on training.
- Practice in 14 Laboratorios prácticos — nothing to install
- 10 Lecciones interactivas y 90 topics mapped to the official exam objectives
Beginner A tu propio ritmo · 1 año de acceso
14 LiveLabs prácticos
Practice real IT tasks in guided environments.
- Entornos reales
- Calificación automática
- Sin instalación
10Lecciones interactivas
90Topics
14Laboratorio en vivo
10Vídeos
100Tarjetas didácticas
100Glosario de términos
01 / Habilidades que obtendrás
What you will be able to do
Try Free →
No se requiere tarjeta de crédito
This Artificial Intelligence course online provides a rigorous foundation in AI logic, learning, and problem-solving. You'll tackle core concepts from propositional and first-order logic to advanced search algorithms, machine learning, and neural networks. With 14 hands-on labs and over 15 hours of video lessons, you'll gain practical experience in building intelligent systems. Understand that while AI offers powerful solutions, every design involves trade-offs between computational complexity and solution optimality. This isn't about magic; it's about engineering intelligent behavior through structured reasoning and adaptive learning.
- Logic-Based AI Systems: Master propositional and first-order logic for knowledge representation and inference, understanding their inherent limitations in real-world complexity and decidability.
- Algorithmic Problem Solving: Implement and analyze search algorithms (uninformed, heuristic) and game theory to navigate complex state spaces, recognizing the trade-off between optimality and computational cost.
- Machine Learning & Neural Networks: Apply foundational machine learning techniques like perceptrons, nearest neighbor methods, and backpropagation for data classification and pattern recognition, acknowledging data quality as a critical constraint.
- Reinforcement Learning: Design and simulate agents that learn optimal policies through interaction, understanding the challenge of balancing exploration versus exploitation in dynamic, uncertain environments.
Course Highlights
-
10 Lecciones estructuradas Cobertura completa de los objetivos principales del curso
-
14 LiveLabs prácticos Escenarios interactivos guiados con evaluación instantánea
-
1 año de acceso completo Aprendizaje a tu propio ritmo, accesible en cualquier momento y en todos los dispositivos
02 / Lecciones y laboratorios
See exactly what you will learn and practice
Plan de estudios
10 Lecciones interactivas · 90 topics01 Introduction 6 topics · 1 Laboratorio en vivo +
- What is Artificial Intelligence?
- The History of AI
- AI and Society
- Agents
- Knowledge-Based Systems
- Exercises
1 Laboratorio en vivo in this lesson — see the labs panel →
02 Propositional Logic 8 topics · 3 Laboratorio en vivo +
- Syntax
- Semantics
- Proof Systems
- Resolution
- Horn Clauses
- Computability and Complexity
- Applications and Limitations
- Exercises
3 Laboratorio en vivo in this lesson — see the labs panel →
03 First-Order Predicate Logic 10 topics · 1 Laboratorio en vivo +
- Syntax
- Semantics
- Quantifiers and Normal Forms
- Proof Calculi
- Resolution
- Automated Theorem Provers
- Mathematical Examples
- Applications
- Summary
- Exercises
1 Laboratorio en vivo in this lesson — see the labs panel →
04 Limitations of Logic 5 topics · 1 Laboratorio en vivo +
- The Search Space Problem
- Decidability and Incompleteness
- The Flying Penguin
- Modeling Uncertainty
- Exercises
1 Laboratorio en vivo in this lesson — see the labs panel →
05 Logic Programming with PROLOG 9 topics · 1 Laboratorio en vivo +
- PROLOG Systems and Implementations
- Simple Examples
- Execution Control and Procedural Elements
- Lists
- Self-modifying Programs
- A Planning Example
- Constraint Logic Programming
- Summary
- Exercises
1 Laboratorio en vivo in this lesson — see the labs panel →
06 Search, Games and Problem Solving 7 topics · 1 Laboratorio en vivo +
- Introduction
- Uninformed Search
- Heuristic Search
- Games with Opponents
- Heuristic Evaluation Functions
- State of the Art
- Exercises
1 Laboratorio en vivo in this lesson — see the labs panel →
07 Reasoning with Uncertainty 6 topics · 2 Laboratorio en vivo +
- Computing with Probabilities
- The Principle of Maximum Entropy
- Lexmed, an Expert System for Diagnosing Appendicitis
- Reasoning with Bayesian Networks
- Summary
- Exercises
2 Laboratorio en vivo in this lesson — see the labs panel →
08 Machine Learning and Data Mining 15 topics · 2 Laboratorio en vivo +
- Data Analysis
- The Perceptron, a Linear Classifier
- Nearest Neighbor Methods
- Data Normalization
- Quality Metrics for Classifiers
- Decision Tree Learning
- Cross-Validation and Overfitting
- Data Augmentation
- Learning of Bayesian Networks
- The Naive Bayes Classifier
- One-Class Learning
- Clustering
- Data Mining in Practice
- Summary
- Exercises
2 Laboratorio en vivo in this lesson — see the labs panel →
09 Neural Networks 11 topics · 1 Laboratorio en vivo +
- From Biology to Simulation
- Hopfield Networks
- Neural Associative Memory
- Linear Networks with Minimal Errors
- The Backpropagation Algorithm
- Deep Learning
- Creativity
- Transformers Take Over Natural Language Processing
- Support Vector Machines
- Summary and Outlook
- Exercises
1 Laboratorio en vivo in this lesson — see the labs panel →
10 Reinforcement Learning 13 topics · 1 Laboratorio en vivo +
- Introduction
- The Task
- Uninformed Combinatorial Search
- Value Iteration and Dynamic Programming
- A Learning Walking Robot and Its Simulation
- Q-Learning
- Exploration and Exploitation
- Approximation, Generalization, and Convergence
- Applications
- AlphaGo, the Breakthrough in Go
- Curse of Dimensionality
- Summary and Outlook
- Exercises
1 Laboratorio en vivo in this lesson — see the labs panel →
Laboratorios prácticos Our edge
14 Laboratorio en vivos- Understanding AI
- Converting Logical Expression into CNF
- Understanding CNF and Resolution
- Converting the Horn Clause into Implication Form
- Converting Sentences into FOL Form
- Understanding the Logical Limits of AI
- Understanding Logic Programming with PROLOG
- Exploring Game Strategies in AI
- Calculating the Conditional Probability
- Understanding Independent Events
- Computing Min-Max Normalization and Standardization (Z-Score)
- Evaluating Binary Classifiers
- Calculating the Total Squared Error
- Understanding Reinforcement Learning
Los laboratorios se ejecutan en tu navegador; no hay nada que instalar.
03 / Preguntas frecuentes
Preguntas antes de empezar
What foundational logic is covered in this Artificial Intelligence course online?+
This Artificial Intelligence Logic training online covers propositional logic, first-order predicate logic, and their respective proof systems like resolution. We also critically examine the inherent limitations of logic, such as the search space problem, decidability, and incompleteness, which are crucial for understanding real-world AI system constraints.
How practical is this Artificial Intelligence Problem Solving certification for real-world AI challenges?+
Highly practical. The course integrates 14 hands-on labs and 50 practice exercises, focusing on implementing search algorithms, logic programming with PROLOG, and applying machine learning techniques. You'll learn to approach problems like game playing and robotic control, understanding that real-world solutions often require balancing computational resources against desired performance.
Does this course involve programming, and what languages are used?+
Yes, programming is integral. The course includes dedicated sections on Logic Programming with PROLOG, providing practical experience in declarative programming for AI. While PROLOG is a focus, the algorithmic concepts for search, machine learning, and reinforcement learning are universally applicable and can be translated to other languages.
What level of machine learning and neural networks is covered?+
This course provides a solid foundation in machine learning and neural networks. You'll learn about data analysis, linear classifiers like the Perceptron, nearest neighbor methods, and the Backpropagation algorithm for neural networks. It's designed to build a strong conceptual and practical understanding, preparing you for more advanced topics, but it's not a deep learning specialization.
What are the key learning resources provided with this Artificial Intelligence Learning Problem Solving guide?+
You'll get access to 14 hands-on labs, 10 video lessons totaling over 15 hours, 94 practice quizzes, 100 flashcards, 50 practice exercises, and 10 comprehensive chapters. These resources are designed to reinforce your understanding of AI logic and reasoning, ensuring a robust learning experience.
Keep going
You might also like
Start Learning AI Logic Now
Learn logic, inference, and decision-making step by step. Work through guided exercises and apply concepts to real scenarios.
- 1 año de acceso completo
- 14 LiveLab incluido
- Certificado de finalización
No se requiere tarjeta de crédito