Curso práctico y aplicado para diseñar, construir y desplegar agentes de IA y chatbots que resuelvan problemas de negocio reales utilizando modelos de lenguaje grandes (LLMs). Los conceptos técnicos (atención, embeddings, tokens, function calling, RAG, multi-agente) se explican con analogías intuitivas y demostraciones en vivo, sin matemáticas profundas, manteniendo el rigor conceptual requerido a nivel de maestría.
Al finalizar el curso, cada estudiante despliega un prototipo funcional construido sobre plataformas no-code / low-code gratuitas, acompañado de métricas de desempeño, documentación técnica y un análisis de consideraciones éticas alineado con frameworks internacionales (EU AI Act, NIST AI RMF).
- Teacher: Andres Felipe Quintero Parra
This course builds upon foundational Machine Learning knowledge and focuses on the transition from classical algorithms to modern Deep Learning systems. Students will learn how to design, train, and deploy neural networks for real-world applications, moving from traditional feature engineering to representation learning. The course emphasizes hands-on experimentation, real-world use cases, and the integration of modern AI tools such as Claude Code, OpenAI Codex, GitHub Copilot, and large language models (LLMs). Students will work across two learning tracks (low-code and high-code), allowing them to either focus on conceptual understanding and applied AI tools or develop advanced programming and model implementation skills.
By the end of the course, students will be able to build end-to-end deep learning solutions and understand how modern AI systems are developed and deployed in practice.
- Teacher: Jhonathan Barrios
This course builds upon foundational Machine Learning knowledge and focuses on the transition from classical algorithms to modern Deep Learning systems. Students will learn how to design, train, and deploy neural networks for real-world applications, moving from traditional feature engineering to representation learning. The course emphasizes hands-on experimentation, real-world use cases, and the integration of modern AI tools such as Claude Code, OpenAI Codex, GitHub Copilot, and large language models (LLMs). Students will work across two learning tracks (low-code and high-code), allowing them to either focus on conceptual understanding and applied AI tools or develop advanced programming and model implementation skills.
By the end of the course, students will be able to build end-to-end deep learning solutions and understand how modern AI systems are developed and deployed in practice.
- Teacher: Jhonathan Barrios
This course provides a conceptually integrated and application-driven introduction to solid-state physics, connecting fundamental physical principles with real-world technologies. The course progresses from thermodynamics and electromagnetic interactions to the microscopic and quantum description of materials, enabling students to understand how material properties emerge from atomic-scale phenomena.
Students will explore thermal behavior, electrical conductivity, electromagnetic response, and quantum properties of solids, including electron transport, band structure, and material interactions with radiation. The course emphasizes the transition from classical to quantum models, culminating in applications such as semiconductors, photovoltaic systems, magnetic materials, and advanced imaging technologies (MRI, PET, and electron microscopy).
Through simulations, virtual laboratories, and applied problem-solving, students will develop analytical and computational skills to model material behavior, evaluate system performance, and propose solutions in engineering and technological contexts.
- Teacher: Rodolfo Capdevilla