We may earn an affiliate commission when you visit our partners.
Course image
Luis Felipe Giraldo Trujillo and Pablo Andrés Arbeláez Escalante

El aprendizaje profundo actualmente es una parte central de la inteligencia artificial contemporánea, y se refiere al proceso realizado por los computadores para aprender de la experiencia permitiendo describir abstracciones complejas a partir de conceptos más simples de forma jerárquica. Este curso presenta una introducción al aprendizaje profundo, centrándose en los métodos más utilizados en diferentes contextos y tipos de datos. A lo largo del curso se estudiarán arquitecturas como redes neuronales artificiales, redes neuronales convolucionales, redes neuronales recurrentes, Transformers para lenguaje y para visión y redes generativas como las redes generativas adversarias y los modelos de difusión. Este es el único curso en español disponible en la plataforma que habla de las más recientes arquitecturas de aprendizaje profundo, como lo son los Transformers para visión.

Enroll now

What's inside

Syllabus

Módulo 1: Introducción al aprendizaje profundo
Este módulo proporciona una base sólida en los principios y conceptos fundamentales del Deep Learning. Desde su historia y evolución hasta las aplicaciones contemporáneas, exploraremos los temas clave que abren las puertas a esta disciplina. Estudiaremos los componentes esenciales de una red neuronal, incluida la estructura, las funciones de activación y las funciones de pérdida. Abordaremos también técnicas de optimización como el descenso del gradiente y la retropropagación, y exploraremos la importancia de los parámetros y los hiperparámetros. Al finalizar este módulo, los participantes tendrán una comprensión sólida de los fundamentos del Deep Learning y estarán preparados para profundizar en áreas más avanzadas de esta emocionante disciplina.
Read more
Módulo 2: Redes neuronales convolucionales y recurrentes
En este módulo especializado se exploran técnicas de aprendizaje profundo utilizadas en el procesamiento de datos secuenciales y en el análisis de imágenes. Durante este módulo, se espera que los participantes adquirieran los conocimientos necesarios para comprender y aplicar las redes neuronales convolucionales (CNNs) y las redes neuronales recurrentes (RNNs) en diversas tareas. Comenzaremos comparando las redes neuronales tradicionales (ANNs) con las redes neuronales convolucionales (CNNs), destacando la operación de convolución en las CNNs. Analizaremos la estructura de AlexNet, una arquitectura famosa en la comunidad de Deep Learning. Además, abordaremos la metodología de entrenamiento y definición de tareas para estas redes. A medida que avanzamos, exploraremos los desafíos que surgen al trabajar con datos secuenciales y la información dependiente del tiempo. Introduciremos el concepto de procesamiento de lenguaje natural y nos sumergiremos en las redes neuronales recurrentes (RNNs) y sus diferentes variantes. Discutiremos los tipos de RNNs y los retos que enfrentan, como la dependencia a largo plazo y el desvanecimiento o explosión del gradiente.
Módulo 3: Transformers
En este modulo se exploran los fundamentos y aplicaciones de los Transformers en el campo del aprendizaje profundo. A lo largo de este módulo, se espera que los participantes adquirieran conocimiento de las estructuras de los Transformers. Se explorarán aspectos claves como el embedding del texto, la codificación posicional y el mecanismo de atención, que permiten a los Transformers capturar relaciones complejas entre los elementos de una secuencia. Además, se abordarán particularidades como el pre-entrenamiento y el aprendizaje de transferencia, y se analizarán las aplicaciones de los Transformers tanto en el procesamiento del lenguaje natural como en el procesamiento de imágenes mediante la arquitectura Transformer Visual.
Módulo 4: Inteligencia artificial generativa
Este módulo explora las técnicas de generación de datos mediante modelos generativos. A lo largo de este módulo, se espera que los participantes adquieran los conocimientos necesarios para comprender y aplicar distintos enfoques en la generación de datos mediante Deep Learning. Comenzaremos analizando la diferencia entre modelos discriminativos y modelos generativos, y cómo estos últimos nos permiten crear contenido original. Exploraremos el concepto de espacio latente, donde la información se codifica para generar nuevas muestras. Además, estudiaremos la arquitectura de los generadores y discriminadores en el contexto de redes generativas adversariales (GANs). Aprenderemos sobre la metodología de entrenamiento y las funciones de pérdida utilizadas para optimizar estos modelos. Finalmente, exploraremos la intuición detrás de los modelos probabilísticos de difusión y su entrenamiento.

Good to know

Know what's good
, what to watch for
, and possible dealbreakers
Examines uses of learning for the purpose of practical application, which maps well to industry objectives
Provides a clear foundation for those new to Deep Learning before moving into more advanced topics
Taught by top instructors, Pablo Andrés Arbeláez Escalante and Luis Felipe Giraldo Trujillo
Introduces Convolutional Neural Networks and Recurrent Neural Networks, which are widely used in industrial image and sequence analysis applications
Covers Transformers, a hot topic in NLP, CV, and other domains
Provides guidance on Generative AI using GANs and Diffusion Models, which are gaining traction in the generative arts communities

Save this course

Save Introducción al deep learning contemporáneo to your list so you can find it easily later:
Save

Activities

Be better prepared before your course. Deepen your understanding during and after it. Supplement your coursework and achieve mastery of the topics covered in Introducción al deep learning contemporáneo with these activities:
Review Convolutional Neural Networks
Review the concepts and techniques related to Convolutional Neural Networks (CNNs) to strengthen your foundation in deep learning and computer vision.
Show steps
  • Read the course materials on CNNs.
  • Watch video tutorials or attend online workshops on CNNs.
  • Practice implementing CNNs using a programming language like Python or R.
Solve Deep Learning Coding Challenges
Engage in coding challenges that focus on implementing deep learning algorithms and models to solidify your understanding and enhance your problem-solving skills.
Browse courses on Deep Learning
Show steps
  • Join online coding platforms like LeetCode or HackerRank.
  • Select challenges related to deep learning and artificial intelligence.
  • Attempt to solve the challenges by implementing deep learning algorithms from scratch.
  • Review your solutions and identify areas for improvement.
Follow Online Tutorials on Advanced Deep Learning Techniques
Stay updated with the latest advancements in deep learning by following online tutorials or workshops that cover advanced techniques and applications, expanding your knowledge and skills.
Browse courses on Deep Learning
Show steps
  • Identify reputable platforms and resources for deep learning tutorials.
  • Search for tutorials that align with your interests and learning goals.
  • Follow the tutorials step-by-step and implement the techniques in your own projects.
Two other activities
Expand to see all activities and additional details
Show all five activities
Write a Technical Blog Post on a Deep Learning Topic
Enhance your understanding of deep learning by researching and writing a blog post on a specific topic, explaining the concepts and providing examples to deepen your knowledge and share it with others.
Browse courses on Deep Learning
Show steps
  • Choose a deep learning topic that you are interested in.
  • Research and gather information from reliable sources.
  • Organize your thoughts and create an outline.
  • Write the blog post in a clear and concise manner.
  • Edit and proofread your post.
Build a Deep Learning Project with a Real-World Dataset
Apply your deep learning knowledge by working on a project that involves collecting, cleaning, and analyzing a real-world dataset, and then building and evaluating a deep learning model to solve a specific problem.
Show steps
  • Identify a problem or task that you want to solve using deep learning.
  • Gather a relevant dataset and explore it.
  • Preprocess and clean the data.
  • Design and implement a deep learning model.
  • Train and evaluate your model.
  • Deploy your model and monitor its performance.

Career center

Learners who complete Introducción al deep learning contemporáneo will develop knowledge and skills that may be useful to these careers:
Data Scientist
Data Scientists use machine learning algorithms to analyze large datasets and extract insights. This course introduces the fundamental principles of deep learning, including neural networks, optimization techniques, and data preprocessing. These concepts are essential for aspiring Data Scientists who want to build and deploy deep learning models for data analysis and prediction.
Machine Learning Engineer
Machine Learning Engineers design, develop, and deploy machine learning models. This course provides a comprehensive overview of deep learning architectures, including convolutional neural networks, recurrent neural networks, and transformers. These architectures are widely used in machine learning applications such as image recognition, natural language processing, and speech recognition.
Artificial Intelligence Engineer
Artificial Intelligence Engineers design and develop AI systems. This course covers advanced deep learning techniques, such as generative adversarial networks and diffusion models, which are used in cutting-edge AI applications such as image synthesis, text generation, and language translation.
Computer Vision Engineer
Computer Vision Engineers develop algorithms and systems for analyzing and interpreting images and videos. This course includes a module on convolutional neural networks, which are the foundation of many computer vision applications such as object detection, image segmentation, and facial recognition.
Natural Language Processing Engineer
Natural Language Processing Engineers develop algorithms and systems for processing and understanding human language. This course includes a module on transformers, which are state-of-the-art models for natural language processing tasks such as machine translation, text summarization, and question answering.
Software Engineer
Software Engineers design, develop, and maintain software systems. While this course is not directly focused on software engineering, it provides a strong foundation in deep learning, which is increasingly used in software applications such as fraud detection, anomaly detection, and predictive analytics.
Data Analyst
Data Analysts collect, analyze, and interpret data to provide insights and support decision-making. This course may be useful for Data Analysts who want to expand their knowledge of deep learning and apply these techniques to data analysis tasks such as anomaly detection, forecasting, and customer segmentation.
Business Analyst
Business Analysts use data and analytics to identify and solve business problems. This course may be useful for Business Analysts who want to gain a deeper understanding of deep learning and its potential applications in business, such as market segmentation, customer churn prediction, and fraud detection.
Product Manager
Product Managers are responsible for managing the development and launch of new products. This course may be useful for Product Managers who want to gain a better understanding of deep learning and its potential applications in product development, such as personalized recommendations, user segmentation, and feature prioritization.
Marketing Manager
Marketing Managers are responsible for developing and executing marketing campaigns. This course may be useful for Marketing Managers who want to gain a better understanding of deep learning and its potential applications in marketing, such as customer segmentation, targeted advertising, and social media analytics.
Financial Analyst
Financial Analysts analyze financial data to make investment recommendations. This course may be useful for Financial Analysts who want to gain a better understanding of deep learning and its potential applications in finance, such as stock price prediction, credit risk assessment, and fraud detection.
Consultant
Consultants provide advice and expertise to businesses and organizations. This course may be useful for Consultants who want to gain a better understanding of deep learning and its potential applications in consulting, such as data analysis, process improvement, and risk management.
Researcher
Researchers conduct scientific research to advance knowledge and solve problems. This course may be useful for Researchers who want to gain a better understanding of deep learning and its potential applications in research, such as drug discovery, climate modeling, and materials science.
Educator
Educators teach students at all levels. This course may be useful for Educators who want to gain a better understanding of deep learning and its potential applications in education, such as personalized learning, adaptive assessments, and educational data mining.
Entrepreneur
Entrepreneurs start and run their own businesses. This course may be useful for Entrepreneurs who want to gain a better understanding of deep learning and its potential applications in entrepreneurship, such as product development, customer acquisition, and market research.

Reading list

We've selected six books that we think will supplement your learning. Use these to develop background knowledge, enrich your coursework, and gain a deeper understanding of the topics covered in Introducción al deep learning contemporáneo.
Provides a comprehensive overview of deep learning, covering the latest advances in the field. It valuable resource for students and researchers who want to learn more about deep learning.
Provides a comprehensive overview of natural language processing using Transformers, covering the latest advances in the field. It valuable resource for students and researchers who want to learn more about natural language processing.
Provides a practical guide to machine learning using Python, covering the latest libraries and techniques. It valuable resource for students and practitioners who want to learn more about machine learning.
Provides a practical guide to deep learning using Python, covering the latest libraries and techniques. It valuable resource for students and practitioners who want to learn more about deep learning.
Provides a comprehensive overview of deep learning, covering the latest advances in the field. It valuable resource for students and researchers who want to learn more about deep learning.
Provides a comprehensive overview of deep learning for computer vision, covering the latest advances in the field. It valuable resource for students and researchers who want to learn more about deep learning for computer vision.

Share

Help others find this course page by sharing it with your friends and followers:

Similar courses

Here are nine courses similar to Introducción al deep learning contemporáneo.
Our mission

OpenCourser helps millions of learners each year. People visit us to learn workspace skills, ace their exams, and nurture their curiosity.

Our extensive catalog contains over 50,000 courses and twice as many books. Browse by search, by topic, or even by career interests. We'll match you to the right resources quickly.

Find this site helpful? Tell a friend about us.

Affiliate disclosure

We're supported by our community of learners. When you purchase or subscribe to courses and programs or purchase books, we may earn a commission from our partners.

Your purchases help us maintain our catalog and keep our servers humming without ads.

Thank you for supporting OpenCourser.

© 2016 - 2024 OpenCourser