We may earn an affiliate commission when you visit our partners.
Rafael Crescenzi
and
Pablo Alejandro Albani
Este curso se centrará en la optimización de Redes Neuronales Profundas, cambiando la idea de que todo el proceso es una “caja negra”.
Comprenderá qué impulsa el rendimiento y podrá obtener mejores resultados de manera más sistemática
Entenderá cómo optimizar los principales Hiperparámetros y su implementación.
Además, aprenderá nuevos conceptos útiles para el entrenamiento de las redes como los mini-batch y las regularizaciones.
También, aprenderá a implementar una red neuronal utilizando TensorFlow
Register for this course and see more details by visiting:
OpenCourser.com/course/wxk8fw/optimizacion
What's inside
Syllabus
Aspectos prácticos del aprendizaje profundo
Se estudiará cómo configurar su aplicación de aprendizaje automático, separando los sets de entrenamiento y testeo. Se entenderá que es la regularización en una red neuronal y cómo definir el problema para poder optimizarlo.
Read more
Syllabus
Aspectos prácticos del aprendizaje profundo
Se estudiará cómo configurar su aplicación de aprendizaje automático, separando los sets de entrenamiento y testeo. Se entenderá que es la regularización en una red neuronal y cómo definir el problema para poder optimizarlo.
Read more
Algoritmos de Optimización
Se estudiarán los distintos métodos de optimización que se pueden utilizar en el entrenamiento de redes neuronales profundas. Además, se analizarán las ventajas de trabajar con minibatches para acelerar el proceso y los beneficios de aplicar una diminución progresiva a la tasa de aprendizaje.
Ajuste de Hiperparámetros, Normalización por lotes e implementación en Tensorflow
Se aprenderán las principales técnicas y opciones en el ajuste de Hiperparámetros, la normalización por lotes y se introducirá la librería Tensorflow para la implementación de redes neuronales en Python
Good to know
Good to know
Know what's good ,
what to watch for , and
possible dealbreakers
An exploration of fundamental Deep Learning concepts that teaches optimization methods for contemporary problems
Covers optimization algorithms, such as Gradient Descent, Batch Normalization, and Adaptive Moment Estimation
Equips learners with practical skills using TensorFlow
Guided by seasoned instructors, Rafael Crescenzi and Pablo Alejandro Albani
Save this course
Save Optimización de Redes Neuronales Profundas to your list so you can find it easily later:
Save
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 Optimización de Redes Neuronales Profundas with these
activities:
Familiarize yourself with TensorFlow
Show steps
Having a basic understanding of TensorFlow will improve your ability to connect to the concepts being discussed in the course.
Browse courses on
TensorFlow
Show steps
-
Read the TensorFlow documentation
-
Complete the TensorFlow tutorial
Follow along with a tutorial on optimizing Deep Neural Networks
Show steps
Following along with a tutorial will help you understand concepts on a deeper level, improving your learning outcomes.
Browse courses on
Optimization
Show steps
-
Find a tutorial on optimizing Deep Neural Networks
-
Follow the steps in the tutorial
Review the concepts of Deep Learning
Show steps
A quick review of the main concepts of Deep Learning will help you prepare for the course.
Browse courses on
Deep Learning
Show steps
-
Read an introduction to Deep Learning
-
Watch a video tutorial on Deep Learning
Four other activities
Expand to see all activities and additional details
Show all seven activities
Attend a 'Study Group' With Classmates
Show steps
Engaging with your classmates in a peer study group can provide you with new perspectives and deepen your understanding of the course material.
Show steps
-
Form a study group with other participants of the program
-
Meet up regularmente for study sessions
-
Discuss and work through problems together
-
Quiz each other on coursework
Optimize your models with Hyperparameter Tuning
Show steps
Hands-on practice with Hyperparameter Tuning will give you a deeper understanding of its practical applications.
Browse courses on
Hyperparameter Tuning
Show steps
-
Choose a machine learning model
-
Tune the hyperparameters of the model
-
Evaluate the performance of the model
Create a Deep Neural Network in TensorFlow
Show steps
Creating a real-world project will help you solidify the concepts taught in the course.
Browse courses on
Deep Neural Networks
Show steps
-
Design the architecture of the network
-
Implement the network in TensorFlow
-
Train the network on a dataset
-
Evaluate the performance of the network
Create a blog post on a topic related to the course
Show steps
Creating content about the course materials will help you gain a deeper understanding of the topics.
Browse courses on
Machine Learning
Show steps
-
Choose a topic related to the course
-
Research the topic
-
Write a blog post about the topic
-
Publish the blog post
Familiarize yourself with TensorFlow
Show steps
Having a basic understanding of TensorFlow will improve your ability to connect to the concepts being discussed in the course.
Browse courses on
TensorFlow
Show steps
Show steps
Show steps
- Read the TensorFlow documentation
- Complete the TensorFlow tutorial
Follow along with a tutorial on optimizing Deep Neural Networks
Show steps
Following along with a tutorial will help you understand concepts on a deeper level, improving your learning outcomes.
Browse courses on
Optimization
Show steps
Show steps
Show steps
- Find a tutorial on optimizing Deep Neural Networks
- Follow the steps in the tutorial
Review the concepts of Deep Learning
Show steps
A quick review of the main concepts of Deep Learning will help you prepare for the course.
Browse courses on
Deep Learning
Show steps
Show steps
Show steps
- Read an introduction to Deep Learning
- Watch a video tutorial on Deep Learning
Four other activities
Expand to see all activities and additional details
Show all seven activities
Attend a 'Study Group' With Classmates
Show steps
Engaging with your classmates in a peer study group can provide you with new perspectives and deepen your understanding of the course material.
Show steps
Show steps
Show steps
- Form a study group with other participants of the program
- Meet up regularmente for study sessions
- Discuss and work through problems together
- Quiz each other on coursework
Optimize your models with Hyperparameter Tuning
Show steps
Hands-on practice with Hyperparameter Tuning will give you a deeper understanding of its practical applications.
Browse courses on
Hyperparameter Tuning
Show steps
Show steps
Show steps
- Choose a machine learning model
- Tune the hyperparameters of the model
- Evaluate the performance of the model
Create a Deep Neural Network in TensorFlow
Show steps
Creating a real-world project will help you solidify the concepts taught in the course.
Browse courses on
Deep Neural Networks
Show steps
Show steps
Show steps
- Design the architecture of the network
- Implement the network in TensorFlow
- Train the network on a dataset
- Evaluate the performance of the network
Create a blog post on a topic related to the course
Show steps
Creating content about the course materials will help you gain a deeper understanding of the topics.
Browse courses on
Machine Learning
Show steps
Show steps
Show steps
- Choose a topic related to the course
- Research the topic
- Write a blog post about the topic
- Publish the blog post
Career center
Learners who complete Optimización de Redes Neuronales Profundas will develop knowledge and skills
that may be useful to these careers:
Deep Learning Engineer
Deep Learning Engineer
Deep Learning Engineers are responsible for developing and deploying deep learning models. They typically have a strong background in computer science and machine learning. This course would be of particular interest to Deep Learning Engineers, as it provides a comprehensive overview of the theory and practice of optimizing deep neural networks.
Computer Vision Engineer
Computer Vision Engineer
Computer Vision Engineers are responsible for developing computer vision systems, which are used in a variety of applications such as object detection, facial recognition, and medical imaging. This course can help Computer Vision Engineers gain the skills they need to optimize deep neural networks, which will enable them to develop more accurate and efficient computer vision systems. In particular, the course's coverage of regularization techniques and mini-batch optimization will be valuable to Computer Vision Engineers.
Natural Language Processing Engineer
Natural Language Processing Engineer
Natural Language Processing Engineers are responsible for developing natural language processing systems, which are used in a variety of applications such as machine translation, text summarization, and spam filtering. This course can help Natural Language Processing Engineers gain the skills they need to optimize deep neural networks, which will enable them to develop more accurate and efficient NLP systems. In particular, the course's coverage of regularization techniques and hyperparameter optimization will be valuable to Natural Language Processing Engineers.
Machine Learning Engineer
Machine Learning Engineer
Machine Learning Engineers design, develop, and maintain machine learning models. They may work on projects such as designing models for computer vision, natural language processing, or fraud detection. This course provides a strong foundation in the theory and practice of optimizing deep neural networks, which will be useful for aspiring Machine Learning Engineers.
Artificial Intelligence Engineer
Artificial Intelligence Engineer
Artificial Intelligence Engineers design, develop, and maintain artificial intelligence systems. This course can help Artificial Intelligence Engineers gain the skills they need to optimize deep neural networks, which will enable them to develop more advanced and effective AI systems.
Data Scientist
Data Scientist
Data Scientists analyze data to extract insights and make predictions. They may use machine learning models to identify trends, predict customer behavior, or optimize business processes. This course can help aspiring Data Scientists by teaching them how to optimize deep neural networks, an essential tool for many data science projects.
Research Scientist
Research Scientist
Research Scientists are responsible for conducting research in various scientific fields. This course can help Research Scientists in fields such as computer vision, natural language processing, or speech recognition gain the skills they need to optimize deep neural networks. In particular, the course's coverage of mini-batch optimization and Tensorflow implementation will be valuable to Research Scientists.
Software Engineer
Software Engineer
Software Engineers design, develop, and maintain software applications. While a background in deep learning is not always a requirement, it is becoming increasingly valuable in this field. This course can help Software Engineers gain the skills they need to optimize deep neural networks, which will enable them to develop more sophisticated and innovative software solutions.
Quantitative Analyst
Quantitative Analyst
Quantitative Analysts use mathematical and statistical models to analyze financial data. This course can help Quantitative Analysts gain the skills they need to optimize deep neural networks, which will enable them to develop more accurate and informative models. In particular, the course's coverage of regularization techniques and hyperparameter optimization will be valuable to Quantitative Analysts.
Statistician
Statistician
Statisticians collect, analyze, and interpret data to help solve problems in various fields. This course may be useful for aspiring Statisticians who are interested in using deep learning to analyze large datasets. The course's coverage of regularization techniques and mini-batch optimization will be particularly valuable for Statisticians.
Data Analyst
Data Analyst
Data Analysts collect, analyze, and interpret data to help businesses make informed decisions. This course may be useful for aspiring Data Analysts who are interested in using deep learning to analyze large datasets. The course's coverage of mini-batch optimization and Tensorflow implementation will be particularly valuable for Data Analysts.
Business Analyst
Business Analyst
Business Analysts help businesses understand their customers, processes, and technologies. This course may be useful for aspiring Business Analysts who are interested in using data science to improve business outcomes. The course's coverage of practical applications of deep learning will be particularly valuable for Business Analysts.
Operations Research Analyst
Operations Research Analyst
Operations Research Analysts use mathematical and analytical methods to solve complex problems in business and industry. This course may be useful for aspiring Operations Research Analysts who are interested in using deep learning to solve optimization problems. The course's coverage of hyperparameter optimization will be particularly valuable for Operations Research Analysts.
Biostatistician
Biostatistician
Biostatisticians use statistical methods to analyze biological data. This course may be useful for aspiring Biostatisticians who are interested in using deep learning to analyze large datasets. The course's coverage of regularization techniques will be particularly valuable for Biostatisticians.
Financial Analyst
Financial Analyst
Financial Analysts provide financial advice to individuals and organizations. This course may be useful for aspiring Financial Analysts who are interested in applying machine learning to financial data. The course's coverage of regularization techniques and hyperparameter optimization will be particularly valuable for Financial Analysts.
For more career information including salaries, visit:
OpenCourser.com/course/wxk8fw/optimizacion
Reading list
We've selected 11 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
Optimización de Redes Neuronales Profundas.
Save
Provides a comprehensive overview of deep learning, including the theoretical foundations, algorithms, and applications. It valuable resource for both beginners and experienced practitioners.
Save
Este libro proporciona una base sólida en el aprendizaje profundo, cubriendo los fundamentos teóricos y las aplicaciones prácticas. Es un recurso valioso para comprender los conceptos clave y las técnicas utilizadas en las redes neuronales profundas.
Este libro ofrece una guía completa para el aprendizaje automático práctico utilizando las bibliotecas Scikit-Learn, Keras y TensorFlow. Proporciona ejemplos detallados y código para ayudar a los estudiantes a desarrollar y evaluar modelos de redes neuronales profundas.
Este libro ofrece una visión general completa del aprendizaje automático y estadístico, cubriendo una amplia gama de técnicas, incluido el aprendizaje profundo. Proporciona una base sólida para los estudiantes que buscan comprender los fundamentos del campo.
Provides a comprehensive overview of deep learning for computer vision. It valuable resource for both beginners and experienced practitioners who want to use deep learning for computer vision.
Provides a comprehensive overview of pattern recognition and machine learning. It valuable resource for both beginners and experienced practitioners.
Provides a comprehensive overview of deep learning for natural language processing. It valuable resource for both beginners and experienced practitioners who want to use deep learning for natural language processing.
Este libro proporciona un enfoque práctico para el aprendizaje profundo utilizando la biblioteca fastai y PyTorch. Ofrece una guía paso a paso para construir y entrenar modelos de redes neuronales profundas, cubriendo temas como optimización, regularización y transferencia de aprendizaje.
Este libro proporciona una base sólida en los fundamentos matemáticos del aprendizaje automático, que son esenciales para comprender los algoritmos de optimización utilizados en el entrenamiento de redes neuronales profundas.
Provides a practical guide to deep learning using Python. It valuable resource for beginners and experienced practitioners who want to use Python for deep learning.
Este libro proporciona una base sólida en los fundamentos de la optimización, que es esencial para entender los algoritmos de optimización utilizados en el entrenamiento de redes neuronales profundas.
For more information about how these books relate to this course, visit:
OpenCourser.com/course/wxk8fw/optimizacion
Share
Similar courses
Here are nine courses similar to
Optimización de Redes Neuronales Profundas.
Aruba Mobility Basics for Spanish Speakers
OpenCourser.com/course/a4xuas/aruba
Aruba Mobility Basics for Spanish Speakers
Most relevant
Gestión de redes sociales
OpenCourser.com/course/ykense/gestion
Gestión de redes sociales
Most relevant
Smart grid: las redes eléctricas del futuro
OpenCourser.com/course/971kmy/smart
Smart grid: las redes eléctricas del futuro
Most relevant
Los bits y bytes de las redes informáticas
OpenCourser.com/course/4dvg56/los
Los bits y bytes de las redes informáticas
Most relevant
De me gusta a leads: interactúa con las y los clientes en línea
OpenCourser.com/course/91rl9n/de
De me gusta a leads: interactúa con las y los clientes en...
Most relevant
Redes de computadores
OpenCourser.com/course/dluerc/redes
Redes de computadores
Most relevant
Smart grid: fundamentos técnicos
OpenCourser.com/course/hsbc05/smart
Smart grid: fundamentos técnicos
Most relevant
Fundamentos de la publicidad en redes sociales
OpenCourser.com/course/xxrgfc/fundamentos
Fundamentos de la publicidad en redes sociales
Most relevant
Introducción al marketing en redes sociales
OpenCourser.com/course/o8yqey/introduccion
Introducción al marketing en redes sociales
Most relevant
Level
Intermediate
Via
Coursera
Institution
Universidad Austral
Instructors
Rafael Crescenzi
Pablo Alejandro Albani
Language
Español
Good to know
An exploration of fundamental Deep Learning concepts that teaches optimization methods for contemporary problems
Covers optimization algorithms, such as Gradient Descent, Batch Normalization, and Adaptive Moment Estimation
Equips learners with practical skills using TensorFlow
Guided by seasoned instructors, Rafael Crescenzi and Pablo Alejandro Albani
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