We may earn an affiliate commission when you visit our partners.
Modèles de séquence
Andrew Ng,
Kian Katanforoosh,
and
Younes Bensouda Mourri
Andrew Ng,
Kian Katanforoosh,
and
Younes Bensouda Mourri
Cette formation vous apprendra à construire des modèles pour le langage naturel, l’audio et les autres données de séquence. Grâce à l’apprentissage profond, les algorithmes de séquence fonctionnent beaucoup mieux qu’il y a deux ans ; nous disposons donc de nombreuses applications très intéressantes en matière de reconnaissance vocale, de synthèse musicale, de chatbots, de traduction automatique, de compréhension naturelle du langage, etc.
Read more
Cette formation vous apprendra à construire des modèles pour le langage naturel, l’audio et les autres données de séquence. Grâce à l’apprentissage profond, les algorithmes de séquence fonctionnent beaucoup mieux qu’il y a deux ans ; nous disposons donc de nombreuses applications très intéressantes en matière de reconnaissance vocale, de synthèse musicale, de chatbots, de traduction automatique, de compréhension naturelle du langage, etc.
Read more
Cette formation vous apprendra à construire des modèles pour le langage naturel, l’audio et les autres données de séquence. Grâce à l’apprentissage profond, les algorithmes de séquence fonctionnent beaucoup mieux qu’il y a deux ans ; nous disposons donc de nombreuses applications très intéressantes en matière de reconnaissance vocale, de synthèse musicale, de chatbots, de traduction automatique, de compréhension naturelle du langage, etc.
Vous allez:
- Comprendre comment construire et former des réseaux neuronaux récurrents (RNN) et des variantes couramment utilisées telles que les GRU et les LSTM.
- Être capable d’appliquer des modèles de séquence à des problèmes de langage naturel, y compris la synthèse de texte.
- Pouvoir appliquer des modèles de séquence à des applications audio, incluant la reconnaissance vocale et la synthèse musicale.
C’est le cinquième et dernier cours de la spécialisation Apprentissage profond.
deeplearning.ai travaille également en partenariat avec le NVIDIA Deep Learning Institute (DLI) dans le cours 5, Modèles de séquence, afin de fournir une affectation de programmation sur la traduction automatique avec l’apprentissage en profondeur. Vous aurez la possibilité de construire un projet d’apprentissage en profondeur avec un contenu de pointe, pertinent pour l’industrie.
Register for this course and see more details by visiting:
OpenCourser.com/course/zrziy6/modeles
What's inside
Syllabus
Réseaux neuronaux récurrents
Découvrez les réseaux neuronaux récurrents. Ce type de modèle s’est avéré extrêmement performant sur les données temporelles. Il comporte plusieurs variantes, y compris les LSTM, les GRU et les RNN bidirectionnels, que vous allez découvrir dans cette section.
Read more
Syllabus
Réseaux neuronaux récurrents
Découvrez les réseaux neuronaux récurrents. Ce type de modèle s’est avéré extrêmement performant sur les données temporelles. Il comporte plusieurs variantes, y compris les LSTM, les GRU et les RNN bidirectionnels, que vous allez découvrir dans cette section.
Read more
Traitement automatique du langage naturel et prolongements lexicaux
Le traitement du langage naturel avec l'apprentissage profond est une combinaison importante. En utilisant des représentations de vecteurs de mots et des couches de prolongements, vous pouvez former des réseaux neuronaux récurrents avec des performances exceptionnelles, dans une grande variété de secteurs. Des exemples d’applications sont l’analyse de sentiments, la reconnaissance d’entités nommées et la traduction automatique.
Modèles de séquence et mécanisme d’attention
Les modèles de séquence peuvent être améliorés à l’aide d’un mécanisme d’attention. Cet algorithme aidera votre modèle à comprendre où celui-ci doit focaliser son attention, compte tenu d’une séquence d’entrées. Cette semaine, vous apprendrez également à reconnaître la parole et à gérer les données audio.
Good to know
Good to know
Know what's good ,
what to watch for , and
possible dealbreakers
Développe les modèles de séquence, qui sont essentiels pour traiter des données audio et linguistiques
Enseigne les réseaux neuronaux récurrents, notamment les LSTM et les GRU, qui sont très efficaces pour les données temporelles
Fournit des affectations de programmation pratique sur la traduction automatique avec l'apprentissage en profondeur
S'appuie sur des représentations de vecteurs de mots et des couches de prolongements pour optimiser le traitement du langage naturel
Intègre un mécanisme d'attention pour améliorer la compréhension des modèles de séquence
Nécessite des connaissances préalables en apprentissage profond
Save this course
Save Modèles de séquence to your list so you can find it easily later:
Save
Save
Activities
Coming soon
We're preparing activities for
Modèles de séquence.
These are activities you can do either before, during, or after a course.
Career center
Learners who complete Modèles de séquence will develop knowledge and skills
that may be useful to these careers:
NLP Engineer
NLP Engineer
NLP Engineers develop and maintain cutting-edge technology for natural language processing, working to improve communication between computers and humans. The course will help you build a great foundation for this career by helping you build a strong understanding of foundational concepts in NLP, such as recurrent neural networks, word vector representations, and attention mechanisms. These concepts are all essential for developing the next generation of NLP applications.
Machine Learning Engineer
Machine Learning Engineer
Machine Learning Engineers develop and maintain machine learning models, working to improve the accuracy and efficiency of these models. The course will introduce you to foundational concepts in machine learning, such as recurrent neural networks, word vector representations, and attention mechanisms. These concepts are all essential for developing the next generation of machine learning models.
Data Scientist
Data Scientist
Data Scientists use their expertise in statistics and programming to analyze data and extract meaningful insights. This course offers a strong introduction to topics like recurrent neural networks, word vector representations, and attention mechanisms, which are highly relevant to data science. Working with these topics can help you build a better foundation in data science.
Natural Language Processing Researcher
Natural Language Processing Researcher
Natural Language Processing Researchers develop new methods for processing and understanding natural language. This course will provide you with a number of valuable skills for this career, including experience with recurrent neural networks, word vector representations, and attention mechanisms. These concepts are at the forefront of NLP research, so you'll gain an edge over other candidates by learning about them.
Speech Recognition Engineer
Speech Recognition Engineer
Speech Recognition Engineers develop and maintain speech recognition systems, working to improve the accuracy and efficiency of these systems. This course will help you build a great foundation for this career by helping you build a strong understanding of foundational concepts in speech recognition, such as recurrent neural networks, word vector representations, and attention mechanisms. These concepts are all essential for developing the next generation of speech recognition systems.
Software Engineer
Software Engineer
Software Engineers design, develop, and maintain software applications. This course will provide you with a number of valuable skills for this career, including experience with recurrent neural networks, word vector representations, and attention mechanisms. These concepts are being increasingly used in software development, so you'll gain an edge over other candidates by learning about them.
Computational Linguist
Computational Linguist
Computational Linguists use their expertise in linguistics and computer science to develop new methods for processing and understanding natural language. This course may be useful for this career path, as it will introduce you to a number of relevant concepts, including recurrent neural networks, word vector representations, and attention mechanisms.
Machine Learning Researcher
Machine Learning Researcher
Machine Learning Researchers develop new methods for machine learning. This course may be useful for this career path, as it will introduce you to a number of relevant concepts, including recurrent neural networks, word vector representations, and attention mechanisms.
Data Analyst
Data Analyst
Data Analysts use their expertise in statistics and programming to analyze data and extract meaningful insights. This course may be useful for this career path, as it will introduce you to a number of relevant concepts, including recurrent neural networks, word vector representations, and attention mechanisms.
Artificial Intelligence Engineer
Artificial Intelligence Engineer
Artificial Intelligence Engineers develop and maintain artificial intelligence systems. This course may be useful for this career path, as it will introduce you to a number of relevant concepts, including recurrent neural networks, word vector representations, and attention mechanisms.
Business Analyst
Business Analyst
Business Analysts use their expertise in business and data analysis to identify and solve business problems. This course may be useful for this career path, as it will introduce you to a number of relevant concepts, including recurrent neural networks, word vector representations, and attention mechanisms.
Project Manager
Project Manager
Project Managers plan and execute projects. This course may be useful for this career path, as it will introduce you to a number of relevant concepts, including recurrent neural networks, word vector representations, and attention mechanisms.
Product Manager
Product Manager
Product Managers develop and manage products. This course may be useful for this career path, as it will introduce you to a number of relevant concepts, including recurrent neural networks, word vector representations, and attention mechanisms.
Technical Writer
Technical Writer
Technical Writers create and maintain technical documentation. This course may be useful for this career path, as it will introduce you to a number of relevant concepts, including recurrent neural networks, word vector representations, and attention mechanisms.
Teacher
Teacher
Teachers educate students in a variety of subjects. This course may be useful for this career path, as it will introduce you to a number of relevant concepts, including recurrent neural networks, word vector representations, and attention mechanisms.
For more career information including salaries, visit:
OpenCourser.com/course/zrziy6/modeles
Reading list
We've selected seven 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
Modèles de séquence.
Save
Comprehensive introduction to deep learning, covering the latest techniques and applications. It valuable resource for anyone who wants to learn about deep learning, regardless of their background.
Save
This comprehensive textbook introduces deep learning, covering theoretical and practical aspects. It provides a solid foundation for those new to the field and a valuable reference for experienced researchers.
Provides a comprehensive overview of speech and language processing, covering topics such as speech recognition, natural language processing, and machine translation. It valuable resource for anyone who wants to learn about these topics, regardless of their background.
This comprehensive textbook provides a solid foundation in speech recognition, covering both theory and practical applications.
Provides a comprehensive overview of natural language processing in Python, covering topics such as tokenization, stemming, and parsing. It valuable resource for anyone who wants to learn about these topics, regardless of their background.
Provides a comprehensive overview of deep learning with Python, covering topics such as neural networks, convolutional neural networks, and recurrent neural networks. It valuable resource for anyone who wants to learn about these topics, regardless of their background.
Save
Provides a comprehensive overview of natural language processing with R, covering topics such as tokenization, stemming, and parsing. It valuable resource for anyone who wants to learn about these topics, regardless of their background.
For more information about how these books relate to this course, visit:
OpenCourser.com/course/zrziy6/modeles
Share
Similar courses
Here are nine courses similar to
Modèles de séquence.
Serverless Machine Learning with Tensorflow on Google Cloud Platform en Français
OpenCourser.com/course/henc5x/serverless
Serverless Machine Learning with Tensorflow on Google...
Most relevant
Attention Mechanism - Français
OpenCourser.com/course/rt6lv9/attention
Attention Mechanism - Français
Most relevant
Créer une Fonction Personnalisée en JS et Google App Script
OpenCourser.com/course/n9pjwt/creer
Créer une Fonction Personnalisée en JS et Google App...
Most relevant
ChatGPT pour tous
OpenCourser.com/course/r4qnel/chatgpt
ChatGPT pour tous
Most relevant
Business Transformation with Google Cloud en Français
OpenCourser.com/course/3gguky/business
Business Transformation with Google Cloud en Français
Most relevant
Le solfège à votre portée
OpenCourser.com/course/ulf0hi/le
Le solfège à votre portée
Most relevant
Introduction à l’économétrie
OpenCourser.com/course/ytajxy/introduction
Introduction à l’économétrie
Most relevant
Vision artificielle et exploitation intelligente des ressources naturelles
OpenCourser.com/course/7liig4/vision
Vision artificielle et exploitation intelligente des...
Most relevant
Traitement d'images : introduction au filtrage
OpenCourser.com/course/ewf2wx/traitement
Traitement d'images : introduction au filtrage
Most relevant
Level
Intermediate
Via
Coursera
Institution
DeepLearning.AI
Instructors
Andrew Ng
Kian Katanforoosh
Younes Bensouda Mourri
Language
Français
Transcripts
English
Español
Português
中文
한국어
Pусский
Good to know
Développe les modèles de séquence, qui sont essentiels pour traiter des données audio et linguistiques
Enseigne les réseaux neuronaux récurrents, notamment les LSTM et les GRU, qui sont très efficaces pour les données temporelles
Fournit des affectations de programmation pratique sur la traduction automatique avec l'apprentissage en profondeur
S'appuie sur des représentations de vecteurs de mots et des couches de prolongements pour optimiser le traitement du langage naturel
Intègre un mécanisme d'attention pour améliorer la compréhension des modèles de séquence
Nécessite des connaissances préalables en apprentissage profond
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