We may earn an affiliate commission when you visit our partners.
Course image
Andrew Ng, Kian Katanforoosh, and Younes Bensouda Mourri

Ce cours vous apprendra à créer des réseaux neuronaux convolutifs et à les appliquer aux données d'image. Grâce à l'apprentissage en profondeur, la vision par ordinateur fonctionne beaucoup mieux qu'il y a seulement deux ans, ce qui permet de nombreuses applications passionnantes allant de la conduite autonome en toute sécurité, à la reconnaissance faciale précise, à la lecture automatique des images radiologiques.

Read more

Ce cours vous apprendra à créer des réseaux neuronaux convolutifs et à les appliquer aux données d'image. Grâce à l'apprentissage en profondeur, la vision par ordinateur fonctionne beaucoup mieux qu'il y a seulement deux ans, ce qui permet de nombreuses applications passionnantes allant de la conduite autonome en toute sécurité, à la reconnaissance faciale précise, à la lecture automatique des images radiologiques.

Vous allez:

- Comprendre comment créer un réseau neuronal convolutif, notamment les variations récentes telles que les réseaux résiduels.

- Savoir appliquer les réseaux convolutifs aux tâches de détection et de reconnaissance visuelles.

- Savoir utiliser le transfert de style neuronal pour générer de l'art.

- Être à même d'appliquer ces algorithmes à une variété d'images, de vidéos et d'autres données 2D ou 3D.

Il s'agit du quatrième cours de spécialisation d'apprentissage approfondi.

Enroll now

Two deals to help you save

What's inside

Syllabus

Fondements des réseaux neuronaux convolutifs
Apprendre à mettre en œuvre les couches de base des CNN (mise en commun, convolutions) et à les empiler correctement dans un réseau profond pour résoudre les problèmes de classification d'images multi-classes.
Read more
Modèles convolutifs profonds : études de cas
Découvrir les astuces pratiques et les méthodes utilisées dans les CNN profonds directement à partir des articles de recherche.
Détection d'objets
Apprendre à appliquer vos connaissances des CNN à l'un des domaines les plus difficiles mais les plus sensibles de la vision par ordinateur : Détection d’objets.
Applications spéciales : Reconnaissance faciale et transfert de style neuronal
Découvrez comment les CNN peuvent être appliqués à plusieurs domaines, y compris la génération d'art et la reconnaissance faciale. Mettez en œuvre votre propre algorithme pour générer de l'art et reconnaître les visages !

Good to know

Know what's good
, what to watch for
, and possible dealbreakers
S'adresse aux débutants en réseaux convolutifs
Enseigne les dernières avancées en matière de réseaux convolutifs
Permet d'appliquer les réseaux convolutifs à des tâches de détection et de reconnaissance visuelle
Enseigne l'utilisation du transfert de style neuronal pour générer de l'art
Applique ces algorithmes à diverses images, vidéos et autres données 2D ou 3D
Requiert une connaissance pratique de l'apprentissage automatique

Save this course

Save Réseaux neuronaux convolutifs 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 Réseaux neuronaux convolutifs with these activities:
Discussion Forum on CNN Applications
Engage with fellow learners to exchange ideas and broaden your understanding of CNN applications in various fields.
Browse courses on Image Analysis
Show steps
  • Join the course discussion forum.
  • Participate in discussions on the latest advancements and use cases of CNNs.
  • Share your own insights and experiences with CNN applications.
TensorFlow Tutorial for Object Detection
Gain practical experience in implementing object detection models using TensorFlow, a widely used deep learning framework.
Browse courses on TensorFlow
Show steps
  • Follow the official TensorFlow tutorial on object detection.
  • Build a custom object detection model for a specific task, such as detecting cats or traffic signs.
  • Refine your model's performance by experimenting with hyperparameters and data augmentation techniques.
Review Convolutional Kernels
Deepen your understanding of convolutional kernels and their application in image processing, a foundational concept in CNNs.
Show steps
  • Reference your notes from a previous course or study resources on image processing.
  • Practice implementing convolutional operations using a programming language such as Python or C++.
  • Experiment with different kernel sizes and strides to observe their effects on feature maps.
Three other activities
Expand to see all activities and additional details
Show all six activities
CNN Research Paper Summary
Develop your critical thinking and communication skills by analyzing and summarizing a research paper on CNNs.
Browse courses on Image Analysis
Show steps
  • Select a recent and relevant research paper on CNNs.
  • Read and understand the paper, including its methodology, results, and conclusions.
  • Write a concise and informative summary of the paper's main findings.
CNN Architecture Analysis
Enhance your comprehension of different CNN architectures and their effectiveness in various image analysis tasks.
Browse courses on Deep Learning Models
Show steps
  • Study the architectures of popular CNNs such as VGG, ResNet, and Inception.
  • Compare and contrast the performance of different CNN architectures on benchmark datasets.
  • Implement a CNN architecture from scratch using a deep learning framework like TensorFlow or PyTorch.
Deep Learning (Adaptive Computation and Machine Learning Series)
Strengthen your theoretical foundation in deep learning and CNNs by reading a comprehensive textbook on the subject.
Show steps
  • Acquire the book and allocate time for regular reading.
  • Read and understand the chapters covering CNNs and their applications.
  • Work through the exercises and examples provided in the book to reinforce your understanding.

Career center

Learners who complete Réseaux neuronaux convolutifs will develop knowledge and skills that may be useful to these careers:
Computer Vision Engineer
Computer Vision Engineers apply deep learning and machine learning to solve computer vision problems, including but not limited to image classification, object detection, facial recognition, and medical imaging. Convolutional Neural Networks are used in many computer vision problems. Réseaux neuronaux convolutifs will teach you how to build them. Taking this course may help you succeed as a Computer Vision Engineer.
Deep Learning Engineer
Deep Learning Engineers develop deep learning solutions to problems involving large datasets and complex relationships between data. While many of their projects focus on computer vision, natural language processing, and speech recognition, they work on problems from all domains. Réseaux neuronaux convolutifs will teach you how to build deep neural networks, including convolutional neural networks. Taking this course will help you succeed as a Deep Learning Engineer.
Machine Learning Engineer
Machine Learning Engineers build and maintain machine learning models for various applications, including but not limited to image classification, natural language processing, and predictive analytics. While their work is broader in scope than Deep Learning Engineers, they frequently build convolutional neural networks as part of their work. Taking Réseaux neuronaux convolutifs may help you build a foundation to succeed as a Machine Learning Engineer.
Data Scientist
Data Scientists build and maintain machine learning models for various applications. Much of their work is focused on data preparation and model evaluation, but they must be able to build models when necessary. Réseaux neuronaux convolutifs may help you build a foundation to succeed as a Data Scientist.
Software Engineer
Software Engineers build and maintain software applications. While they do not typically specialize in a particular domain, they can still work on computer vision projects. Réseaux neuronaux convolutifs can teach you how to use convolutional neural networks, which are useful for computer vision projects.
Data Analyst
Data Analysts analyze data to extract insights and trends. While they do not typically specialize in a particular domain, they must be able to understand the technical details of the data they analyze. Réseaux neuronaux convolutifs may help you understand the technical details of computer vision data.
Financial Analyst
Financial Analysts analyze financial data to make recommendations about investments. While they do not typically specialize in a particular domain, they must be able to understand the technical details of the data they analyze. Réseaux neuronaux convolutifs may help you understand the technical details of deep learning models, which are used in some quantitative analysis, which in turn informs financial analysis.
Product Manager
Product Managers build and manage software products. While they do not typically specialize in a particular domain, they must be able to understand the technical details of their products. Réseaux neuronaux convolutifs may help you understand the technical details of computer vision products.
Consultant
Consultants provide advice and guidance to businesses on a variety of topics. While they do not typically specialize in a particular domain, they must be able to understand the technical details of the topics they advise on. Réseaux neuronaux convolutifs may help you understand the technical details of computer vision topics.
Quantitative Analyst
Quantitative Analysts use mathematical and statistical models to analyze financial data. While they do not typically specialize in a particular domain, they must be able to understand the technical details of the models they use. Réseaux neuronaux convolutifs may help you understand the technical details of deep learning models, which are used in some quantitative analysis.
Actuary
Actuaries use mathematical and statistical models to assess risk. While they do not typically specialize in a particular domain, they must be able to understand the technical details of the models they use. Réseaux neuronaux convolutifs may help you understand the technical details of deep learning models, which are used in some actuarial models.
Technical Writer
Technical Writers create documentation for software and other technical products. While they do not typically specialize in a particular domain, they must be able to understand the technical details of the products they document. Réseaux neuronaux convolutifs may help you understand the technical details of computer vision products.
Research Scientist
Research Scientists explore new algorithms and techniques to solve complex problems. While some specialize in a particular domain, others work on more general-purpose problems. Réseaux neuronaux convolutifs may help you build a foundation for your work as a Researcher, especially if you work on computer vision problems.
Statistician
Statisticians use mathematical and statistical models to analyze data. While they do not typically specialize in a particular domain, they must be able to understand the technical details of the models they use. Réseaux neuronaux convolutifs may help you understand the technical details of deep learning models, which are used in some statistical models.
Business Analyst
Business Analysts analyze business needs and develop solutions to meet those needs. While they do not typically specialize in a particular domain, they must be able to understand the technical details of the solutions they develop. Réseaux neuronaux convolutifs may help you understand the technical details of computer vision solutions.

Reading list

We've selected ten 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 Réseaux neuronaux convolutifs.
Ce livre est une référence complète sur l'apprentissage par renforcement. Il couvre les concepts de base des CNN et fournit des exemples pratiques.
Ce livre fournit un guide pratique pour la création et le déploiement de réseaux neuronaux convolutifs. Il est particulièrement utile pour les développeurs qui souhaitent appliquer les CNN à des applications du monde réel.
Ce livre est une référence complète sur l'apprentissage approfondi, couvrant les concepts fondamentaux, les architectures de réseau et les applications. Il est particulièrement utile pour fournir des connaissances de base et une compréhension approfondie des réseaux de neurones convolutifs.
Ce livre fournit un guide pratique pour l'utilisation de Scikit-Learn, Keras et TensorFlow pour l'apprentissage automatique. Il couvre les techniques de base des CNN et fournit des exemples pratiques.
Ce livre fournit un guide pratique pour l'utilisation des réseaux neuronaux convolutifs dans la vision par ordinateur. Il couvre les techniques de base des CNN et fournit des exemples pratiques.
Ce livre fournit une introduction pratique à l'apprentissage approfondi pour les professionnels. Il couvre les techniques de base des CNN et fournit des exemples pratiques.
Ce livre fournit une introduction complète à la vision par ordinateur, y compris les techniques de traitement d'image, la stéréovision et la reconnaissance d'objets. Il est utile pour fournir un contexte sur les applications des réseaux de neurones convolutifs en vision par ordinateur.
Ce livre couvre une large gamme de sujets en apprentissage automatique, y compris les réseaux de neurones artificiels, les machines à vecteurs de support et les arbres de décision. Il est utile pour fournir des connaissances de base sur les algorithmes d'apprentissage automatique qui sous-tendent les réseaux de neurones convolutifs.
Ce livre fournit un guide pratique pour mettre en œuvre des réseaux de neurones convolutifs à l'aide de la bibliothèque Python Keras. Il est utile pour les apprenants qui souhaitent acquérir une expérience pratique de la création et de la formation de réseaux de neurones convolutifs.
Ce livre fournit une introduction accessible à l'intelligence artificielle, y compris les réseaux de neurones. Il est utile pour les débutants qui souhaitent acquérir une compréhension de base des concepts clés.

Share

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

Similar courses

Here are nine courses similar to Réseaux neuronaux convolutifs.
Partager des données grâce à l'art de la visualisation
Most relevant
Initiation aux conteneurs avec Docker
Most relevant
L'analyse de données UX
Most relevant
Comptes nationaux trimestriels et indicateurs de...
Most relevant
Données au service de la santé de la population
Most relevant
Création de Designs Marketing avec Canva
Most relevant
Construire des wireframes (maquettes fonctionnelles) et...
Most relevant
L’IA pour tous
Most relevant
Fondamentaux de la science des données
Most relevant
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