Lorsque vous vous inscrivez à ce cours, vous êtes également inscrit(e) à cette Spécialisation.
Apprenez de nouveaux concepts auprès d'experts du secteur
Acquérez une compréhension de base d'un sujet ou d'un outil
Développez des compétences professionnelles avec des projets pratiques
Obtenez un certificat professionnel partageable
Il y a un module dans ce cours
Step confidently into the world of generative AI with our expertly crafted online course, designed to equip you with both foundational knowledge and hands-on experience in cutting-edge deep learning techniques. This course guides you through the essential concepts of how computers interpret and generate images and text, starting with the basics of image representation and progressing through advanced architectures like convolutional neural networks and autoencoders. You’ll explore the power of variational autoencoders and diffusion models, learning how these state-of-the-art tools drive modern image generation and enhancement. With practical exercises using industry-standard libraries such as PyTorch and Hugging Face, you’ll gain direct experience building and deploying generative models for both images and text. The course culminates with an in-depth look at natural language processing pipelines and transformer architectures, empowering you to harness large language models for real-world applications. By the end, you’ll have developed a robust skill set in generative AI, ready to innovate in research, creative industries, or technology-driven businesses. Join us and unlock your potential in the rapidly evolving field of artificial intelligence.
This module explores how generative models process and create images and text. Learners will understand image representation, convolutional neural networks, and autoencoders, progressing to variational autoencoders for probabilistic image generation. The module introduces diffusion models and practical image generation using Hugging Face’s diffusers library, including advanced tasks like interpolation and restoration. Shifting to text, it covers natural language processing pipelines, word embeddings, and the transformer architecture, culminating in hands-on experience with large language models using the Hugging Face Transformers library. By the end, students gain both theoretical knowledge and practical skills in multimodal generative AI.
Inclus
44 vidéos3 devoirs
Afficher les informations sur le contenu du module
44 vidéos•Total 416 minutes
Topics•1 minute
Representing Images as Tensors•8 minutes
Desiderata for Computer Vision•5 minutes
Features of Convolutional Neural Networks•8 minutes
Working with Images in Python•10 minutes
The FashionMNIST Dataset•5 minutes
Convolutional Neural Networks in PyTorch•11 minutes
Components of a Latent Variable Model (LVM)•9 minutes
The Humble Autoencoder•5 minutes
Defining an Autoencoder with PyTorch•6 minutes
Setting up a Training Loop•10 minutes
Inference with an Autoencoder•4 minutes
Look Ma, No Features!•8 minutes
Adding Probability to Autoencoders (VAE)•5 minutes
Variational Inference: Not Just for Autoencoders•7 minutes
Transforming an Autoencoder into a VAE•13 minutes
Training a VAE with PyTorch•14 minutes
Exploring Latent Space•12 minutes
Latent Space Interpolation and Attribute Vectors•13 minutes
Topics•1 minute
Generation as a Reversible Process•5 minutes
Sampling as Iterative Denoising•4 minutes
Diffusers and the Hugging Face Ecosystem•7 minutes
Generating Images with Diffusers Pipelines•28 minutes
Deconstructing the Diffusion Process•19 minutes
Forward Process as Encoder•17 minutes
Reverse Process as Decoder•7 minutes
Interpolating Diffusion Models•9 minutes
Image-to-Image Translation with SDEdit•8 minutes
Image Restoration and Enhancement•11 minutes
Topics•1 minute
The Natural Language Processing Pipeline•13 minutes
Generative Models of Language•10 minutes
Generating Text with Transformers Pipelines•15 minutes
Deconstructing Transformers Pipelines•8 minutes
Decoding Strategies•13 minutes
Transformers are Just Latent Variable Models for Sequences•12 minutes
Visualizing and Understanding Attention•24 minutes
Turning Words into Vectors•11 minutes
The Vector Space Model•7 minutes
Embedding Sequences with Transformers•10 minutes
Computing the Similarity Between Embeddings•8 minutes
Semantic Search with Embeddings•7 minutes
Contrastive Embeddings with Sentence Transformers•7 minutes
3 devoirs•Total 90 minutes
Latent Space Rules Everything Around Me Quiz•30 minutes
Demystifying Diffusion Quiz•30 minutes
Generating and Encoding Text with Transformers Quiz•30 minutes
Obtenez un certificat professionnel
Ajoutez ce titre à votre profil LinkedIn, à votre curriculum vitae ou à votre CV. Partagez-le sur les médias sociaux et dans votre évaluation des performances.
The World’s Leading Learning Company
Pearson provides in-demand training and expert resources across business, technology, and professional development.
Designed to help learners at all levels gain new skills, advance their careers, and stay competitive in a rapidly changing world, Pearson's expert-led courses offer practical, real-world knowledge from industry leaders. Whether you're preparing for a certification, enhancing workplace skills, or driving impact in your organization, Pearson is your trusted partner in lifelong learning.
Explore Pearson's courses and take the next step in your professional journey.
Pour quelles raisons les étudiants sur Coursera nous choisissent-ils pour leur carrière ?
Felipe M.
Étudiant(e) depuis 2018
’Pouvoir suivre des cours à mon rythme à été une expérience extraordinaire. Je peux apprendre chaque fois que mon emploi du temps me le permet et en fonction de mon humeur.’
Jennifer J.
Étudiant(e) depuis 2020
’J'ai directement appliqué les concepts et les compétences que j'ai appris de mes cours à un nouveau projet passionnant au travail.’
Larry W.
Étudiant(e) depuis 2021
’Lorsque j'ai besoin de cours sur des sujets que mon université ne propose pas, Coursera est l'un des meilleurs endroits où se rendre.’
Chaitanya A.
’Apprendre, ce n'est pas seulement s'améliorer dans son travail : c'est bien plus que cela. Coursera me permet d'apprendre sans limites.’
When will I have access to the lectures and assignments?
To access the course materials, assignments and to earn a Certificate, you will need to purchase the Certificate experience when you enroll in a course. You can try a Free Trial instead, or apply for Financial Aid. The course may offer 'Full Course, No Certificate' instead. This option lets you see all course materials, submit required assessments, and get a final grade. This also means that you will not be able to purchase a Certificate experience.
What will I get if I subscribe to this Specialization?
When you enroll in the course, you get access to all of the courses in the Specialization, and you earn a certificate when you complete the work. Your electronic Certificate will be added to your Accomplishments page - from there, you can print your Certificate or add it to your LinkedIn profile.
Is financial aid available?
Yes. In select learning programs, you can apply for financial aid or a scholarship if you can’t afford the enrollment fee. If fin aid or scholarship is available for your learning program selection, you’ll find a link to apply on the description page.