Introduction to Deep Learning

Développez vos compétences avec Coursera Plus pour 239 $/an (habituellement 399 $). Économisez maintenant.

Ce cours n'est pas disponible en Français (France)

Nous sommes actuellement en train de le traduire dans plus de langues.

Introduction to Deep Learning

Ce cours fait partie de Spécialisation "Machine Learning: Theory and Hands-on Practice with Python"

Instructeur : Daniel E. Acuna

Inclus avec

5 modules

Obtenez un aperçu d'un sujet et apprenez les principes fondamentaux.

niveau Intermédiaire

Expérience recommandée

2 semaines à compléter

à 10 heures par semaine

Planning flexible

Apprenez à votre propre rythme

5 modules

Obtenez un aperçu d'un sujet et apprenez les principes fondamentaux.

niveau Intermédiaire

Expérience recommandée

2 semaines à compléter

à 10 heures par semaine

Planning flexible

Apprenez à votre propre rythme

Ce que vous apprendrez

Explain the mathematical foundations of neural networks and how they learn from data.
Train and regularize deep neural networks for effective generalization.
Design and apply specialized neural network architectures for images and sequences.
Apply transformer-based and multimodal models to real-world scenarios.

Compétences que vous acquerrez

Catégorie : Recurrent Neural Networks (RNNs)
Catégorie : Artificial Intelligence and Machine Learning (AI/ML)
Catégorie : Network Architecture
Catégorie : Natural Language Processing
Catégorie : Large Language Modeling
Catégorie : Network Model
Catégorie : Embeddings

Outils que vous découvrirez

Catégorie : PyTorch (Machine Learning Library)
Catégorie : Keras (Neural Network Library)
Catégorie : Vision Transformer (ViT)

Détails à connaître

Certificat partageable

Ajouter à votre profil LinkedIn

Récemment mis à jour !

janvier 2026

Évaluations

6 devoirs

Enseigné en Anglais

Découvrez comment les employés des entreprises prestigieuses maîtrisent des compétences recherchées

En savoir plus sur Coursera pour les affaires

logos de Petrobras, TATA, Danone, Capgemini, P&G et L'Oreal

Élaborez votre expertise du sujet

Ce cours fait partie de la Spécialisation "Machine Learning: Theory and Hands-on Practice with Python"

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 5 modules dans ce cours

Introduction to Deep Learning provides a rigorous, concept-driven introduction to the models that power modern AI systems—from image recognition to large language models. You’ll build neural networks from first principles, understanding how forward passes, loss functions, and backpropagation enable learning. As the course progresses, you’ll train and regularize deep models, design convolutional networks for vision, model sequences with RNNs, LSTMs, and attention, and apply transformer-based architectures such as BERT, GPT, and Vision Transformers. You will also look at the latest trends in contrastive learning and CLIP. By combining mathematical foundations with practical application, this course equips you to understand, train, and use deep learning models with confidence.

This course can be taken for academic credit as part of CU Boulder’s Masters of Science in Computer Science (MS-CS), Master of Science in Artificial Intelligence (MS-AI), and Master of Science in Data Science (MS-DS) degrees offered on the Coursera platform. These fully accredited graduate degrees offer targeted courses, short 8-week sessions, and pay-as-you-go tuition. Admission is based on performance in three preliminary courses, not academic history. CU degrees on Coursera are ideal for recent graduates or working professionals. Learn more: MS in Artificial Intelligence: https://www.coursera.org/degrees/ms-artificial-intelligence-boulder MS in Computer Science: https://coursera.org/degrees/ms-computer-science-boulder MS in Data Science: https://www.coursera.org/degrees/master-of-science-data-science-boulder

Welcome to Introduction to Deep Learning. This module builds the mathematical foundations of neural networks. Starting from linear models, you will learn about the artificial neuron and develop the mathematics of gradient descent and backpropagation. The focus is on understanding how and why neural networks work through the underlying math—covering the forward pass, loss functions, and the chain rule to show how information flows through networks and how they learn from data.

Inclus

15 vidéos6 lectures2 devoirs1 devoir de programmation

15 vidéos Total 104 minutes

Machine Learning Introduction 2 minutes
Deep Learning Introduction 2 minutes
Academic Integrity and AI Use Policy for the Machine Learning Specialization 9 minutes
From Linear Regression to the Artificial Neuron 9 minutes
Activation Functions and Non-Linearity: The Mathematical Notation and Problem Setup 5 minutes
Activation Functions and Non-Linearity: Why Non-Linearity is Important 6 minutes
Activation Functions and Non-Linearity: Sigmoid Activation and its Gradient 10 minutes
Activation Functions and Non-Linearity: Rectified Linear Unit Activation and its Gradient 4 minutes
Activation Functions and Non-Linearity: Other Activations and How to Choose Among Them 4 minutes
Layers, Depth, and Forward Propagation 10 minutes
Matrix Notation and Dimensions 9 minutes
Loss Functions: MSE and Cross-Entropy 7 minutes
Gradient Descent: The Math of Optimization 8 minutes
The Chain Rule and Backpropagation 9 minutes
Backpropagation Through a Network 10 minutes

6 lectures Total 96 minutes

Course Updates and Accessibility Support 1 minute
Earn Academic Credit for Your Work! 10 minutes
Course Support 10 minutes
Assessment Expectations 5 minutes
Download the Recommended Reading for This Course 10 minutes
From Linear Models to Neural Networks - Recommended Reading 60 minutes

2 devoirs Total 35 minutes

AI Policy Quiz 5 minutes
Neural Network Foundations 30 minutes

1 devoir de programmation Total 60 minutes

Lab 1: Building and Training Your First Neural Network in Keras 60 minutes

This module focuses on training neural networks effectively. Topics include optimization algorithms, hyperparameter tuning, and regularization techniques to prevent overfitting and achieve good generalization. You will compare different optimizers like SGD, momentum, and Adam, understand how learning rate and batch size affect training dynamics, and apply weight decay, dropout, early stopping, and batch normalization.

Inclus

7 vidéos2 lectures1 devoir1 devoir de programmation

7 vidéos Total 43 minutes

SGD, Momentum, and Adam 8 minutes
Learning Rate and Batch Size 7 minutes
Epochs and Monitoring Training 6 minutes
Understanding Overfitting 6 minutes
L2 Regularization (Weight Decay) 6 minutes
Dropout 5 minutes
Early Stopping and Batch Normalization 7 minutes

2 lectures Total 90 minutes

Optimization Algorithms - Recommended Reading 60 minutes
Regularization Techniques - Recommended Reading 30 minutes

1 devoir Total 30 minutes

Training and Regularizing Neural Networks 30 minutes

1 devoir de programmation Total 60 minutes

Lab 2: Applying Regularization to Improve Model Generalization 60 minutes

This module introduces you to convolutional neural networks (CNNs), the foundation of modern computer vision. Topics include how convolutional and pooling layers work, CNN architecture design, and practical techniques like data augmentation and transfer learning. The module covers classic architectures like VGG and ResNet and explains why CNNs outperform fully-connected networks on image data.

Inclus

7 vidéos2 lectures1 devoir1 devoir de programmation

7 vidéos Total 51 minutes

Why CNNs for Images? 8 minutes
The Convolution Operation 8 minutes
Pooling Layers 5 minutes
CNN Architecture: Conv → Pool → Dense 7 minutes
VGG, ResNet, and Skip Connections 9 minutes
Data Augmentation 6 minutes
Transfer Learning 7 minutes

2 lectures Total 75 minutes

Introduction to CNNs - Recommended Reading 45 minutes
Training CNNs in Practice - Recommended Reading 30 minutes

1 devoir Total 30 minutes

Convolutional Neural Networks for Image Recognition 30 minutes

1 devoir de programmation Total 60 minutes

Lab 3: Training a CNN for Image Classification with Augmentation 60 minutes

This module covers sequence modeling, starting with recurrent neural networks (RNNs) and long short-term memory networks (LSTMs), then progressing to the attention mechanism—the key innovation that led to transformers. Topics include how RNNs maintain hidden states across time steps, why the vanishing gradient problem motivated LSTMs, and how attention allows models to focus on relevant parts of their input.

Inclus

7 vidéos1 lecture1 devoir1 devoir de programmation

7 vidéos Total 48 minutes

Sequential Data and RNN Architecture 7 minutes
Hidden State and Backprop Through Time 7 minutes
LSTM Architecture 7 minutes
The Attention Mechanism 8 minutes
Self-Attention and QKV 8 minutes
Multi-Head Attention 4 minutes
Positional Encoding 6 minutes

1 lecture Total 60 minutes

Recurrent Neural Networks - Recommended Reading 60 minutes

1 devoir Total 30 minutes

Sequence Modeling – RNNs, LSTMs, and the Attention Mechanism 30 minutes

1 devoir de programmation Total 60 minutes

Lab 4: Building a Sequence Model with Attention 60 minutes

This final module covers the transformer architecture, which has revolutionized deep learning across domains. Topics include BERT and GPT as encoder-only and decoder-only variants, Vision Transformers (ViT) that apply attention to images, and CLIP for multimodal learning connecting vision and language. The module emphasizes applying pre-trained models to real tasks.

Inclus

8 vidéos1 lecture1 devoir1 devoir de programmation

8 vidéos Total 50 minutes

The Transformer Architecture 6 minutes
Encoder and Decoder Structure 7 minutes
Layer Normalization in Transformers 6 minutes
BERT: Encoder-Only Transformer 5 minutes
GPT: Decoder-Only Transformer 5 minutes
Vision Transformer (ViT) 7 minutes
CLIP and Contrastive Learning 5 minutes
Zero-Shot Classification with CLIP 9 minutes

1 lecture Total 30 minutes

The Transformer Architecture - Recommended Reading 30 minutes

1 devoir Total 30 minutes

Transformers, Vision Transformers, and CLIP 30 minutes

1 devoir de programmation Total 60 minutes

Lab 5: Using Pre-trained Vision Transformers and CLIP for Image Classification 60 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.

Instructeur

Daniel E. Acuna

University of Colorado Boulder

3 Cours 3 302 apprenants

Offert par

University of Colorado Boulder

En savoir plus sur Machine Learning

Pearson
Learning Deep Learning: Unit 1
Cours
MathWorks
Introduction to Deep Learning for Computer Vision
Cours
IBM
Introduction to Deep Learning & Neural Networks with Keras
Cours
University of Colorado Boulder
Deep Learning Applications for Computer Vision
Cours

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.’

Ouvrez de nouvelles portes avec Coursera Plus

Accès illimité à 10,000+ cours de niveau international, projets pratiques et programmes de certification prêts à l'emploi - tous inclus dans votre abonnement.

Faites progresser votre carrière avec un diplôme en ligne

Obtenez un diplôme auprès d’universités de renommée mondiale - 100 % en ligne

Découvrir les diplômes

Rejoignez plus de 3 400 entreprises mondiales qui ont choisi Coursera pour les affaires

Améliorez les compétences de vos employés pour exceller dans l’économie numérique

Foire Aux Questions

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.

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.

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.