Practical Deep Learning with Python

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

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

Practical Deep Learning with Python

Ce cours fait partie de Spécialisation Mastering AI: Neural Nets, Vision System, Speech Recognition

Instructeur : Edureka

Inclus avec Coursera Plus

4 modules

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

niveau Intermédiaire

Expérience recommandée

11 heures pour terminer

3 semaines à 3 heures par semaine

Planning flexible

Apprenez à votre propre rythme

4 modules

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

niveau Intermédiaire

Expérience recommandée

11 heures pour terminer

3 semaines à 3 heures par semaine

Planning flexible

Apprenez à votre propre rythme

Ce que vous apprendrez

Understand the core components of deep learning models and their role in AI.
Apply CNN, R-CNN, and Faster R-CNN for object detection tasks.
Implement RNNs and LSTMs for sequential data processing.
Optimize and evaluate deep learning models for improved performance.

Détails à connaître

Certificat partageable

Ajouter à votre profil LinkedIn

Récemment mis à jour !

février 2025

Évaluations

13 devoirs

Enseigné en Anglais

Découvrez comment les employés des entreprises prestigieuses maîtrisent des compétences recherchées

En savoir plus sur Coursera pour les affaires

Élaborez votre expertise du sujet

Ce cours fait partie de la Spécialisation Mastering AI: Neural Nets, Vision System, Speech Recognition

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

Obtenez un certificat professionnel

Ajoutez cette qualification à votre profil LinkedIn ou à votre CV

Partagez-le sur les réseaux sociaux et dans votre évaluation de performance

Il y a 4 modules dans ce cours

Welcome to the Practical Deep Learning with Python course, where you'll gain hands-on experience with cutting-edge deep learning techniques to model and analyze complex datasets. Unlock the power of deep learning to solve real-world problems and uncover actionable insights from massive data volumes. This course explores industry-specific applications and equips you with the practical skills needed to build and optimize advanced models.

By the end of this course, you’ll be able to: - Describe the foundational components of deep learning models and their significance in artificial intelligence. - Illustrate the working of CNNs, R-CNNs, and Faster R-CNNs for object detection and related applications. - Understand the limitations of Perceptrons and how Multi-Layer Perceptrons (MLPs) address them. - Implement Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM) architectures for sequential data analysis. - Optimize and evaluate deep learning models to achieve higher accuracy and efficiency. This course is designed for data scientists, machine learning engineers, and AI enthusiasts with a foundational knowledge of Python and machine learning who aim to expand their expertise in deep learning. Experience in building machine learning models, along with knowledge of statistics and proficiency in Python programming, is recommended for this course. Embark on this educational journey to enhance your expertise in deep learning and elevate your capabilities in building intelligent systems for the future of artificial intelligence.

In this module, you will explore the fundamental components of deep learning by designing perceptron and implementing their functionality. You will address the limitations of perceptron by utilizing Multi-Layer Perceptron (MLPs) and observe how MLPs significantly enhance model performance.

Inclus

25 vidéos4 lectures4 devoirs2 sujets de discussion

25 vidéosTotal 113 minutes

Course Introduction4 minutesPrévisualiser le module
Environment Configuration1 minute
Machine Learning vs. Deep Learning5 minutes
What is Deep Learning?2 minutes
Neural Networks6 minutes
Artificial Neural Network (ANN)5 minutes
ANN: Types and Applications4 minutes
Forward Propagation4 minutes
Perceptron7 minutes
Learning Rate7 minutes
What is Activation Function? 4 minutes
Activation Function and it's Types4 minutes
Importance of Epoch5 minutes
Single Layer Perceptron - Define Sigmoid Function 5 minutes
Single Layer Perceptron - Decision Boundary6 minutes
Limitations of Single Layered Perceptron2 minutes
Multi-Layered Perceptron2 minutes
What is Backpropagation? 2 minutes
Backpropagation 3 minutes
Demonstration: Building a Simple Neural Network3 minutes
Demonstration: Understanding How Backpropagation has Worked4 minutes
Demonstration: Handwritten Digits Classification - Data Preprocessing 4 minutes
Demonstration: Handwritten Digits Classification- Designing the Model4 minutes
Demonstration: Handwritten Digits Classification - Optimizing the Model 5 minutes
Summary of Deep Learning Components5 minutes

4 lecturesTotal 40 minutes

Welcome to Practical Deep Learning with Python10 minutes
System Requirements and Pre-requisite for Studying Deep Learning10 minutes
Learning Rate in Deep Learning10 minutes
Hebbian Learning Algorithm10 minutes

4 devoirsTotal 48 minutes

Knowledge Check : Deep Learning Components30 minutes
Practice Quiz : Environment Set-Up and Configuration6 minutes
Practice Quiz : Essentials for Deep Learning6 minutes
Practice Quiz : Building Perceptron and it's Working6 minutes

2 sujets de discussionTotal 20 minutes

Introduce Yourself10 minutes
What are the structural and functional similarities between the human brain and neural networks?10 minutes

In the second module of this course, learners will learn about the working of Convolutional Neural Networks (CNN) and understand their importance in training deep learning models. Learners will also work on improving CNN model performance using RCNN and Faster RCNN, observe the computation time of these models, and gauge their accuracy score.

Inclus

27 vidéos3 lectures4 devoirs1 sujet de discussion

27 vidéosTotal 126 minutes

Limitations of MLP3 minutesPrévisualiser le module
MLP Limitations: Resolving the Issue with CNN3 minutes
Visual Cortex and CNN6 minutes
Convolutional Layer 6 minutes
Working of Convolutional Layer 6 minutes
Demonstration: Load and Preprocess the Data 5 minutes
Demonstration: Designing the Model 5 minutes
Demonstration: Building the CNN Model 3 minutes
Demonstration: Model Accuracy 1 minute
Demonstration: Adding More Layers 4 minutes
Demonstration: Building Basic CNN Model with New Parameters5 minutes
Demonstration: Pre-trained Model 3 minutes
Classification and Object Detection5 minutes
Introduction to RCNN5 minutes
R-CNN: Bounding Box Regression2 minutes
Pre-trained Model6 minutes
Fast Regional - CNN5 minutes
Demonstration: Creating Base Variables and Loading the Model3 minutes
Demonstration: Training the Model and Visualizing the Predictions4 minutes
Demonstration: SVM as a Classifier3 minutes
Fast RCNN Limitations5 minutes
Advent of Faster R-CNN6 minutes
Tensorflow Hub3 minutes
Demonstration: Object Detection with Faster RCNN-Pretrained Model setup5 minutes
Demonstration: Object Detection with Faster RCNN - Building the Model6 minutes
Summary of CNN in Deep Learning2 minutes
Summary of Faster RCNN4 minutes

3 lecturesTotal 30 minutes

Why Convolutions are Important?10 minutes
SVM Classifier in Object Detection 10 minutes
Faster R-CNN Architecture10 minutes

4 devoirsTotal 48 minutes

Knowledge Check : Deep Learning with CNN, RCNN and Faster RCNN30 minutes
Practice Quiz : CNN6 minutes
Practice Quiz : TensorFlow Hub for Object Detection using Faster RCNN6 minutes
Practice Quiz : Faster RCNN (Recurrent Convolutional Neural Network)6 minutes

1 sujet de discussionTotal 10 minutes

Which among the following techniques is most useful?10 minutes

This module focuses on Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM) networks for sequential data processing. Learners will gain practical skills in building, training, and optimizing models for complex tasks.

Inclus

24 vidéos4 lectures4 devoirs

24 vidéosTotal 125 minutes

RNN Fundamentals5 minutesPrévisualiser le module
RNN Architecture4 minutes
RNN Architecture: Workflow5 minutes
Implementing RNN6 minutes
Demonstration: RNN-Dataset Preparation 6 minutes
Demonstration: RNN-Building the Model 5 minutes
Basics of LSTM6 minutes
LSTM Structure6 minutes
Forget Gate and Input Gate5 minutes
Output Gate2 minutes
Importance of LSTM Architecture5 minutes
Types of LSTM3 minutes
Demonstration: Next Word Prediction- Processing the Corpus5 minutes
Demonstration: Next Word Prediction- Layers 5 minutes
Demonstration: Next Word Prediction- Model Compilation and Prediction7 minutes
Improving a Model6 minutes
Model Optimization4 minutes
Using Adam Optimizer6 minutes
Model Compilation3 minutes
Model Compilation with Popular Frameworks4 minutes
Demonstration: Model Compilation- Preparing the Dataset5 minutes
Demonstration: Building and Compiling Model 4 minutes
Demonstration: From RMSProp to Adam 4 minutes
Summary of Deep Learning with RNN and LSTM with Model Optimization5 minutes

4 lecturesTotal 40 minutes

Recurrent Neural Networks (RNNs) in Deep Learning10 minutes
Attention-Based LSTM (Long Short-Term Memory)10 minutes
Capsule Networks in Deep Learning10 minutes
Model Optimizers: Beyond ADAM10 minutes

4 devoirsTotal 48 minutes

Knowledge Check : Deep Learning with RNN, LSTM and Model Optimization30 minutes
Practice Quiz : Working of Recurrent Neural Networks (RNN)6 minutes
Practice Quiz : LSTM Architecture and Working6 minutes
Practice Quiz : Module Optimization and Compilation6 minutes

This module is designed to assess an individual on the various concepts and teachings covered in this course. Evaluate your knowledge with a comprehensive graded quiz on SLP, MLP, RNN, CNN, LSTM and many more complex deep learning concepts.

Inclus

1 vidéo1 lecture1 devoir1 sujet de discussion

Instructeur

Edureka

61 Cours60 216 apprenants

Offert par

Edureka

Recommandé si vous êtes intéressé(e) par Machine Learning

IBM
Deep Learning with PyTorch
Cours
IBM
IBM Deep Learning with PyTorch, Keras and Tensorflow
Certificat Professionnel
Packt
Deep Neural Network for Beginners Using Python
Cours
IBM
Deep Learning with Keras and Tensorflow
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

Deep learning is a subset of machine learning that emphasizes artificial neural network algorithms designed to mimic the structure and functions of the human brain. Multi-layered neural networks are developed to autonomously learn and identify features from vast datasets, enabling them to effectively perform tasks such as speech recognition, image recognition, and natural language processing. Deep learning plays a crucial role in AI advancements as it requires extensive amounts of data and computational strength.

The target audience for Practical Deep Learning with Python comprises beginners and intermediate learners eager to grasp and utilize deep learning methods with Python. This course is tailored for for data scientists, AI Research Analysts, and developers who possess fundamental programming skills and a basic grasp of machine learning principles.

To effectively follow the exercises and examples in Practical Deep Learning with Python, you will need a computer with the following minimum system requirements:

- Operating System: Windows, macOS, or Linux.

- Processor: A multi-core processor (preferably with support for AVX instructions).

- RAM: At least 8 GB of RAM, though 16 GB or more is recommended for larger datasets.

- Storage: At least 10 GB of free disk space to accommodate datasets, libraries, and project files.

- Python Environment: Python 3.6 or later installed with libraries such as TensorFlow or PyTorch, NumPy, Matplotlib, and Pandas.

Please note: All the practical are performed on Google Colab

To effectively learn deep learning, it is advisable to acquire the following essential knowledge and skills:

- Mathematics: A solid grasp of linear algebra (matrices, vectors), calculus (derivatives and gradients), probability, and fundamental statistics. These ideas are essential for grasping the workings of neural networks and the process of optimization.

- Programming Abilities: Mastery of Python is crucial, since the majority of deep learning frameworks, such as TensorFlow and PyTorch, are built on Python. Having knowledge of libraries like NumPy, Pandas, and Matplotlib is also advantageous.

- Machine Learning Essentials: Grasping the core principles of machine learning, including supervised and unsupervised learning, overfitting, underfitting, and evaluation metrics for models, will establish a solid groundwork.

Data Management: Familiarity with data preprocessing methods, such as addressing missing data, normalization, and data augmentation, is beneficial.

Access to lectures and assignments depends on your type of enrollment. If you take a course in audit mode, you will be able to see most course materials for free. To access graded assignments and to earn a Certificate, you will need to purchase the Certificate experience, during or after your audit. If you don't see the audit option:

The course may not offer an audit option. 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. If you only want to read and view the course content, you can audit the course for free.