К содержимому
learnspaceYOUR NEXT CHAPTER
ПРОСТРАНСТВО ОБУЧЕНИЯ
ГлавнаяКаталог курсовМоё обучениеCoursera

Знания без границ

Учитесь у лучших университетов и компаний мира.

Открыть Coursera
Интеграция
Пространство университета
Моё пространствоСтраница курса
↵
ЯЛичный кабинетСтудент
© 2026 LearnSpaceКаждый день — возможность узнать больше.Помощь
Practical Deep Learning with Python · LearnSpace
Назад в каталог
courseraАнализ данных

Practical Deep Learning with Python

Курс от Edureka
Средний≈ 12.1 чАнглийский
О курсеНавыкиПрограммаПреподаватели

О курсе

Gain hands-on experience in deep learning with Python and learn to design, train, and optimize advanced neural networks for real-world artificial intelligence applications. This course is ideal for data scientists, machine learning engineers, and AI enthusiasts who want to enhance their skills in building intelligent systems using Python. Throughout this deep learning training, you’ll explore how to model and analyze complex datasets with techniques widely applied in computer vision, natural language processing, and predictive analytics. You’ll also develop the ability to solve large-scale data problems and uncover actionable insights through deep learning. By the end of the course, you will be able to: - Explain the foundational components of deep learning models and their significance in artificial intelligence. - Apply Convolutional Neural Networks (CNNs), R-CNNs, and Faster R-CNNs for object detection and image-related applications. - Recognize the limitations of Perceptrons and implement Multi-Layer Perceptrons (MLPs) for improved data modeling. - Build and apply Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM) architectures for sequential and time-series data. - Optimize, evaluate, and fine-tune neural networks to improve accuracy, efficiency, and scalability. This course is designed for professionals and learners with a working knowledge of Python and machine learning who are ready to expand into deep learning and artificial intelligence. Experience with Python programming, statistics, and prior machine learning projects will be helpful in making the most of this training. Begin your journey into deep learning with Python and strengthen your ability to build advanced AI systems that solve real-world problems and power the future of intelligent technologies.

Навыки, которые вы освоите

Convolutional Neural NetworksRecurrent Neural Networks (RNNs)Fine-tuningPython ProgrammingApplied Machine LearningArtificial IntelligenceMachine Learning MethodsModel OptimizationModel EvaluationModel Training

Программа курса

4 модулей · 108 учебных материалов

01Deep Learning Components36 материалов

Environment Set-Up and Configuration

Welcome to Practical Deep Learning with PythonЧтениеCourse IntroductionВидеоYour Understanding of Deep Learning BasicsDIALOGUEEnvironment ConfigurationВидео

Учитесь у экспертов

Edureka

Преподаватель курса

Practical Deep Learning with Python
В каталоге вашей программы

Инвестируйте в себя

Новые знания — в удобное для вас время.

Начать на Coursera

Обучение откроется на Coursera
в новой вкладке

Обучение на Coursera

≈ 12.1 ч

4 модулей

Язык: Английский

Субтитры: Венгерский

Часть программы вашего университета
Introduce YourselfОбсуждение
System Requirements and Pre-requisite for Studying Deep LearningЧтение
Practice Quiz : Environment Set-Up and ConfigurationЗадание

Essentials of Deep Learning

Machine Learning vs. Deep LearningВидеоWhat is Deep Learning?ВидеоNeural NetworksВидеоArtificial Neural Network (ANN)ВидеоANN: Types and ApplicationsВидеоForward PropagationВидеоPerceptronВидеоLearning RateВидеоWhat is Activation Function? ВидеоActivation Function and it's TypesВидеоImportance of EpochВидеоSingle Layer Perceptron - Define Sigmoid Function ВидеоSingle Layer Perceptron - Decision BoundaryВидеоLearning Rate in Deep LearningЧтениеWhat are the structural and functional similarities between the human brain and neural networks?ОбсуждениеPractice Quiz : Essentials for Deep LearningЗадание

Building Perceptron and it's Working

Limitations of Single Layered PerceptronВидеоMulti-Layered PerceptronВидеоWhat is Backpropagation? ВидеоBackpropagation ВидеоDemonstration: Building a Simple Neural NetworkВидеоDemonstration: Understanding How Backpropagation has WorkedВидеоDemonstration: Handwritten Digits Classification - Data Preprocessing ВидеоDemonstration: Handwritten Digits Classification- Designing the ModelВидеоDemonstration: Handwritten Digits Classification - Optimizing the Model ВидеоHebbian Learning AlgorithmЧтениеPractice Quiz : Building Perceptron and it's WorkingЗадание

Module Wrap-Up and Assessment

Summary of Deep Learning ComponentsВидеоKnowledge Check : Deep Learning ComponentsЗадание
02Deep Learning with CNN, RCNN and Faster RCNN35 материалов

Convolutional Neural Network

Limitations of MLPВидеоMLP Limitations: Resolving the Issue with CNNВидеоVisual Cortex and CNNВидеоConvolutional Layer ВидеоWorking of Convolutional Layer ВидеоDemonstration: Load and Preprocess the Data ВидеоDemonstration: Designing the Model ВидеоDemonstration: Building the CNN Model ВидеоDemonstration: Model Accuracy ВидеоDemonstration: Adding More Layers ВидеоDemonstration: Building Basic CNN Model with New ParametersВидеоDemonstration: Pre-trained Model ВидеоWhy Convolutions are Important?ЧтениеPractice Quiz : CNNЗадание

TensorFlow Hub for Object Detection using Faster RCNN

Classification and Object DetectionВидеоIntroduction to RCNNВидеоR-CNN: Bounding Box RegressionВидеоPre-trained ModelВидеоFast Regional - CNNВидеоDemonstration: Creating Base Variables and Loading the ModelВидео

Faster RCNN

Fast RCNN LimitationsВидеоAdvent of Faster R-CNNВидеоTensorflow HubВидеоDemonstration: Object Detection with Faster RCNN-Pretrained Model setupВидеоDemonstration: Object Detection with Faster RCNN - Building the ModelВидеоFaster R-CNN ArchitectureЧтение

Module Wrap-Up and Assessment

Summary of CNN in Deep LearningВидеоSummary of Faster RCNNВидеоKnowledge Check : Deep Learning with CNN, RCNN and Faster RCNNЗадание
03Deep Learning with RNN, LSTM and Model Optimization32 материалов

Working of Recurrent Neural Networks (RNN)

RNN FundamentalsВидеоRNN ArchitectureВидеоRNN Architecture: WorkflowВидеоImplementing RNNВидеоDemonstration: RNN-Dataset Preparation ВидеоDemonstration: RNN-Building the Model ВидеоRecurrent Neural Networks (RNNs) in Deep LearningЧтениеPractice Quiz : Working of Recurrent Neural Networks (RNN)Задание

LSTM Architecture

Basics of LSTMВидеоLSTM StructureВидеоForget Gate and Input GateВидеоOutput GateВидеоImportance of LSTM ArchitectureВидеоTypes of LSTMВидеоDemonstration: Next Word Prediction- Processing the Corpus

Module Optimization and Compilation

Improving a ModelВидеоModel OptimizationВидеоUsing Adam OptimizerВидеоModel CompilationВидеоModel Compilation with Popular FrameworksВидеоDemonstration: Model Compilation- Preparing the DatasetВидео

Module Wrap-Up and Assessment

Summary of Deep Learning with RNN and LSTM with Model OptimizationВидеоKnowledge Check : Deep Learning with RNN, LSTM and Model OptimizationЗадание
04Course Wrap-Up and Assessment5 материалов
Final Reflections on Practical Deep LearningDIALOGUECourse Summary for Practical Deep Learning with PythonВидеоPractice Project: MNIST Fashion Dataset - AnalysisЧтениеKnowledge Check : Practical Deep Learning with PythonЗаданиеDescribe Your Learning JourneyОбсуждение
Demonstration: Training the Model and Visualizing the PredictionsВидео
Demonstration: SVM as a ClassifierВидео
SVM Classifier in Object Detection Чтение
Practice Quiz : TensorFlow Hub for Object Detection using Faster RCNNЗадание
Which among the following techniques is most useful?Обсуждение
Practice Quiz : Faster RCNN (Recurrent Convolutional Neural Network)Задание
Видео
Demonstration: Next Word Prediction- Layers Видео
Demonstration: Next Word Prediction- Model Compilation and PredictionВидео
Attention-Based LSTM (Long Short-Term Memory)Чтение
Capsule Networks in Deep LearningЧтение
Practice Quiz : LSTM Architecture and WorkingЗадание
Demonstration: Building and Compiling Model Видео
Demonstration: From RMSProp to Adam Видео
Model Optimizers: Beyond ADAMЧтение
Practice Quiz : Module Optimization and CompilationЗадание