Tensor Flow 2.0Introduction to deep learning with tensor flow
5 subjects
Foundations of Neural NetworksThis subject provides the fundamental knowledge needed to understand deep learning, covering the core concepts of neural networks and the necessary mathematical and software tools.
7 lessons
IntroductionThis lesson introduces the basics of deep learning and its growing popularity
The Core Components of a Neural NetworkThis lesson explores the fundamental building blocks of neural networks.
Environment SetupThis lesson will prepare your environment for deep learning projects
The Math Behind Neural NetworksThis lesson covers the essential mathematical concepts for understanding how neural networks work
Key Functions and Their RolesThis lesson focuses on activation and loss functions, two critical components of a neural network
The Learning ProcessThis lesson explains how a neural network learns to make predictions.
Gradient Descent VariantsThis lesson explores different variations of the gradient descent algorithm.
Building Blocks and OptimizationThis subject covers more practical aspects of building and optimizing deep learning models.
6 lessons
Practical Model BuildingThis lesson focuses on building a practical neural network model for a real-world task.
Model Evaluation MetricsThis lesson teaches how to evaluate the performance of a deep learning model
RegularizationThis lesson explores techniques to prevent overfitting in deep learning models.
Handling Common Dataset IssuesThis lesson addresses the challenge of working with imbalanced datasets.
Visualizing and DebuggingThis lesson shows how to use TensorBoard for visualizing and debugging models.
Input Pipeline and OptimizationThis lesson focuses on optimizing data loading and training.
Computer Vision with CNNsThis subject is dedicated to convolutional neural networks (CNNs) and their applications in computer vision.
5 lessons
Introduction to Computer VisionThis lesson introduces the field of computer vision and its applications.
Building a CNNThis lesson provides a hands-on guide to building your first Convolutional Neural Network. It walks you through a practical image classification problem using the CIFAR-10 dataset
Preventing OverfittingThis lesson covers data augmentation, a key technique for improving model generalization.
Transfer LearningThis lesson introduces transfer learning and its benefits.
Object DetectionThis lesson focuses on object detection, a specific computer vision task.
Sequence Models and NLPThis subject covers recurrent neural networks (RNNs) and their applications in natural language processing (NLP).
4 lessons
Introduction to Sequence ModelsThis lesson introduces Recurrent Neural Networks (RNNs), which are specifically designed to handle sequential data like text, audio, and time series.
Tackling RNN ChallengesThis lesson addresses common problems faced when training RNNs.
Natural Language Processing (NLP)This lesson introduces the basics of NLP.
Word EmbeddingsThis lesson focuses on the concept of word embeddings.
Projects and DeploymentThis subject provides hands-on experience through projects and covers model deployment.
3 lessons
Customer Churn Prediction ProjectThis project applies deep learning to predict customer churn.
Potato Disease Classification ProjectThis project is an end-to-end deep learning project to classify diseases in potato plants.
Advanced NLPThis lesson introduces BERT, a powerful model for NLP.
