Deep Learning in TensorFlow #4 L3 - CNN: Convolutional Layer (Kernel, Strides, Padding, Activation)

⭐️About this Course
This Deep Learning in TensorFlow Specialization is a foundational program that will help you understand the principles and Python code of Machine Learning and Deep Learning and prepare you to participate in the development of leading-edge AI and data scientist technology.

In this Specialization, you will build and train neural network architectures with some hands-on project, such as Vanilla Neural Networks, Convolutional Neural Networks, Recurrent Neural Networks, LSTMs, and learn the advance techniques on how to make them better with strategies.

🌟🌟🌟 Earn a Certificate [MEMBERS only]
When you finish every course and complete the hands-on project and a final project assessment, you'll earn a Certificate that you can share with prospective employers.

============================================================================

============================================================================

What you will learn from this course:
Course 1 Numpy Basics
- Introduction to Tensors for Deep Learning with NumPy
- NumPy Structure
- NumPy Properties & Attributes
- NumPy Array Creation
- NumPy Indexing and Slicing
- NumPy Shape Manipulation
- NumPy Element-wise VS Broadcasting
- NumPy Aggregate and Statistical Functions
- NumPy Dot Product and Matrix Multiplication

Course 2 Neural Networks in TensorFlow
- A Gentle Introduction of AI, ML and NN
- Logistic Regression
- From Logistic Regression to Neural Network
- Build your first Neural Network
Hands-on Project - Image Classification

Course 3 Neural Networks in TensorFlow - Advanced Techniques
- Introduction & Sequential Model
- Sequential Model - Attributes
- Sequential Model - Save and load models
- Sequential Model - Compile()
- Frequently Used Optimizers
- Frequently Used Loss Functions
- Frequently Used Metrics
- Sequential Model - Fit()
- Usage of Returns
- Usage of Callbacks
- ModelCheckPoint
- TensorBoard
- EarlyStopping
- Usage of Batch Size
- Sequential Model - Evaluate()
- Sequential Model - Predict()

Course 4 Convolutional Neural Networks in TensorFlow
- Introduction & Basic Architecture
- Build your first Convolutional Neural Network
- Convolutional Layer
- Kernel, Strides, Padding
- Activation
- Pooling Layer
- Maximum Pooling
- Average Pooling
- Flatten & Dense Layer

Course 5 Recurrent Neural Networks in TensorFlow
- Introduction
- Mathematical Representations
- Build your first Recurrent Neural Network
- Recurrent Neural Networks
- Vanishing and Exploding Gradients
- Solutions
- Long Short-Term Memory (LSTM) Networks
- Introduction
- Core Concept of LSTMs
- How LSTMs work
- Summary
Hands-on Project - LSTM model for Image Classification

Course 6 Keras Functional API
- Introduction
- Build a Neural Network with Functional API
- Features
- Use the same graph of layers to define multiple models
- Callable model
- Manipulate complex graph topologies
- Shared layers
- Extract and reuse nodes
Hands-on Project - ResNet model for Image Classification