Mastering the Fundamentals of Neural Networks Online Course

Mastering the Fundamentals of Neural Networks Online Course

This course offers a hands-on journey into deep learning, covering Neural Networks, Convolutional Neural Networks (CNNs), and Recurrent Neural Networks (RNNs). You’ll learn core concepts such as logistic and linear regression, forward and backward propagation, cross-entropy, convolution operations, residual networks, and RNN architectures including GRU and LSTM. With practical code blocks and notebooks, you’ll gain the skills to apply these deep learning techniques across applications like computer vision, NLP, speech recognition, and more.

Who should take this Course? 

The Docker and Kubernetes for ASP.NET Developers Online Course is ideal for ASP.NET developers, software engineers, and DevOps professionals who want to containerize, deploy, and manage scalable web applications. It is also suitable for students, IT professionals, and full-stack developers seeking hands-on experience with Docker and Kubernetes to streamline deployment, orchestrate containers, and build production-ready ASP.NET applications.

What you will learn

• Learn about linear and logistic regression in ANN
• Learn about cross-entropy between two probability distributions
• Understand convolution operation which scans inputs with respect to their dimensions
• Understand VGG16, a convolutional neural network model
• Understand why to use recurrent neural network
• Understand Long short-term memory (LSTM)

Course Outline

Welcome

• Welcome Message
• Course Outline

Artificial Neural Networks

• Linear Regression
• Logistic Regression
• Purpose of Neural Networks
• Forward Propagation
• Backward Propagation
• Activation Function
• Cross-Entropy Loss Function
• Gradient Descent
• Lab 1 - Introduction to Python
• Lab 2 - Introduction to TensorFlow — Remove the Throat-Clearing Sound in the Start of the Video
• Lab 3 - Introduction to Neural Network
• Lab 4 - Functional API
• Lab 5 - Building Deeper and Wider Model

Convolutional Neural Networks

• Image Data
• Tensor and Matrix
• Convolutional Operation
• Padding
• Stride
• Convolution in 2D and 3D
• VGG16
• Residual Network
• Lab 1 - Introduction to Convolutional 1-Dimensional
• Lab 2 - Introduction to CNN
• Lab 3 - Deep CNN
• Lab 4 - Transfer Learning

Recurrent Neural Networks

• Welcome to RNN
• Why Use RNN
• Language Processing
• Forward Propagation in RNN
• Backward Propagation Through Time
• Gated Recurrent Unit (GRU)
• Long Short-Term Memory (LSTM)
• Bi-Directional RNN
• Lab 1 - RNN in Text Classification
• Lab 2 - Sequence to Sequence Stock Candlestick Forecast