Dive deep into the theory and implementation of Neural Networks. This course will have you implementing tools at the heart of modern AI such as Perceptrons, activation functions, and the crucial components of multi-layer Neural Networks. All of this without the help of high-level libraries leaves you with a profound understanding of the underpinning mechanisms.
Overview
Syllabus
- Lesson 1: Understanding Neural Networks: An Introduction to the Perceptron Algorithm
- Perceptron Logic Probe Decision-Making
- Perceptron Prediction Calibration
- Code the Perceptron's Decision Function
- Lesson 2: Understanding and Implementing Neural Network Activation Functions
- Step Function in Action
- Comparing Function: Sigmoid and Tanh
- Sigmoid Activation Function Implementation
- Lesson 3: Backpropagation Unveiled: Understanding the Mathematics and Code Behind Neural Network Learning
- Training a Neural Network to Solve XOR
- Implement Prediction in the Neural Network
- Implement Weight Update in Neural Network
- Implement Sigmoid Derivative and Prediction Function in a Neural Network
Related Courses
-
Foundations of Deep Learning and Neural Networks
-
How Neural Networks Learn: Exploring Architecture, Gradient Descent, and Backpropagation
-
Deep Learning - Crash Course 2023
-
Deep Learning Fundamentals with Keras
-
Mastering Neural Networks and Model Regularization
-
Building a Neural Network in TensorFlow
