Learn the core concepts, architecture, math, and training process behind neural networks.
What You'll Learn
- Understand biological vs artificial neurons
- Build feed-forward neural networks
- Train models with gradient descent & backpropagation
- Use activation functions for nonlinear modeling
- Evaluate neural networks using ML metrics
Requirements
- Basic Python + ML knowledge
- NumPy installed
- optional: scikit-learn
Earn Your Certificate
Showcase your skills with a certificate! Complete the course, submit your project, and earn your certificate. Here's a sample of what you'll receive to show off your accomplishments.
Course Curriculum
4 Chapters
20 Lectures
37h 52m 22s
1. Introduction to Neural Networks
5 Lectures|1 Assignment|1 Quiz|7h 26m 28s
1. Biological vs Artificial Neurons
2. Structure of an Artificial Neuron
3. Feed-Forward Architecture Overview
4. Activation Functions
5. Neural Network Use Cases
6. Lesson 1 Basics
7. Build a Single-Neuron Model
8. Activation Functions Guide
2. Training Neural Networks
5 Lectures|1 Assignment|11h 17m 54s
3. Model Improvement & Optimization
5 Lectures|1 Assignment|1 Quiz|4h 43m
4. Building Neural Networks with scikit-learn
5 Lectures|1 Assignment|14h 25m
Live Classes from the courses
Reviews
No reviews available
$20.00$59.0066% Off
Course Includes
Share On :