Get in Touch

Course Outline

Introduction to Neural Networks

  1. Understanding Neural Networks
  2. Current landscape of neural network applications
  3. Neural Networks compared to regression models
  4. Supervised versus unsupervised learning

Overview of Available Packages

  1. nnet, neuralnet, and other tools
  2. Distinctions between packages and their respective limitations
  3. Visualizing neural network structures

Applying Neural Networks

  • Core concepts of neurons and neural networks
  • A simplified model of the brain
  • Neuron opportunities
  • The XOR problem and the nature of value distributions
  • The polymorphic nature of the sigmoidal function
  • Other activation functions
  • Constructing neural networks
  • Concept of neuron connections
  • Neural networks as nodes
  • Building a network
  • Neurons
  • Layers
  • Scaling
  • Input and output data
  • Range from 0 to 1
  • Normalization
  • Training neural networks
  • Backward propagation
  • Propagation steps
  • Network training algorithms
  • Range of application
  • Estimation
  • Challenges in approximation capabilities
  • Examples
  • OCR and image pattern recognition
  • Other applications
  • Implementing a neural network model to predict stock prices of listed companies

Requirements

Familiarity with programming in any language is recommended.

 14 Hours

Number of participants


Price per participant

Testimonials (3)

Upcoming Courses

Related Categories