Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Course Outline
Introduction to Neural Networks
- Understanding what neural networks are
- The current landscape of neural network applications
- Comparing neural networks with regression models
- Supervised versus unsupervised learning
Overview of Available Packages
- Introduction to packages such as nnet, neuralnet, and others
- Differentiating between packages and their respective limitations
- Techniques for visualizing neural networks
Applying Neural Networks
- The fundamental concepts of neurons and neural networks
- A simplified model of the human brain
- The role and function of neurons
- The XOR problem and the nature of value distribution
- The polymorphic characteristics of sigmoidal functions
- Other activation functions
- Constructing neural networks
- The concept of neuron connectivity
- Neural networks represented as nodes
- Building a network architecture
- Understanding neurons
- The structure of layers
- Scaling techniques
- Handling input and output data
- Working with values in the 0 to 1 range
- Data normalization
- Training neural networks
- Backpropagation
- Propagation steps
- Network training algorithms
- Practical ranges of application
- Estimation methods
- Challenges related to approximation capabilities
- Examples
- OCR and image pattern recognition
- Additional applications
- Implementing a neural network model to predict the stock prices of listed companies
Requirements
Proficiency in programming in any language is recommended.
14 Hours
Testimonials (3)
I mostly enjoyed the graphs in R :))).
Faculty of Economics and Business Zagreb
Course - Neural Network in R
We gained some knowledge about NN in general, and what was the most interesting for me were the new types of NN that are popular nowadays.
Tea Poklepovic
Course - Neural Network in R
I liked the new insights in deep machine learning.
