Visão Geral

Este Curso Neural Network in R, é uma introdução à aplicação de redes neurais em problemas do mundo real usando o software R-project.

Pre-Requisitos

• Programação em qualquer linguagem de programação recomendada

Materiais

Conteúdo Programatico

Introduction to Neural Networks

1. What are Neural Networks
2. What is current status in applying neural networks
3. Neural Networks vs regression models
4. Supervised and Unsupervised learning

Overview of packages available

1. nnet, neuralnet and others
2. Differences between packages and itls limitations
3. Visualizing neural networks

Applying Neural Networks

1. Concept of neurons and neural networks
2. A simplified model of the brain
3. Opportunities neuron
4. XOR problem and the nature of the distribution of values
5. The polymorphic nature of the sigmoidal
6. Other functions activated
7. Construction of neural networks
8. Concept of neurons connect
9. Neural network as nodes
10. Building a network
11. Neurons
12. Layers
13. Scales
14. Input and output data
15. Range 0 to 1
16. Normalization
17. Learning Neural Networks
18. Backward Propagation
19. Steps propagation
20. Network training algorithms
21. range of application
22. Estimation
23. Problems with the possibility of approximation by
24. Examples
25. OCR and image pattern recognition
26. Other applications
27. Implementing a neural network modeling job predicting stock prices of listed