Online Neural Network Course Schedule

NeuroSolutions is used for all of the demonstrations is our course not just because we created the software, but because it is an excellent platform for experimenting with different techniques and topologies.

Day One - Introduction to Neural Networks & NeuroSolutions

Introduction to Neural Networks
  • Terminology
  • Fundamental principles of neural networks
  • Overview of neural network architectures and training
  • When to use and why should you use neural networks
Fundamentals of NeuroSolutions
  • Overview of breadboards, palettes, families, etc.
  • Building a neural network with the NeuralExpert and training it
  • Testing a neural network with the TestingWizard
  • Using probes to understand the training process and the results
  • What to look for and how to use probes in a network
  • Using and setting the network parameters

Day Two - Day Two - Intro to NeuroSolutions for Excel, Intro to Supervised Learning and Adaptive Systems

Using NeuroSolutions for Excel
  • Preprocessing and analyzing your input data
  • Tagging your data
  • Creating a neural network
  • Training a neural network
  • Testing a neural network
  • Analyzing your results
  • Optimizing neural network parameters / inputs
Fundamentals of Adaptive Systems and Neural Networks
  • Adaptive Systems and Linear Regression
  • Analyzing linear adaptive systems
  • Understanding gradient descent training

Day Three - Supervised Learning and MLPs, RBFs, SVMs and PNNs

Supervised Learning and Multi-layer Perceptrons (MLPs)
  • Overview of MLPs (nonlinear extenstions to linear adaptive systems)
  • Comparison of backprop variations including Momentum, Levenberg-Marquardt, RProp and Conjugate Gradient
  • Ways to improve generalization
  • Building a neural network with the NeuralBuilder and training it
  • Project 1: Using MLPs for classification
Radial basis functions (RBFs)
  • Introduction to unsupervised learning
  • What are RBFs and why/when should you use them?
  • How to use RBFs and how to set their parameters
Support Vector Machines (SVMs) and Probabilistic Neural Networks (PNNs)
  • Support Vector Machines (SVMs)
  • Probabilistic Neural Networks (PNNs)
  • Project 2: Solve a Classification problem using one of these architectures

Day Four - Temporal Neural Networks

Temporal processing and dynamical systems
  • Adaptive signal processing fundamentals
  • Adaptive linear filtering and its applications
  • Time Delay Neural Networks (TDNN)
  • Time Lagged Recurrent Network (TLRN)
  • Backpropagation Through Time learning algorithm

Day Five - Practical Application of Neural Networks

  • Data Cleaning (Garbage In / Garbage Out)
  • Data Randomization
  • Data Preprocessing (Including PCA’s)
  • Topology, Input, and Parameter Selection
  • Genetic Optimization
  • Sensitivity Analysis
  • Greedy Search / Back-Elimination
  • Express Builder for NeuroSolutions for Excel
  • Leave-N-Out Training
  • Applying Production Data

Day Six - Automated Processing

  • Introduction to NeuroSolutions Infinity
  • Data Preparation in Infinity
  • Projects and Experiments
  • Ranking Inputs
  • Ranking Models
  • Validating Models
  • Production Data in Infinity
  • Class Project: Solve a previous problem with NS Infinity instead of NeuroSolutions and compare the results.

Day Seven - Embedding a Neural Network into an Application

Embedding a Neural Network
  • C++ Code Generation
  • OLE Automation
  • Custom Solution Wizard (Windows-based DLL)
  • Infinity QuickDeploy

Day Eight - Advanced Topics

  • Creating Custom Neural Network Components
  • NeuroSolutions for MATLABTM
  • Advanced NeuroSolutions for ExcelTM
  • Financial Forecasting with Neural Networks