Neural Network | Workshop on Artificial Neural Network & Fuzzy Logic using MATLAB
The objective of this hands-on workshop is to give insight to MATLAB for Artificial Neural Network & Fuzzy Logic and provide hands-on experience in selected applications. This leads to solve the complex and dynamic real time problems. This workshop provide s a vibrant opportunity for researchers and faculty members.
Topics to be covered in Workshop
- Introduction
- Biological Neuron
- Dendrites
- Axon
- Synapse
- Introduction Neural Network
- BASIC introduction Neuron
- Activation function
- The Neuron Diagram
- Neuron Models
- step function
- ramp function
- sigmoid function
- Gaussian function
- Network Architectures
- single-layer feed-forward
- multi-layer feed-forward
- recurrent
- Neural Network Learning Rules
- Supervised and Unsupervised Learning
- Hebbian Learning Rule
- Perceptron Learning Rule
- Delta Learning Rule
- Winner Take All Learning Rule
- Fuzzy Logic
- Definition of fuzzy
- Fuzzy Logic Representation
- Fuzzy Logic Example
Introduction of MATLAB
- About MATLAB.
- MATLAB Screen
- Variable , array , Matrix , Indexing
- Operators (Arithmetic, relational, Logical ).
- Display Facilities
- Flow Control (IF, Switch ,For ,While ,Break) .
- Command line
- M-File
- Mat-file.
- Scripts and Functions.
- Data storage.
- Input/output capability.
Working On MATLAB Environment
- How to open, quit and work on command window.
- Introduction of MATLAB Screen.
- Command Window.
- Current Directory.
- Workspace.
- Command history.
- Introduction of useful command.
Getting Started with Neural Network Toolbox
- Classify Patterns with a Neural Network
- Neural Network Pattern Recognition Tool.
- Neural Network Fitting Tool.
- Network Time Series Tool.
- Parallel Computing on CPUs and GPUs
Neural Networks: MATLAB examples
- Calculate the output of a simple neuron
- Classification of linearly separable data with a perceptron
- Classification of a 4-class problem with a 2-neuron perceptron
- ADALINE time series prediction with adaptive linear filter
- Classification of an XOR problem with a multilayer perceptron
- Classification of a 4-class problem with a multilayer perceptron
- Radial basis function networks for classification of XOR problem
- 1D and 2D Self Organized Map
Duration: The duration of this workshop will be two consecutive days, with eight hour session each day in a total of sixteen hours properly divided into theory and hands on sessions.
Certification Policy:
- Certificate of Participation for all the workshop participants.
- At the end of this workshop, a small competition will be organized among the participating students and winners will be awarded with a 'Certificate of Excellence'.
- Certificate of Coordination for the coordinators of the campus workshops.
Eligibility: There are no prerequisites. Anyone interested, can join this workshop.
