16-08-2014, 12:14 PM
Introduction to Neural Networks seminar report
NEURAL NETWORKS.doc (Size: 108 KB / Downloads: 9)
Abstract
Neural Network is the representation of brain's
learning approach. This brain operates as
multiprocessor and has excellent interlinked. Neural
Network also can be represented as "Parallel
distributed processing" planning. It is utilised in the
computer applications for solving the complicated
problems. There are many benefits from Neural
Network such as no requirements for specifying the
relevant factors, an unsophisticated model which has
many factors for performance, a straightforward
model, fault tolerance and an innate synchronou
Neural Network is the representation of brain's
learning approach. This brain operates as
multiprocessor and has excellent interlinked. Neural
Network also can be represented as "Parallel
distributed processing" planning. It is utilised in the
computer applications for solving the complicated
problems. There are many benefits from Neural
Network such as no requirements for specifying the
relevant factors, an unsophisticated model which has
many factors for performance, a straightforward
model, fault tolerance and an innate synchronou
What is Neural Network?
Brain : operates as multiprocessor; has excellent
linked
Has remarkable capability to improve the
problems, explain them by computers
Has neurons, which work as the fundamental
processors
Synapse: interconnection between neurons
Input: the activation of arriving neurons
accumulated by the weights of synapses
Result: the activation of neurons, which is
calculated by employing a threshold function
Parallel distributing processing; solving complicated
problems on the computers
Kohonen
Kohonen Self-Organizing Neural Network
Unsupervised Learning: Learning with no
guidance
Examines only input, produce the recognition
of this input
How to implement Neural Network?
Implementing 2 Kinds of Neural Network
Kohonen
Back Propagation
Programming language is C++
Superior management in classes
Fast for doing the duties
Neural Networks Examples
Input Vectors problem (Kohonen)
Travelling Salesman problem (Kohonen)
XOR problem (Back Propagation)Input Vectors problem (Kohonen)
Input: 4 Input vectors
Output: 2 Weight vectors
Conclusion and Future Work
Neural Networks
Unsupervised Learning : Kohonen
Supervised Learning : Back Propagation
Advantages and Neural Network Examples
Adapt for the research about the Biometric Thrill and
Arousal Detection system
Analyse, Recognize and Predict the results