Learning In Neural Networks

[raje.maheshkumar]

[attachment=15092]
INTRODUCTION
Artificial intelligence is the part of computer science concerned with designing intelligent computers.
Learning implies that a processing unit is capable of changing its input/output behavior as a result of changes in the environment
NEURAL NETWORKS
Process of humans doing intelligent things.
Neural networks and artificial neurons
Brain modeling
Artificial system building
LEARNING IN ARTIFICIAL NEURAL NETWORKS
Machine Learning
Learning Agents
Ideal Rational Agents
Intelligent Agents
The Agent Environments
Classification among the different types of Learning
Supervised Learning
Unsupervised Learning
Reinforced Learning
Competitive Learning
The Delta Rule
The Generalized Delta Rule
The Gradient Descend Rule
Hebbian Learning
Pattern Recognition
The Learning Process
Associative mapping
Regularity detection
Fixed networks
Adaptive networks
Transfer function
Back-propagation algorithm
Machine Learning
Types of Learning
The Need for Learning
Learning in Evolutionary Computation Systems
Types of Learning in Rule Based Systems
Rule Induction Systems
Concept Learning and Classification
Conclusion
The computing world has a lot to gain from neural networks
Neural networks also contribute to other areas of research such as neurology and psychology.
the most exciting aspect of neural networks is the possibility that some day 'conscious' networks might be produced