Professional Documents
Culture Documents
and
Neural network Learning
Knowledge Engineering
• Knowledge Engineering is the process of designing knowledge_x0002_based systems
(e.g. expert systems, data-driven models)
• It consist of three stages:
• Knowledge acquisition : the process of obtaining the knowledge from experts.
• Learning by observation.
Knowledge Representation
Knowledge Representation Paradigms
According to McCalla and Cercone (1983):
• Semantic networks are concept graphs connected by relations, such as IS-A
relation (Dog IS-A mammal).
• First-order logic is useful for manipulation of facts (e.g. automatic
theorem_x0002_proving).
• Frames or schemata are decomposable structures or chunks used to represent
concepts.
• Production systems are algorithms represented by sets of rules
(condition_x0002_action pairs), which were used to model human reasoning.
NEURAL NETWORK LEARNING
What is meant with learning?
• The ability of the neural network (NN) to learn form its environment
and to improve its performance through learning.
3)Hebbian Learning←Neurobiological
4)Competitive Learning←Neurobiological
→ A set of neurons that are all the same ( excepts for synaptic weights).
• Clamped Conditions:
The visible neurons are al lclamped onto specific states determined by
the environment.
• Free -Running Conditions:
→ All the neurons (visible and hidden) are allowed to operate freely.
→The Boltzmann learning rule:
∆Wkj= ɳ(Pkj+ -Pkj-),
J≠K
Credit Assignment
Desired
Environment Teacher Response
+
Actual Response
Learning System
Error Signal
→ Error-performance surface.
Learning without a teacher
• No labeled examples available of the function to be
learned.
a)Reinforcement learning
b)Unsupervised learning
Reinforcement learning
Primary reinforcement
State input (vector)
Environment Critic
Heuristic Reinforcement
Action Learning System
X Y
Pattern Associator