4. Artificial Neural Networks
Objectives of this class:
• Functionality of a (artificial) neuron
• Neural networks (NN)
• Training of a NN
Universität Paderborn, ADT 3.2
Background, Definitions
●
An artificial neural network (ANN), often just called a "neuralnetwork" (NN), is a mathematical model or computational model based on biological neural networks.
●
It consists of an interconnected group of artificial neurons and processes information using a connectionist approach tocomputation.
●
In most cases an ANN is an adaptive system that changes its structure based on external or internal information that flows through the network during the learning phase.●
In more practical terms neural networks are non-linear statistical data modeling tools.●
NN can be used to model complex relationships between inputs and outputs or to find patterns in data.Functional Model of a Neuron (Brain Cell)
Synapse
Dendrite
Soma Axon
Universität Paderborn, ADT 3.4
Technical Model of a Neuron
O
Schmitt Trigger +
–
a
Operational Amplifier (a: amplification factor) I1
I2 I3
(Additive)
I1 I2
I3
O
a Symbol of a Neuron
increasing decreasing
Neuronal Network
I1 I2 I3
O1 O2
Feedback