Neural networks

1
Neural Networks
Swipe
2
What is neural network?
An Artificial Neural Network (ANN) is an
information processing paradigm that is inspired
by biological nervous systems. It is composed of
a large number of highly interconnected
processing elements called neurons. An ANN is
configured for a specific application, such as
pattern recognition or data classification .
3
Why use neural networks?
Ability to derive meaning from complicated or
imprecise data. Extract patterns and detect
trends that are too complex to be noticed by
either humans or other computer
techniques. Adaptive learning. Real Time
Operation. Neural networks enable us to find
solution where algorithmic methods are
computationally intensive or do not exist. There
is no need to program neural networks they learn
with examples. Neural networks offer significant
speed advantage over conventional techniques.
4
Neural Networks v/s Conventional Computer
Conventional computers use an algorithmic
approach, but neural networks works similar to
human brain and learns by example.
5
Inspiration from Neurobiology
A neuron many-inputs / one?output unit. Output
can be excited or not excited. Incoming signals fr
om other neurons determine if the neuron shall
excite ("fire"). Output subject to attenuation in
the synapses, which are junction parts of the
neuron.
output
inputs
6
Types of neural networ
Fixed networks, in which the weights cannot be
changed, ie dW/dt0. In such networks, the
weights are fixed a priori according to the
problem to solve. Adaptive networks, which are
able to change their weights, ie dW/dt not 0.
7
The Learning Process
Associative mapping in which the network learns
to produce a particular pattern on the set of
input units whenever another particular pattern
is applied on the set of input units. The
associative mapping can generally be broken down
into two mechanisms Nearest-neighbour recall.
Interpolative recall
8
Hetero-association recall mechanisms
Nearest-neighbour recall, where the output
pattern produced corresponds to the input
pattern stored, which is closest to the pattern
presented. Interpolative recall, where the
output pattern is a similarity dependent
interpolation of the patterns stored
corresponding to the pattern presented. Yet
another paradigm, which is a variant associative
mapping is classification, ie when there is a
fixed set of categories into which the input
patterns are to be classified.
9
Key Features
Neural network design, training, and simulation.
Pattern recognition, clustering, and data-fitting
tools. Unsupervised networks including
self-organizing maps and
competitive layersSupervised networks
feedforward, radial basis, LVQ, time delay,
including nonlinear

• autoregressive (NARX), and layer-recurrents.
• Preprocessing and postprocessing for improving
  the efficiency of network training and assessing
  network performance.
• Modular network representation for managing and

visualizing networks of arbitrary size.
Routines for improving generalization
overfitting.
to prevent
Simulinkblocks for building and evaluating
networks, and advanced blocks for control
applications.
neural systems
10
Topics for next Post
Similarity learning
Stay Tuned with