1. Uploaded By : REHMAT ULLAH
ARTIFICIAL INTELIGENCE,Bcs 6th
KUST University,Kohat ,Pakistan
2/8/2012
2. Composed of many “neurons” that co-operate to
perform the desired function
Models of the brain and nervous system
Highly parallel
◦ Process information much more like the brain
than a serial computer
Learning
Very simple principles
Very complex behaviours
Applications
◦ As powerful problem solvers
◦ As biological models
3. An Artificial Neural Network is a network of many
very simple processors, each possibly having a local
memory.
Theunits are connected by unidirectional
communication channels, which carry numeric data.
Theunits operate only on their local data and on the
inputs they receive via the connections.
4. Classification
Pattern recognition, feature extraction, image matching
Noise Reduction
Recognize patterns in the inputs and produce noiseless
outputs
Prediction
Extrapolation based on historical data
5. Ability to learn
NN’s figure out how to perform their function on their
own
Determine their function based only upon sample inputs
Ability to generalize
i.e. produce reasonable outputs for inputs it has not been
taught how to deal with
6. A neuron: many-inputs / one-
output unit
Dendrites receive activation
from other neurons
Axons act as transmission
lines to send activation to
other neurons
Synapses ,the junctions allow
signal transmission between
the axons and dendrites
7. ANNs incorporate the two fundamental
components of biological neural nets:
1. Neurones (nodes)
2. Synapses (weights)
10. Neuron consists of three basic components.
1 . Weights
2 . Thresholds
3 . Activation function
11. Weighting Factors
The values w1,w2,…wn are weights to determine the
strength of input vector x=[x1,x2,…xn]T
Thresholds
The node’s internal threshold is the magnitude offset
Activation Function
Performs a mathematical operation on the signal output
Most common are linear,threshold,S shaped,tangent
hyperbolic function
Choice of function depend on the problem solved by the
neural network
12. Neural Networks offer improved performance over
conventional technologies in areas which includes:
Machine Vision
Robust Pattern Detection
Signal Filtering
Virtual Reality
Artificial Life
and more.
13. Advantages
◦ Adapt to unknown situations
◦ Robustness: fault tolerance due to network
redundancy
◦ Autonomous learning and generalization
Disadvantages
◦ Not exact
◦ Large complexity of the network structure
14. Learning the Distribution of Object Trajectories for
Event Recognition
Radiosity for Virtual Reality Systems
Speechreading (Lipreading)
Detection and Tracking of Moving Targets
Real-time Target Identification for Security
Applications
Autonomous Walker & Swimming Eel
15. Robocup: Robot
World Cup Using
HMM's (hidden
Markov
models) for
Audio-to-Visual
Conversion
Artificial Life:
Galapagos
16. The moving target detection and track methods here are "track before detect"
methods.
They correlate sensor data versus time and location, based on the nature of
actual tracks.
The track statistics are "learned" based on artificial neural network (ANN)
training with prior real or simulated data.
(a) Raw input
backgrounds
with weak
targets included,
(b) Detected
target sequence
at the ANN
processing
output,
post-detection
tracking not
included
17. As part of the research program Neuroinformatik the IPVR
develops a neural speechreading system as part of a user
interface for a workstation.
A neural classifier detects visibility of teeth edges and other
attributes. At this stage of the approach the edge between the
closed lips is automatically modeled if applicable, based on a
neural network's decision.
18. The system localises and tracks peoples' faces as they
move through a scene. It integrates the following
techniques:
1. Motion detection
2. Tracking people based upon motion
3. Tracking faces using an appearance model
Faces are tracked robustly by integrating motion and
model-based tracking.
19. (A) Tracking in low resolution and poor (B) Tracking two people
lighting conditions simultaneously: lock is maintained
on the faces despite unreliable
motion-based body tracking.