PRESENTATION ON

NEURAL NETWORKS

GROUP-5
1st Sem BCA ‘B’
KRISTU JAYANTI COLLEGE
SESSION-1
 INTRODUCTION

The term neural network had been used to

refer to a network or circuit of biological
neurons. The modern usage of the term
often refers to artificial neural networks,
which are composed of artificial neurons or
nodes.
It has two distinct usages:
 Biological neural networks
 Artificial neural networks
BIOLOGICAL NEURAL NETWORKS

 Biological neural networks are made up of

real biological neurons that are connected
or functionally related in the peripheral
nervous system or the central nervous
system.
 In the field of neuroscience, they are often
identified as groups of neurons that perform
a specific physiological function in
laboratory analysis.
BIOLOGICAL NEURAL NETWORKS
 ARTIFICIAL NEURAL
NETWORKS
 Artificial neural networks are made up of
interconnecting artificial neurons .
 Artificial neural networks may either be
used to gain an understanding of biological
neural networks.
 For solving artificial intelligence problems
without necessarily creating a model of a
real biological system.
 The real, biological nervous system is highly
complex and includes some features that
ARTIFICIAL NEURAL NETWORKS
 HISTORY

 The concept of neural networks started in the

late 1800s as an effort to describe how the
human mind performed.
 The Austrian School of economics theory of
spontaneous order was explained by Murray
Rothbard .
 In the brain spontaneous order arises out of
decentralized networks of simple units
(neurons).
 History(cont.)
 In the late 1940s Donald Hebb made one of the
first hypotheses of learning with a mechanism of
neural plasticity called Hebbian learning.
 Hebbian learning is considered to be a 'typical'
unsupervised learning rule and it and later
variants were early models for long term
potentiation.
 These ideas started being applied to
computational models in 1948 with Turing's B-
type machines and the perceptron.
 APPLICATIONS

 Facial Animation
 Behavioral Animation and Evolution of
Behavior
 Autonomous Walker & Swimming Eel
 Robocup: Robot World Cup
 FACIAL ANIMATION

 Facial animations created using hierarchical

B-spline as the underlying surface
representation.
 Neural networks could be use for learning
of each variations in the face expressions for
animated sequences.
 Groups of control vertices were then moved
around to created various facial expressions
 Three of these expressions were chosen as
key shapes, the spline surface was exported
FACIAL ANIMATION
BEHAVIORAL ANIMATION AND
EVOLUTION OF BEHAVIOR
 The more elaborate behavioral model
included predictive obstacle avoidance and
goal seeking.
 Obstacle avoidance allowed the boids to fly
through simulated environments while
dodging static objects.
 For applications in computer animation, a
low priority goal seeking behavior caused the
flock to follow a scripted path.
BEHAVIORAL ANIMATION AND
EVOLUTION OF BEHAVIOR
 AUTONOMOUS WALKER &
SWIMMING EEL
 The research in this area involves
combining biology, mechanical engineering
and information technology.
 In order to develop the techniques
necessary to build a dynamically stable
legged vehicle controlled by a neural
network.
 This would incorporate command signals,
sensory feedback and reflex circuitry in
order to produce the desired movement.
AUTONOMOUS WALKER &
SWIMMING EEL
 ROBOCUP: ROBOT WORLD
CUP
 The training of player in the process of making the
decision of whether (a) to dribble the ball; (b) to pass
it on to another team-mate; (c) to shoot into the net.
 The training of the goalkeeper in process of
intelligent guessing of how the ball is going to be kick
by the opponents. Complexities arise when one
opponent decides to pass the ball to another player
instead of attempting a score.
 Evolution of a co-operative and perhaps
unpredictable team.
ROBOCUP: ROBOT WORLD CUP
 CONCLUSION
 The development of true Neural Networks is
a fairly recent event, which has been met with
success.
 Two of the different systems that have been
developed are: the basic feed forward
Network and the Hopfield Net.
 The future of Neural Networks is wide open,
and may lead to many answers and/or
questions.
THANK YOU