Download as pptx, pdf, or txt
Download as pptx, pdf, or txt
You are on page 1of 10

Department Of Artificial Intelligence

And Machine Learning.

Presented By:
 BHARANI B I Guided By:
 MANOJ KUMAR S G
 SARAVANA HARIS S
MR.JEYAGANESH
 MITHILESH G
 KEERTHI VASAN E
ARTIFICIAL NEURAL
NETWORK
INTRODUCTION TO ANN…
Artificial neural networks are a fascinating area of
study that have revolutionized the field of machine
learning. At their core, they are designed to mimic the
way our brains process information, using
interconnected nodes to analyze and interpret data.
 Artificial neural networks are a series of algorithms
that work together to recognize patterns in data.
WHAT IS ANN?
Artificial neural networks (ann) are a type of machine
learning algorithm that are modeled after the structure
and function of the human brain.
Just like the human brain is made up of interconnected
neurons, ann consist of layers of interconnected nodes.
These nodes process and transmit information through
the network, allowing the ANN to learn from data and
make predictions.
HOW DO ANN WORKS?
Artificial neural networks (anns) are modeled after the
human brain, with layers of interconnected nodes called
neurons. Each neuron receives input from other neurons
and processes that input to produce an output.
The output is then passed on to other neurons in the
next layer until a final output is produced. During
training, the weights between neurons are adjusted to
minimize the difference between the predicted output
TRAINING AN ANN
Artificial neural networks are
trained using a process called
backpropagation, which involves
adjusting the weights of the
connections between neurons based
on the difference between the
predicted output and the actual
output. This process is repeated
multiple times until the network is
TYPES OF ANN
There are three main types of artificial neural networks:
Feedforward neural network.
Recurrent neural network.
Convolutional neural network.
ADVANTAGES OF ANN
Advantages of artificial neural network,
The ability to learn and adapt.
 The ability to handle complex relationships.
The ability to generalize.
The ability to deal with noise.
The ability to be parallelized.
LIMITATIONS OF ANN
Limitations of artificial neural network,
Artificial neural networks require lots of computational
power.
 Neural network models are hard to explain.
Neural network training requires lots of data.
Data preparation for neural network models needs
careful attention.
Optimizing neural network models for production can
APPLICATIONS OF ANN
Artificial neural networks are used for a range of
applications,
Image recognition
Speech recognition
Machine translation
Natural language processing
Medical diagosis
Financial trading

You might also like