Scribd
Upload
37 views5 pages

Artificial Neural Network

Artificial neural networks are computing systems inspired by biological neural networks in animal brains that can learn tasks from examples without being explicitly programmed. They work by using a common model of multi-layer neural connections that can be trained to recognize patterns in data through backpropagation algorithms. For example, a neural network can be trained to identify images that contain cats by analyzing labeled example images of cats and non-cats and learning to automatically identify cat-like features without prior domain knowledge about cats.

Uploaded by

mexiwe
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
37 views5 pages

Artificial Neural Network

Artificial neural networks are computing systems inspired by biological neural networks in animal brains that can learn tasks from examples without being explicitly programmed. They work by using a common model of multi-layer neural connections that can be trained to recognize patterns in data through backpropagation algorithms. For example, a neural network can be trained to identify images that contain cats by analyzing labeled example images of cats and non-cats and learning to automatically identify cat-like features without prior domain knowledge about cats.

Uploaded by

mexiwe
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 5

Artificial Neural

Network
SAQIB SAEED (01-131162-026)
SUBTAIN HAIDER (01-131162-049)
What is Artificial Neural Network?
Artificial neural networks or connectionist systems are computing systems that are inspired by,
but not identical to, biological neural networks that constitute animal brains.
Such systems "learn" to perform tasks by considering examples, generally without programmed
with task-specific rules.
How it works?
This is a large and complex topic because
there are many different types of artificial
neural network models.
The most common model, which has become
the foundation for most of the others, is the
3-layer fully-connected backpropagation
model
Reference
Example
In image recognition, they might learn to identify images that contain cats by analyzing example
images that have been manually labelled as "cat" or "no cat" and using the results to identify
cats in other images.
They do this without any prior knowledge of cats, for example, that they have fur, tails, whiskers
and cat-like faces. Instead, they automatically generate identifying characteristics from the
examples that they process.
Thank you 
ANY QUESTIONS?

You might also like