0% found this document useful (0 votes)
15 views7 pages

Artificial Intelligence (AI) - A Level

Uploaded by

Denver Demis
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
0% found this document useful (0 votes)
15 views7 pages

Artificial Intelligence (AI) - A Level

Uploaded by

Denver Demis
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/ 7

Artificial Intelligence

[AI]
[Machine Learning, Artificial Neural Networks, Deep Learning]
Machine Learning
• What is machine learning?
• Machine learning is part of AI
• Machine learning is used by AI to manage data

There are multiple types of Learning Techniques

Supervised

Learning Unsupervised
Techniques
Reinforcement
Learning Techniques
Unsupervised Learning Reinforcement
• The system draws its own conclusions
Learning
• The data given is very wide
• This is a mix of the
• There is no restriction to the data they
previous two learning
have
methods
• Machine creates it’s own equations
accordingly • The datas are given wide
• The experts are also there
• It works based on reward
Supervised Learning system when ever it makes
a right choice
• The system does not draw its own • Example:- Maze solving or
conclusions robots that play chess
• The data given is very limited
• Expert Systems are used
• Machine creates it’s own equation from
the expert’s suggestion
Regression Analysis
• Method of function for AI
• “finding Correlation between input and output”
• Using mathematical formulas
• Using functions to predict and provide
Artificial Neural Network
Back Propagation Of Errors

• An algorithm for machine learning that optimizes the

values for parameters which are adjustable. It is applied

first to the nodes in the output layer and then works

backward through the nodes in hidden layers until

finally the input nodes are considered


Deep Learning

• An algorithm uses artificial neural network while having

multiple hidden layers which cannot be known by any

person other than the algorithm itself

You might also like