Scribd
Upload
2K views1 page

Limitations of Perceptrons

Perceptrons have limitations in that they can only output 0 or 1 and can only classify data that is linearly separable. They cannot compute the XOR function since it is not linearly separable, with its positive and negative instances unable to be separated by a line. This was a major drawback, but multilayer networks have since solved this issue.

Uploaded by

vinay kumar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
2K views1 page

Limitations of Perceptrons

Perceptrons have limitations in that they can only output 0 or 1 and can only classify data that is linearly separable. They cannot compute the XOR function since it is not linearly separable, with its positive and negative instances unable to be separated by a line. This was a major drawback, but multilayer networks have since solved this issue.

Uploaded by

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

Limitations of Perceptrons:

(i) The output values of a perceptron can take on only one of two values (0 or
1) due to the hard-limit transfer function.
(ii) Perceptrons can only classify linearly separable sets of vectors. If a
straight line or a plane can be drawn to separate the input vectors into their
correct categories, the input vectors are linearly separable. If the vectors are
not linearly separable, learning will never reach a point where all vectors are
classified properly
The Boolean function XOR is not linearly separable (Its positive and negative
instances cannot be separated by a line or hyperplane). Hence a single layer
perceptron can never compute the XOR function. This is a big drawback
which once resulted in the stagnation of the field of neural networks. But this
has been solved by multi-layer.

You might also like