Aspire's Library

A Place for Latest Exam wise Questions, Videos, Previous Year Papers,
Study Stuff for MCA Examinations - NIMCET

Previous Year Question (PYQs)

Let $W_{ij}$ represents weight between node $i$ at layer $k$ and node $j$ at layer $(k-1)$ of a given multilayer perceptron. The weight updation using gradient descent method is given by:





Solution

In gradient descent, weights are updated in the opposite direction of the gradient.

The general rule is:

$New\ Weight=Old\ Weight-\alpha\times Gradient$

Here,

$\alpha$ is the learning rate.

So,

$W_{ij}(t+1)=W_{ij}(t)-\alpha\dfrac{\partial E}{\partial W_{ij}}$


Online Test Series,
Information About Examination,
Syllabus, Notification
and More.

Click Here to
View More

Online Test Series,
Information About Examination,
Syllabus, Notification
and More.

Click Here to
View More
Ask Your Question or Put Your Review.

loading...