Consider the following training set:

Input values $(x)$

Pattern $1$: $x=(0,1)$

Pattern $2$: $x=(1,0)$

Target output values

$-1$

$1$

initial weight: $w=(0\mathrm{.}1,0\mathrm{.}1),$ learning constant: $=0\mathrm{.}1,$ activation function: $f(x)=$

$2x+1.$

Find the weight vector of the first epoch of gradient descent error minimization and

delta learning rules for the training set given above. The weight update rule for gradient

descent error minimization is given as follows:

$w_{kl}=\frac{\text{d}\text{e}\text{l}\text{E}(w_{ij})}{del{w}_{kl}}={\displaystyle \underset{p=1}{\overset{?}{}}}(tar{g}_l-ou{t}_l)f^{\text{'}}({\displaystyle \underset{i=1}{\overset{?}{}}}i{n}_i{w}_{il})i{n}_k$Consider the following training set: input values $($x$)$ desired output values $($y$)$ x $1=(-1,-1,-1)1$ x $2=(1,1,1)-1$ Given the learning constant $\backslash$alpha $=0\mathrm{.}1$and initial weight vector w $0=(0\mathrm{.}1,0\mathrm{.}1,0\mathrm{.}1)$: Use the perceptron learning method to find the weight vector for the training set given above for one epoch $($update the weight vector one time for each training pattern$)?1.$ Consider the following training set: $[$ input values $($x$)$ desired output values $($y$)$; x$^1=(-1,-1,-1)1$; x$^2=(1,1,1)-1]$ Given the learning constant $\backslash$alpha $=0\mathrm{.}1$ and initial weight vector w$^0=(0\mathrm{.}1,0\mathrm{.}1,0\mathrm{.}1)$ : Use the perceptron learning method to find the weight vector for the training set given above for one epoch $($update the weight vector one time for each training pattern$)?$