Computer science

\ufeffTASK

- 3 ("

BASICS

"

\ufeffof ANNs

)

Consider deep feedforward ANN with its weights and biases, specified in Figure. This ANN has one input layer, two hidden layers and one output layer.

For simplicity, assume, that activation function for each node is an identity function, i

.

.

\ufeffa linear function with UNIT coefficient: g

(

) =

.

For known outputs y

1 = 369

; y

2 = 19

; y

3 = 316

\ufeffand known second input x

2 = 14,

\ufeffdetermine the first input x

1,

\ufeffgiven by the positive or negative integer with absolute value less than

100 (

this condition can be expressed as follows:

|

1 | < 100) .

Figure

- 3

: Given deep ANN with one input layer, two hidden layers and one output layer.

\ufeff

YOUR TASK

- 3

\ufeffANSWER:

*

10

\ufeffpoints

Your answer

SUBMIT YOUR MATLAB SCRIPT FOR Task

- 3

\ufeffAS ONE

(

SINGLE

)

\ufeffFILE INTO THE WINDOW BELOW, using \'cut

-

and

-

paste\' method, cutting the script from your

* .

M file.

Hidden Layer

- 2

Answer