Question: Compute the Gradient [ 1 ] y = sigma ( wx + b ) = sigma ( 2 . 0 3 . 5

Compute the Gradient [1]
y=\sigma (wx + b)=\sigma (2.03.52.0)0.0180
wL =(y y) x =(0.01800.5)3.50.493
bL =y y =0.01800.50.482
Update Moving Averages [2]
sW =\beta sW +(1\beta )(wL)
2=0.900+0.10(0.493)20.0243
sB =\beta sB +(1\beta )(bL)
2=0.900+0.10(0.482)20.0233
Update Weights and Biases [2]
w = w +
\eta
sW +
wL =2.0+
0.10
0.0243+1e 8
(0.493)2.0482
b = b +
\eta
sB +
bL =2.0+
0.10
0.0233+1e 8
(0.482)2.0471
(b) No marks for equations
Forward Pass [1]
h =\sigma (w1x1+ w2x2+ b)=\sigma (0.73.5+0.20.5+0)0.927
Compute the reconstructed outputs [1]
x1= h w3+ b =0.927(0.2)=(0.1854)
x2= h w4+ b =0.9270.5=0.4635

Step by Step Solution

There are 3 Steps involved in it

1 Expert Approved Answer
Step: 1 Unlock blur-text-image
Question Has Been Solved by an Expert!

Get step-by-step solutions from verified subject matter experts

Step: 2 Unlock
Step: 3 Unlock

Students Have Also Explored These Related General Management Questions!