iteration 0/100 · avg error 50.0%learning rate 2.0 · 100 iterations
smile% = σ(score) = 1 ⁄ (1 + e−score) · score = w1·p1 + w2·p2 + … + w12·p12

the 12 multipliers

0
0
0
0
0
0
0
0
0
0
0
0

training faces

target100%
score0
σ →50%
target0%
score0
σ →50%
target0%
score0
σ →50%
target100%
score0
σ →50%

loss — average error

0%25%50%

draw a face — test it

σ 50% (0) → undecided
predicting with: trained · 100 iterations