가입 후 초대 링크를 공유하면 동영상 재생 및 초대 보상을 받을 수 있습니다.

Mathematica
@mathemetica
Math isn't escape. It's the map through the madness.
가입 October 2024
204 팔로잉 중    77.4K 팬
One neuron, by the numbers. Inputs 0.2, 0.5, 0.43 times weights 0.4, 0.26, 0.3 give 0.08 + 0.13 + 0.129. Add bias 0.1: z = 0.439. Activation: σ(z) = 1/(1 + e⁻ᶻ), so σ(0.439) ≈ 0.608. That number is passed to every neuron in the next layer. Training picks the weights w that minimise the average loss (1/n) Σ ℓ(h(xᵢ; w), yᵢ), by stepping down the loss surface along −∇L. Learning is weighted sums, a squashing function, and gradient descent.
더 보기