註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

Mathematica
@mathemetica
Math isn't escape. It's the map through the madness.
加入 October 2024
204 正在關注    77.4K 粉絲
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.
顯示更多