HBR
• 1.6k
• 6
• 7

The idea is that each $$\vec{y}_k$$ depends on $$\vec{w}$$. Therefore for the first equation, simply apply the chain rule for each $$\vec{y}_k$$ and sum them up. Componentwise one has: $$\frac{dL}{d\vec{w}}=\sum_k{\frac{dQ}{d\vec{y}_k}\cdot\frac{\partial \vec{y}_k}{\partial \vec{w}}} \tag{*}$$$$\left(\frac{dL}{d\vec{w}}\right)_{i}=\sum_{k,\alpha}{\left(\frac{dQ}{d\vec{y}_k}\right)_{\alpha}\left(\frac{\partial \vec{y}_k}{\partial \vec{w}}\right)_{i\alpha}} \tag{*}$$ Maybe the order in which they appear multiplying each other has confused you.

The second is obtained supposing that the function $$\vec{y}_{k}$$ can be put as a function of $$\vec{y}_{k+1}$$ (your first equation suggets this). Therefore the derivative in $$(*)$$ can be expressed as: $$\frac{dQ}{d\vec{y}_k}=\frac{dQ}{d\vec{y}_{k+1}}\cdot\frac{\partial \vec{y}_{k+1}}{\partial \vec{y}_k}$$$$\frac{dQ}{d\vec{y}_k}=\frac{\partial \vec{y}_{k+1}}{\partial \vec{y}_k}\frac{dQ}{d\vec{y}_{k+1}}$$

HBR
• 1.6k
• 6
• 7

The idea is that each $$\vec{y}_k$$ depends on $$\vec{w}$$. Therefore for the first equation, simply apply the chain rule for each $$\vec{y}_k$$ and sum them up: $$\frac{dL}{d\vec{w}}=\sum_k{\frac{dQ}{d\vec{y}_k}\cdot\frac{\partial \vec{y}_k}{\partial \vec{w}}} \tag{*}$$ Maybe the order in which they appear multiplying each other has confused you.

The second is obtained supposing that the function $$\vec{y}_{k}$$ can be put as a function of $$\vec{y}_{k+1}$$ (your first equation suggets this). Therefore the derivative in $$(*)$$ can be expressed as: $$\frac{dQ}{d\vec{y}_k}=\frac{dQ}{d\vec{y}_{k+1}}\cdot\frac{\partial \vec{y}_{k+1}}{\vec{y}_k}$$$$\frac{dQ}{d\vec{y}_k}=\frac{dQ}{d\vec{y}_{k+1}}\cdot\frac{\partial \vec{y}_{k+1}}{\partial \vec{y}_k}$$

HBR
• 1.6k
• 6
• 7

The idea is that each $$\vec{y}_k$$ depends on $$\vec{w}$$. Therefore for the first equation, simply apply the chain rule for each $$\vec{y}_k$$ and sum them up: $$\frac{dL}{d\vec{w}}=\sum_k{\frac{dQ}{d\vec{y}_k}\cdot\frac{\partial \vec{y}_k}{\partial \vec{w}}} \tag{*}$$ Maybe the order in which they appear multiplying each other has confused you.

The second is obtained supposing that the function $$\vec{y}_{k}$$ can be put as a function of $$\vec{y}_{k+1}$$ (your first equation suggets this). Therefore the derivative in $$(*)$$ can be expressed as: $$\frac{dQ}{d\vec{y}_k}=\frac{dQ}{d\vec{y}_{k+1}}\cdot\frac{\partial \vec{y}_{k+1}}{\vec{y}_k}$$