Get the power of blast
Where:
$$X=[x_1,\ x_2,\ x_3,\ ...,\ x_n]^T$$ $$W=[w_1,\ w_2,\ w_3,\ ...,\ w_n]^T$$ $$\varepsilon=[\varepsilon_1,\ \varepsilon_2,\ \varepsilon_3,\ ...,\ \varepsilon_n]^T$$The aim is to search for the best W that minimize the mean of e.
\[{e^{-\Delta{r}{G^{'\circ}}/RT}}\] $$\hat p=\sigma(\theta^T \cdot x_b)=\frac{1}{1+\mathbf{e}^{-{\theta^{T \cdot x_b}}}}$$ \[f(r)= \frac{{e^{-\Delta{r}{G^{'\circ}}/RT}}}{1 + {e^{-\Delta{r}{G^{'\circ}}/RT}} + \sum {{r^'} \in {R_N}\backslash {{\left\{ r \right\}}^{{\rm{ }}{{\rm{e}}^{ - {\Delta _r}{G^{' \circ /RT}}}}}}} \] \[f{(r)=}\frac{{e}}^{-{\Delta_r}{G^{'\circ/RT}}}{{{{1+}}{{{e}}^{-{\Delta _r}{G^{'\circ/RT}}}}+\sum{{r^'}\in{R_N}\backslash{{\left\{r\right\}}^{{{}}{{{e}}^{-{\Delta _r{G^{'\circ/RT}}}}} $$J(\theta)=-\frac{1}{m}\displaystyle\sum_{i=1}^m y^{(i)}\log(\hat p^{(i)})+(1-y^{(i)})\log(1-\hat p^{(i)})\\ =-\frac{1}{m}\displaystyle\sum_{i=1}^m y^{(i)}\log(\sigma(-X_b^{(i)}\theta))+(1-y^{(i)})\log(1-\sigma(-X_b^{(i)}\theta))\\ \[f(r) = \frac{e^{-\Delta{r}{G^{'\circ}}/RT}}{{{\rm{1 + }}{{\rm{e}}^{ - {\Delta _r}{G^{' \circ /RT}}}} + \sum {{r^'} \in {R_N}\backslash {{\left\{ r \right\}}^{{\rm{ }}{{\rm{e}}^{ - {\Delta _r}{G^{' \circ /RT}}}}}}} }}}\] \[f{\rm{(r) = }}\frac{{{{\rm{e}}^{ - {\Delta _r}{G^{' \circ /RT}}}}}}{{{\rm{ 1 + }}{{\rm{e}}^{ - {\Delta _r}{G^{' \circ /RT}}}} + \sum {{r^'} \in {R_N}\backslash {{\left\{ r \right\}}^{{\rm{ }}{{\rm{e}}^{ - {\Delta _r}{G^{' \circ /RT}}}}}}} }}\]