1,884
个编辑
更改
→神经信息压缩方法
<math>\min_{\omega,\theta,\theta'} \sum_{i=0}^{T-1}w(\boldsymbol{x}_t)||\boldsymbol{y}_t-g_{\theta'}(\boldsymbol{y}_{t+1})||+\lambda|| \hat{\boldsymbol{x}}_{t+1}-\boldsymbol{x}_{t+1} ||</math>
<math>\min_{\omega,\theta,\theta'} \sum_{i=0}^{T-1}w(\boldsymbol{x}_t)||\boldsymbol{y}_t-g_{\theta'}(\boldsymbol{y}_{t+1})||+\lambda|| \hat{\boldsymbol{x}}_{t+1}-\boldsymbol{x}_{t+1} ||</math>
其中<math>w(x_t)</math>为逆概率权值,如下所示
其中<math>w(x_t)</math>为逆概率权值,如下所示：
<math>
<math>
w(\boldsymbol{x}_t)=\frac{\tilde{p}(\boldsymbol{y}_t)}{p(\boldsymbol{y}_t)}=\frac{\tilde{p}(\phi(\boldsymbol{x}_t))}{p(\phi(\boldsymbol{x}_t))}
w(\boldsymbol{x}_t)=\frac{\tilde{p}(\boldsymbol{y}_t)}{p(\boldsymbol{y}_t)}=\frac{\tilde{p}(\phi(\boldsymbol{x}_t))}{p(\phi(\boldsymbol{x}_t))}