1,923
个编辑
更改
→神经信息压缩方法
<math>\max_{\phi,f_q,\phi^+} \mathcal{J}(f_q), s.t. || \hat{\boldsymbol{x}}_{t+1}-\boldsymbol{x}_{t+1} || < \epsilon, \hat{\boldsymbol{x}}_{t+1}=\phi^{\dag}(f_q(\phi(\boldsymbol{x}_t))).</math>
<math>\max_{\phi,f_q,\phi^+} \mathcal{J}(f_q), s.t. || \hat{\boldsymbol{x}}_{t+1}-\boldsymbol{x}_{t+1} || < \epsilon, \hat{\boldsymbol{x}}_{t+1}=\phi^{\dag}(f_q(\phi(\boldsymbol{x}_t))).</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>
<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>