this is for holding javascript data
Bernal Jimenez edited section_Thresholding_RateSAIL_label_thresh__.tex
about 8 years ago
Commit id: 959943d8918555ddb293f9dba40636fb08a00842
deletions | additions
diff --git a/section_Thresholding_RateSAIL_label_thresh__.tex b/section_Thresholding_RateSAIL_label_thresh__.tex
index 59b38aa..8846371 100644
--- a/section_Thresholding_RateSAIL_label_thresh__.tex
+++ b/section_Thresholding_RateSAIL_label_thresh__.tex
...
y_i &= 1 \text{ if } u_i > \theta_i \text{ else } 0
\end{split}
\end{equation}
which are leakiness, linear filtering, and inhibition. $y_j$ is the instantaneous spiking variable for neuron $i$. This circuit may not always descend the objective function, as we can show.
Given the analog optimization problem in \ref{desc}, there are a number of different ways to instantiate a LIF circuit to approximate inference. The negative gradient can be interpreted as the driving force in the circuit
\begin{equation}
\frac{du_i}{dt} = -\frac{\partial E(a|X; \Phi, W, \theta)}{\partial u_i} = -\frac{\partial E(a|X; \Phi, W, \theta)}{\partial a_i} \frac{\partial a_i}{\partial u_i}
\end{equation}