this is for holding javascript data
Bernal Jimenez edited section_Descending_the_Alternate_Sparse__.tex
about 8 years ago
Commit id: 60dc18998ea2cbabcd3849125cb475b7ef0ebb7a
deletions | additions
diff --git a/section_Descending_the_Alternate_Sparse__.tex b/section_Descending_the_Alternate_Sparse__.tex
index b32612c..2876c74 100644
--- a/section_Descending_the_Alternate_Sparse__.tex
+++ b/section_Descending_the_Alternate_Sparse__.tex
...
\begin{equation}
-\frac{\partial E(a| X; \Phi, W, \theta)}{\partial a_i} = \sum_jX_j\Phi_{ji}-\sum_j \Phi_{ji}^2a_i - \theta_i - 2\sum_{j\ne i}W_{ji}a_j.
\end{equation}
The first term is the same linear filtering
term as in SAILnet. term. The second is the leakiness term with an additional scaling by the length squared of the dictionary element. The dictionary is commonly normalized to have length 1 to prevent it from growing without bound, although Oja's rule does not require this. Empirically, the mean norm will be on the order of length 1, but can vary by a small integer factor and will have non-zero variance. It is an interesting prediction that the leakiness of the membrane of a neuron should scale with the overall strength of its synapses. $-\theta$ would be converted into a spike-threshold in a LIF version of this analog equation. Finally, the last term
is twice the SAILnet value due to $W$
being symmetric. accounts for within layer inhibition.
Without an LIF circuit, the analog optimization problem is thus solved by