this is for holding javascript data
Bernal Jimenez edited In_this_document_we_will__.tex
about 8 years ago
Commit id: 835994887e3751adf1680c7231464fe8f3172478
deletions | additions
diff --git a/In_this_document_we_will__.tex b/In_this_document_we_will__.tex
index 77ea7f5..e591976 100644
--- a/In_this_document_we_will__.tex
+++ b/In_this_document_we_will__.tex
...
In this document, we will describe alternative versions of SAILnet \cite{Zylberberg_2011} which address the convergence issues present in the original. The first section \ref{descend} will briefly sketch the sparse approximation equations obtained when the membrane potentials in SAILnet are interpreted as continuous coefficients in our sparse coding model. We will explore the gradient that arises both from the standard RMS reconstruction error and the version of Oja's rule used in SAILnet. In section
\ref{thresh} \ref{thresh}, we will introduce a thresholding approach to maintain neurally plausible properties but also descend the reconstruction, sparsity and decorrelation objective in a similar manner to Rozell's LCA \cite{Rozell_2008}. Finally, in section \ref{spike}, we will show that a spiking version of our Rate-based Sparse and Independent Local network will converge to the appropriate sparse coefficients \cite{Shapero_13}.