From 0738b0c283181ef1260a39e82caae65eb4684d4a Mon Sep 17 00:00:00 2001 From: mhjensen Date: Mon, 7 Oct 2019 23:01:48 +0200 Subject: [PATCH] rnn disposition --- doc/src/Recurrent/Recurrent.do.txt | 6 +++++- doc/src/Recurrent/Recurrent.do.txt~ | 3 +++ 2 files changed, 8 insertions(+), 1 deletion(-) diff --git a/doc/src/Recurrent/Recurrent.do.txt b/doc/src/Recurrent/Recurrent.do.txt index 2d054e465..9a1e83dba 100644 --- a/doc/src/Recurrent/Recurrent.do.txt +++ b/doc/src/Recurrent/Recurrent.do.txt @@ -38,4 +38,8 @@ This means also that we need to have weights that link both the inputs $x_t$ to the output from the previous time $y_{t-1}$ and $y_t$. The figure here shows an example of a simple RNN. -Add figures and bring up equations. Have example with eigenvalues solvers +Add figures and bring up equations. Have example with eigenvalues solvers as well. +Discussions about dynamic unrolling through time. discuss memory cells, input and output + +Add about LSTM cell. +Should add autoencoders? diff --git a/doc/src/Recurrent/Recurrent.do.txt~ b/doc/src/Recurrent/Recurrent.do.txt~ index cc3a0b6ea..2d054e465 100644 --- a/doc/src/Recurrent/Recurrent.do.txt~ +++ b/doc/src/Recurrent/Recurrent.do.txt~ @@ -36,3 +36,6 @@ the output from the previous layer $t-1$, that is $y_{t1}$. This means also that we need to have weights that link both the inputs $x_t$ to the outputs $y_t$ as well as weights that link the output from the previous time $y_{t-1}$ and $y_t$. The figure here shows an example of a simple RNN. + + +Add figures and bring up equations. Have example with eigenvalues solvers