aboutsummaryrefslogtreecommitdiffstats
path: root/paper
diff options
context:
space:
mode:
authorThibaut Horel <thibaut.horel@gmail.com>2015-02-06 01:58:36 -0500
committerThibaut Horel <thibaut.horel@gmail.com>2015-02-06 01:58:36 -0500
commitb07ea233bc2c519404f44f24c03b9a2c2f94c290 (patch)
treeecb6ba126c1714cdd20485be10518d6dad6e67f5 /paper
parent0b26569f6ec37266b449c01d9049118dc022dbfc (diff)
downloadcascades-b07ea233bc2c519404f44f24c03b9a2c2f94c290.tar.gz
Fix more bug
Diffstat (limited to 'paper')
-rw-r--r--paper/sections/model.tex2
1 files changed, 1 insertions, 1 deletions
diff --git a/paper/sections/model.tex b/paper/sections/model.tex
index cf69960..36829f2 100644
--- a/paper/sections/model.tex
+++ b/paper/sections/model.tex
@@ -61,7 +61,7 @@ where $f: \reals \rightarrow [0,1]$
\end{definition}
In other words, each generalized linear cascade provides, for each node $j \in
-V$ a series of measurements $(X^t, X^t_j)_{t \in {\cal T}_j}}$ sampled from
+V$ a series of measurements $(X^t, X^{t+1}_j)_{t \in {\cal T}_j}$ sampled from
a generalized linear model. Note also that $\E[X^{t+1}_i\,|\,X^t]
= f(\inprod{\theta_i}{X^t})$. As such, $f$ can be interpreted as the inverse
link function of our generalized linear cascade model.