From f005ea9cc9361a78a2aa74da5fbaa250f6a0f769 Mon Sep 17 00:00:00 2001 From: Mike Clark Date: Sun, 1 Nov 2020 00:17:19 +0000 Subject: [PATCH] Update readme.md --- readme.md | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/readme.md b/readme.md index 3782764..066bfb8 100644 --- a/readme.md +++ b/readme.md @@ -98,7 +98,9 @@ This has a better calibrated uncertainty and a better fit ## Experiment: Comparing models on toy 1d regression -I put some work into replicating the behaviour shown in the [original deepmind tensorflow notebook](https://github.com/deepmind/neural-processes/blob/master/attentive_neural_process.ipynb). At the same time I compared multiple models. +I put some work into replicating the behaviour shown in the [original deepmind tensorflow notebook](https://github.com/3springs/attentive-neural-processes/blob/RANPfSD/anp-rnn_1d_regression.ipynb). At the same time I compared multiple models. + +Note this is in the RANPfSD branch. ### Results @@ -119,7 +121,7 @@ Compare deepmind: ![](docs/deepmind1.png) -And this repo with an ANP (anp_1d_regression.ipynb) +And this repo with an ANP (https://github.com/3springs/attentive-neural-processes/blob/RANPfSD/anp-rnn_1d_regression.ipynb) ![](docs/replicate2.png)