From 5f8d63a688f8738ddec5f62b0de79cd5843c67e0 Mon Sep 17 00:00:00 2001
From: ernstklrb <33454758+ernstklrb@users.noreply.github.com>
Date: Wed, 23 Sep 2020 13:55:57 +0200
Subject: [PATCH 1/2] fix README.md spelling, wording

---
 README.md | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/README.md b/README.md
index 764ccfd..6bdace0 100644
--- a/README.md
+++ b/README.md
@@ -17,8 +17,8 @@ instance, in an object recognition network, an attribution method could tell us
 which pixels of the image were responsible for a certain label being picked, or
 which words from sentence were indicative of strong sentiment.
 
-Applications range from helping a developer debug, allowing analysts to explore
-the logic of a network, and to give end-user’s some transparency into the reason
+Applications range from helping a developer debug over allowing analysts to explore
+the logic of a network to giving end-users some transparency into the reason
 for a network’s prediction.
 
 **Integrated Gradients** is a variation on computing the gradient of the
@@ -44,14 +44,14 @@ deep models (sparse and dense, text and vision).
 This [How-To document][howto] describes the steps involved in implementing integrated gradients
 for an arbitrary deep network.
 
-This repository provideds code for implementing integrated gradients for networks
+This repository provides code for implementing integrated gradients for networks
 with image inputs. It is structured as follows:
 * [Integrated Gradients library][intgrad-lib]: Library implementing the core
 integrated gradients algorithm.
 * [Visualization library][vis-lib]: Library implementing methods for visualizing
 atributions for image models.
 * [Inception notebook][incp-notebook]: A [Jupyter](http://jupyter.org/) notebook
-for generating and visualizing atributions for the [Inception (v1)][incp-paper]
+for generating and visualizing attributions for the [Inception (v1)][incp-paper]
 object recognition network.
 
 We recommend starting with the notebook. To run the notebook, please follow the following instructions.

From bfe68f5a6790bd989cf7da2667c76900d77037d1 Mon Sep 17 00:00:00 2001
From: ernstklrb <33454758+ernstklrb@users.noreply.github.com>
Date: Thu, 24 Sep 2020 08:18:31 +0200
Subject: [PATCH 2/2] remove (my) clumsy range-over-to construct

---
 README.md | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/README.md b/README.md
index 6bdace0..9f677e5 100644
--- a/README.md
+++ b/README.md
@@ -17,9 +17,9 @@ instance, in an object recognition network, an attribution method could tell us
 which pixels of the image were responsible for a certain label being picked, or
 which words from sentence were indicative of strong sentiment.
 
-Applications range from helping a developer debug over allowing analysts to explore
-the logic of a network to giving end-users some transparency into the reason
-for a network’s prediction.
+Applications include helping developers debug their models, allowing analysts 
+to explore the logic of a model, and giving end-users some transparency into the 
+reason for a network's prediction.
 
 **Integrated Gradients** is a variation on computing the gradient of the
 prediction output w.r.t. features of the input. It requires no modification to