Initial content

ShashwatAntony · ShashwatAntony · commit d184a230cd53 · 2021-09-23T18:22:46.000+05:30
diff --git a/docs/about.md b/docs/about.md
@@ -1,7 +1,7 @@
-# Hoc cum cur indigenae sacra
-
-## Ut populos sacris
+# About Us
 
+## Coming Soon
+<!-- 
 Lorem markdownum Praescia qua cernens accessi congressus notavi, de castra
 trepidare amantem illum per, ire parvo. Grai boves induta orant moram opesque
 cessasse, rear sunt vero carpant. Mora dum **posse rapitur**, temerarius
@@ -77,3 +77,4 @@ quoque rumor terga et sinat vibrata resedit transit cetera eiaculatus fluctibus.
 Rura eodem imago virgineo communis vana; nullique sua: et amantis, fas nec,
 *aes* adeundi verbis, sit. Illa onerosa est, est vulgatos, nubes dedit perque
 inque?
+ -->
diff --git a/docs/algo.md b/docs/algo.md
@@ -0,0 +1,10 @@
+# Algorithm
+
+####Overview
+
+Arya XAI uses significance propagation as the base algorithm. This propagation is different for each network component as they follow different mathematical functions.
+
+Arya XAI currently has two modes of operation. 
+
+1. Network Analysis: In this mode, the significance is always positive and propagated according to the contribution of each unit. This can be used to prune the under-utilized parts of the network and modify the saturated ones. The is also helpful in reducing or modifying the input features. 
+2. Decision Analysis: In this mode, the significance can be negative or positive depending on the relative contribution of any unit to the decision. The is helpful in providing explanations based on which input features are positively/ negatively affecting the decision.
diff --git a/docs/examples.md b/docs/examples.md
@@ -0,0 +1,8 @@
+#Example
+
+#### Neural Network
+<p style="text-align:center;"><img src="/img/network.png" alt="drawing" width="400"></p>
+
+
+#### XAI Output
+<p style="text-align:center;"><img src="/img/weights.png" alt="drawing" width="400"></p>
diff --git a/docs/img/network.png b/docs/img/network.png
diff --git a/docs/img/weights.png b/docs/img/weights.png
diff --git a/docs/index.md b/docs/index.md
@@ -1,17 +1,9 @@
 # Welcome to Arya XAI
 
-For full documentation visit [mkdocs.org](https://www.mkdocs.org).
 
-## Commands
+####Arya-XAI - Translating ‘black box DL models’ into interpretable & trustable models
+Arya-XAI enhances & explains your DL model predictions, by generating new and simple interpretable explanations in real time as required by various stakeholders. 
 
-* `mkdocs new [dir-name]` - Create a new project.
-* `mkdocs serve` - Start the live-reloading docs server.
-* `mkdocs build` - Build the documentation site.
-* `mkdocs -h` - Print help message and exit.
+Current approaches to explain black box DL models are heavily reliant on specific data types and network components which severely limits their applicability on diverse use-cases and novel network architectures. This poses challenges to understand or explain true-to-model functioning. Arya-Xai  decodes this ‘true-to-model’ feature weightage along with node level weightages for any neural network. 
 
-## Project layout
-
-    mkdocs.yml    # The configuration file.
-    docs/
-        index.md  # The documentation homepage.
-        ...       # Other markdown pages, images and other files.
+The framework not only improves interpretability of DL models substantially, but also offers easy to understand reasons behind the outcome
diff --git a/mkdocs.yml b/mkdocs.yml
@@ -2,5 +2,7 @@ site_name: Arya XAI Documentation
 site_url: http://docs.arya-xai.ai/
 nav:
     - Home: index.md
+    - Algorithm: algo.md
+    - Example: examples.md
     - About: about.md
 theme: readthedocs
