Move framework.md out of the tutorials directory.

The framework description is a standalone document and doesn't belong with the tutorials, which are examples demonstrating the use of the NSL framework.

PiperOrigin-RevId: 268250707

Author: arjung

g3doc/_book.yaml

@@ -14,7 +14,7 @@ upper_tabs:
     - name: Guide & Tutorials
       contents:
       - title: Framework
-        path: /neural_structured_learning/tutorials/framework
+        path: /neural_structured_learning/framework
       - title: Install
         path: /neural_structured_learning/install
       - heading: Neural graph learning tutorials

g3doc/_index.yaml

@@ -32,9 +32,9 @@ landing_page:
         </ul>
         <p>Incorporating structured signals is done only during training. So, the performance of the
         serving/inference workflow remains unchanged. More information on neural structured learning
-        can be found in our <a href="tutorials/framework">framework description</a>. To get started,
+        can be found in our <a href="framework">framework description</a>. To get started,
         please see our <a href="install"> install guide</a>, and for a practical introduction to
-        NSL, check out our <a href="tutorials/framework#step-by-step_tutorials">tutorials.</a></p>
+        NSL, check out our <a href="framework#step-by-step_tutorials">tutorials.</a></p>
     - code_block: |
         <pre class = "prettyprint">
         import tensorflow as tf

g3doc/tutorials/framework.md renamed to g3doc/framework.md

@@ -11,7 +11,7 @@ minimizing the neighbor loss, see the figure below). This technique is generic
 and can be applied on arbitrary neural architectures (such as Feed-forward NNs,
 Convolutional NNs and Recurrent NNs).
 
-![NSL Concept](../images/nlink_figure.png)
+![NSL Concept](images/nlink_figure.png)
 
 Note that the generalized neighbor loss equation is flexible and can have other
 forms besides the one illustrated above. For example, we can also select
@@ -41,7 +41,7 @@ neighbor loss. On the other hand, for induced neighbor-based regularization
 (adversarial), we compute the neighbor loss as the distance between the output
 prediction of the induced adversarial neighbor and the ground truth label.
 
-![NSL workflow](../images/workflow_overview.png)
+![NSL workflow](images/workflow_overview.png)
 
 ## Why use NSL?
 
@@ -80,15 +80,15 @@ To obtain hands-on experience with Neural Structured Learning, we have three
 tutorials that cover various scenarios where structured signals may be
 explicitly given, induced or constructed:
 
-*   [Graph regularization for document classification using natural graphs](graph_keras_mlp_cora.ipynb).
+*   [Graph regularization for document classification using natural graphs](tutorials/graph_keras_mlp_cora.ipynb).
     In this tutorial, we explore the use of graph regularization to classify
     documents that form a natural (organic) graph.
 
-*   [Graph regularization for sentiment classification using synthesized graphs](graph_keras_lstm_imdb.ipynb).
+*   [Graph regularization for sentiment classification using synthesized graphs](tutorials/graph_keras_lstm_imdb.ipynb).
     In this tutorial, we demonstrate the use of graph regularization to classify
     movie review sentiments by constructing (synthesizing) structured signals.
 
-*   [Adversarial learning for image classification](adversarial_keras_cnn_mnist.ipynb).
+*   [Adversarial learning for image classification](tutorials/adversarial_keras_cnn_mnist.ipynb).
     In this tutorial, we explore the use of adversarial learning (where
     structured signals are induced) to classify images containing numeric
     digits.