chore: add FL to showcase & encrypt/decrypt example

README.md

@@ -107,6 +107,34 @@ print(f"Similarity: {int((y_pred_fhe == y_pred_clear).mean()*100)}%")
     # Similarity: 100%
 ```
 
+It is also possible to call encryption, model prediction, and decryption functions separately as follows.
+Executing these steps separately is equivalent to calling `predict_proba` on the model instance.
+
+<!--pytest-codeblocks:cont-->
+
+```python
+# Predict probability for a single example
+y_proba_fhe = model.predict_proba(X_test[[0]], fhe="execute")
+
+# Quantize an original float input
+q_input = model.quantize_input(X_test[[0]])
+
+# Encrypt the input
+q_input_enc = model.fhe_circuit.encrypt(q_input)
+
+# Execute the linear product in FHE
+q_y_enc = model.fhe_circuit.run(q_input_enc)
+
+# Decrypt the result (integer)
+q_y = model.fhe_circuit.decrypt(q_y_enc)
+
+# De-quantize and post-process the result
+y0 = model.post_processing(model.dequantize_output(q_y))
+
+print("Probability with `predict_proba`: ", y_proba_fhe)
+print("Probability with encrypt/run/decrypt calls: ", y0)
+```
+
 This example is explained in more detail in the [linear model documentation](docs/built-in-models/linear.md). Concrete ML built-in models
 have APIs that are almost identical to their scikit-learn counterparts. It is also possible to convert PyTorch networks to FHE with the Concrete ML conversion APIs. Please refer to the [linear models](docs/built-in-models/linear.md), [tree-based models](docs/built-in-models/tree.md) and [neural networks](docs/built-in-models/neural-networks.md) documentation for more examples, showing the scikit-learn-like API of the built-in
 models.

docs/README.md

@@ -54,9 +54,10 @@ Executing these steps separately is equivalent to calling `predict_proba` on the
 <!--pytest-codeblocks:cont-->
 
 ```python
+# Predict probability for a single example
 y_proba_fhe = model.predict_proba(X_test[[0]], fhe="execute")
 
-# Quantize an input (float)
+# Quantize an original float input
 q_input = model.quantize_input(X_test[[0]])
 
 # Encrypt the input
@@ -68,11 +69,11 @@ q_y_enc = model.fhe_circuit.run(q_input_enc)
 # Decrypt the result (integer)
 q_y = model.fhe_circuit.decrypt(q_y_enc)
 
-# De-quantize the result
+# De-quantize and post-process the result
 y0 = model.post_processing(model.dequantize_output(q_y))
 
-print("Probability with `predict_proba`: ", y0)
-print("Probability with encrypt/run/decrypt calls: ", y_proba_fhe)
+print("Probability with `predict_proba`: ", y_proba_fhe)
+print("Probability with encrypt/run/decrypt calls: ", y0)
 ```
 
 This example shows the typical flow of a Concrete ML model:

docs/getting-started/showcase.md

@@ -40,6 +40,19 @@ Simpler tutorials that discuss only model usage and compilation are also availab
          <td><a href="../../use_case_examples/titanic">use_case_examples/titanic</a></td>
          <!--- end -->
       </tr>
+      <tr>
+         <td><strong>Federated Learning and Private Inference</strong></td>
+         <td>
+            <p></p>
+            <p>Use federated learning to train a Logistic Regression while preserving training data confidentiality. 
+            Import the model into Concrete ML and perform encrypted prediction</p>
+         </td>
+         <td></td>
+         <!--- start -->
+         <td><a href="../.gitbook/assets/demo_mnist.png">mnist.png</a></td>
+         <td><a href="../../use_case_examples/federated_learning">use_case_examples/federated_learning</a></td>
+         <!--- end -->
+      </tr>
       <tr>
          <td><strong>Neural Network Fine-tuning</strong> </td>
          <td>

script/doc_utils/fix_gitbook_table.py

@@ -70,7 +70,7 @@ def process_file(file_str: str):
     with open(file_path_output, "w", encoding="utf-8") as fout:
         print(processed_content, file=fout)
 
-    assert how_many == 8
+    assert how_many == 9
 
     return True