update

examples/tutorials/self-paced-training/part-1_federated_learning_introduction/chapter-1_running_federated_learning_applications/01.8_recap/recap.ipynb

@@ -5,45 +5,36 @@
    "id": "7b152728-3366-4432-adb1-29aa3051dc22",
    "metadata": {},
    "source": [
-    "# Summary of Chapter 1\n",
+    "# Chapter 1 Recap\n",
     "\n",
-    "We cover a lot of materials in Chapter 1. We guide you through the process of running federated learning applications. Here is an overview of the key contents:\n",
     "\n",
-    "1. **Running Federated Learning Job**\n",
-    "    - **Installation and Data Preparation**: Instructions for setting up the environment and preparing the data.\n",
-    "        - [setup.ipynb](../01.1_running_federated_learning_job/setup.ipynb)\n",
-    "    - **Training Classifier with PyTorch**: Steps to train a classifier using PyTorch in a federated learning setup.\n",
-    "        - [runing_pytorch_fl_job.ipynb](../01.1_running_federated_learning_job/runing_pytorch_fl_job.ipynb)\n",
+    "Throughout this chapter, we've learned several crucial concepts and practical skills in federated learning. Here are the essential takeaways:\n",
     "\n",
-    "2. **From Stand-Alone Deep Learning to Federated Learning**\n",
-    "    - **Conversion to Federated Learning**: Guide on converting deep learning models with PyTorch to federated learning.\n",
-    "        - [convert_dl_to_fl.ipynb](../01.2_convert_deep_learning_to_federated_learning/convert_dl_to_fl.ipynb)\n",
+    "1. **Federated Learning Fundamentals**\n",
+    "   - FL enables collaborative model training while keeping data at source\n",
+    "   - Basic FL workflow: client training → model aggregation → model broadcast → repeat\n",
+    "   - NVIDIA FLARE provides a robust framework for implementing FL systems\n",
     "\n",
-    "3. **Customizing the Federated Algorithms**\n",
-    "    - **Server Logic Customization**: Techniques to customize server logic for specific federated learning needs, we built an our own fed avg algorithms with best model seleciton, model saving and loading, as well as early stopping. \n",
-    "        - [customize_server_logics.ipynb](../01.3_customize_server_logics/customize_server_logics.ipynb)\n",
+    "2. **Converting Traditional to Federated Learning**\n",
+    "   - Most PyTorch models can be adapted for federated learning\n",
+    "   - Key modifications needed:\n",
+    "     - Separating training logic from model loading. The model can be received and send back to server, while keep the trainig logics about the same.\n",
+    "    \n",
     "\n",
-    "4. **Adjusting Training Parameters**\n",
-    "    - **Client Logic Customization**: Methods to customize client logic to optimize training parameters. Here we show how to customize the training for each site. \n",
-    "        - [customize_client_training.ipynb](../01.4_customize_client_training/customize_client_training.ipynb)\n",
+    "3. **Customization Capabilities**\n",
+    "   - Server-side customization:\n",
+    "     - Implementing custom aggregation strategies\n",
+    "     - Model selection and persistence\n",
+    "     - Early stopping mechanisms\n",
+    "   - Client-side customization:\n",
+    "     - Local training optimization\n",
+    "     - Site-specific parameters\n",
+    "     - Custom data handling\n",
     "\n",
-    "5. **Tracking Training Metrics**\n",
-    "    - **Experiment Tracking**: Tools and methods to track experiments and monitor training metrics effectively.\n",
-    "        - [experiment_tracking.ipynb](../01.5_experiment_tracking/experiment_tracking.ipynb)\n",
     "\n",
-    "6. **Job Structure and Configurations**\n",
-    "    - **Understanding Job Structure and Configuration**: Detailed explanation of the job structure and configurations necessary for running federated learning jobs.\n",
-    "        - [01.1.6.1_understanding_fl_job.ipynb](../01.6_job_structure_and_configuration/01.1.6.1_understanding_fl_job.ipynb)\n",
+    "These fundamentals prepare you for more advanced FL concepts and implementations in the following chapters.\n",
     "\n",
-    "7. **Recap of Covered Topics**\n",
-    "    - **Summary and Recap**: A recap of the topics covered in the previous sections.\n",
-    "        - [recap.ipynb](../01.7_recap/recap.ipynb)\n",
-    "\n",
-    "Each section is designed to provide comprehensive guidance and practical examples to help you implement and customize federated learning in your applications. For detailed instructions and examples, refer to the respective notebooks linked in each section.\n",
-    "\n",
-    "\n",
-    "Now let's move on to the [Chapter 2](../../chapter-2_develop_federated_learning_applications/02.0_introduction/introduction.ipynb\n",
-    ")"
+    "Now let's move on to the [Chapter 2](../../chapter-2_develop_federated_learning_applications/02.0_introduction/introduction.ipynb)"
    ]
   },
   {