diff --git a/README.md b/README.md
index 97840fc92a267ff9896a9de50d94af3b43e808f9..f8c9464920a9893e7efd89e366925462c959f387 100644
--- a/README.md
+++ b/README.md
@@ -1,30 +1,68 @@
 # Progressive Layer-based Compression for Convolutional Spiking Neural Network 
-Here you find the code for the paper `Progressive Layer-based Compression for Convolutional Spiking Neural Network` ([link](https://hal.archives-ouvertes.fr/hal-03826823))
-## Requirement
+Here you find the code for the paper `Progressive Layer-based Compression for Convolutional Spiking Neural Network` <!--([link](https://hal.archives-ouvertes.fr/hal-03826823))-->
+
+## CSNN
+
+### Requirement for the simulator
 
 * C++ compiler (version >= 14)
 * Cmake (version >= 3.1)
 * Qt4 (version >= 4.4.3)
 
-## CSNN Installation and Build
+### Building the binaries
+
 Run the following commands inside CSNN folder:
 
     mkdir build
     cd build
-    cmake ../ -G"Unix Makefiles" -DCMAKE_BUILD_TYPE=Release
+    cmake ../ -G"Unix Makefiles" -DCMAKE_BUILD_TYPE=Release -DCMAKE_CXX_FLAGS='-std=c++11'
     make
 Don't forget to build again if you change the source code.
 
-## How to use CSNN
-Run MNIST Example:
+### How to use CSNN
+Once the `make` command is finished, you should see binary files which represent each simulation
+
+Run a simulation:
+
+    ./[sim_name] x y
+    
+    args:
+        x = enable PP (pruning) [0 or 1]
+        y = enable DSWR (reinforcement) [0 or 1]
+
+To run MNIST simulation without compression and reinforcement:
 
     ./Mnist 0 0
 
+In `apps` folder you find the source code for each simulation where you can change the architecture, the network parameters, or activate the layerwise compression.
+
+## Going from CSNN to SpiNNaker
+To transfer the learned weights from CSNN to SpiNNaker, we use the following command:
+
+    ./Weight_extractor [binary file geenrated from a simulation] [name_layer]
+
+For example:
+
+    ./Weight_extractor mnist_params conv1
+> `weights_conv1` is generated
+
+This will generate another binary file (named weights_[name_layer]) which contains only the weights of the selected layer .
+
 ## How to use SpiNNaker scripts
-To run the SpiNNaker scripts, please check the following link:
+To setup the SpiNNaker board, please check the following link:
 
 http://spinnakermanchester.github.io/
 
+### Weights adaptation for PyNN and SpiNNaker
+
+in SpiNNaker folder:
+
+run the `ConvertTheWeights.ipynb` notebook to adapt the extracted weights from CSNN to a text format readable by PyNN.
+
+### Using the extracted weights with SpiNNaker
+
+Run the `SpiNNakerRun.ipynb` notebook to deploy the weights on the board and run simulation.
+
 ## Folder structure
 
 ```
@@ -32,8 +70,9 @@ CSNN            # The C++ Simulator of Convolutional Spiking Neural Network
 SpiNNaker       # The scripts in python which are used for running on the SpiNNaker board
 ```
 
-# Citation
+<!--# Citation
 
 If you found our work useful, please don't forget to cite:
 
 > Hammouda Elbez, Mazdak Fatahi. Progressive Layer-based Compression for Convolutional Spiking Neural Network. 2022. ⟨hal-03826823⟩
+-->
\ No newline at end of file
diff --git a/SpiNNaker/SpiNNakerRun.ipynb b/SpiNNaker/SpiNNakerRun.ipynb
index 6aed942ee9d00ffd4fa8b44a8181a8a4f8b96fbe..b40d6a6aaa2e0fd7b3d868960cc4d8c8a1947ad8 100644
--- a/SpiNNaker/SpiNNakerRun.ipynb
+++ b/SpiNNaker/SpiNNakerRun.ipynb
@@ -682,7 +682,7 @@
     "            if not os.path.exists(f'{path}/{str(now)}/{param_name}_{str(param_val)}'):   #   1\n",
     "                os.mkdir(f'{path}/{str(now)}/{param_name}_{str(param_val)}')\n",
     "\n",
-    "            tests_name=['0_0_25_0.7_Zero_Removed_False_not_transposed', '1_1_25_0.7_Zero_Removed_False_not_transposed']\n",
+    "            tests_name=['baseline', 'compressed']\n",
     "\n",
     "            if not os.path.exists(f'{path}/{str(now)}/{param_name}_{str(param_val)}/{str(time)}'):    #   2\n",
     "                os.mkdir(f'{path}/{str(now)}/{param_name}_{str(param_val)}/{str(time)}')\n",
@@ -714,13 +714,6 @@
     "\n",
     "                mySpiNNaker.sim.end()\n"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {