Added code for NN

1-first-project/tdt/README.md

@@ -23,7 +23,7 @@ The given data at [iui-datalrelease1-sose2021-readonly/\*](/opt/iui-datarelease1
 There were 100 participants.
 
 The folder-structure is as follows:\
-`/opt/iui-datarelease1-sose2021/{P}/{N}{A}.csv`
+`/opt/iui-datarelease1-sose2021/{P}/split_letters_csv/{N}{A}.csv`
 
 | Variable | Description                           | 
 | -------- | ------------------------------------- |
@@ -72,8 +72,36 @@ todo
 
 ### Time
 
-- Time is negative for some data, gotta find out why
+## Neural Network
+This segment are notes dedicated to the neural network itself.
 
-## Model selection
+### Ideas
 
-todo
+- Don't use batch normalization but normalize by maxval of sensor
+
+### Results
+
+```python
+model = Sequential()
+
+model.add(Flatten(input_shape=X_filter[0].shape))
+
+model.add(BatchNormalization())
+
+model.add(Dense(1560, activation='relu'))
+
+model.add(Dense(750, activation='relu'))
+
+model.add(Dense(300, activation='relu'))
+
+model.add(Dense(156, activation='relu'))
+
+model.add(Dense(26, activation='softmax'))
+```
+
+```
+Evaluate on test data
+82/82 [==============================] - 0s 3ms/step - loss: 1.4249 - acc: 0.7299
+```
+
+todo: more testing