diff --git a/1_DL_base/NeuralNetwork.py b/1_DL_base/NeuralNetwork.py
new file mode 100644
index 0000000000000000000000000000000000000000..7e0cc90376fee6c89b65c34ca02581f4f80028ae
--- /dev/null
+++ b/1_DL_base/NeuralNetwork.py
@@ -0,0 +1,51 @@
+import numpy as np
+import copy
+
+
+class NeuralNetwork:
+    input_tensor = None
+    label_tensor = None
+
+    def __init__(self, optimizer):
+        self.optimizer = optimizer
+        self.layers = []
+        self.loss = []
+        self.data_layer = None
+        self.loss_layer = None
+
+    def forward(self):
+
+        input_tensor, label_tensor = self.data_layer.next()
+        self.input_tensor = np.copy(input_tensor)
+        self.label_tensor = np.copy(label_tensor)
+
+        for i in self.layers:
+            input_tensor = i.forward(input_tensor)
+
+        return self.loss_layer.forward(input_tensor, label_tensor)
+
+    def backward(self):
+        error_tensor = self.loss_layer.backward(self.label_tensor)
+
+        for i in reversed(self.layers):
+            error_tensor = i.backward(error_tensor)
+
+    def append_layer(self, layer):
+        if layer.trainable:
+            layer.set_optimizer(copy.deepcopy(self.optimizer))
+
+        self.layers.append(layer)
+
+    def train(self, iterations):
+
+        for i in range(iterations):
+            intermed_loss = self.forward()
+            self.loss.append(intermed_loss)
+            self.backward()
+            # removed weights update in
+
+    def test(self, input_tensor):
+        for i in self.layers:
+            input_tensor = i.forward(input_tensor)
+
+        return input_tensor