Added Basic Neural Network

This is a basic implementation of a neural network using pytorch. The network accepts an input of 784 and generate a final output of 10. eg(classifying 28x28 -> 784 images of 10 digits)

ML Cookbook/BasicNeuralNet.py

@@ -0,0 +1,23 @@
+from torch import nn
+
+class BasicNeuralNet(nn.Module):
+    def __init__(self):
+        super().__init__()
+        
+        # Inputs to hidden layer linear transformation
+        self.hidden = nn.Linear(784, 256)
+        # Output layer, 10 units 
+        self.output = nn.Linear(256, 10)
+        
+        # Define sigmoid activation and softmax output 
+        self.sigmoid = nn.Sigmoid()
+        self.softmax = nn.Softmax(dim=1)
+        
+    def forward(self, x):
+        # Pass the input tensor through each of the operations
+        x = self.hidden(x)
+        x = self.sigmoid(x)
+        x = self.output(x)
+        x = self.softmax(x)
+        
+        return x