Update

3 files changed, 54 insertions, 29 deletions

diff --git a/example.py b/gradient_descent.py
index 66df486..3f7f124 100755
--- a/example.py
+++ b/gradient_descent.py
@@ -3,35 +3,6 @@
 from src.scalar import Scalar
 from src.graph import Graph
 
-# Manual Backpropagation
-
-# a = Scalar(2, label='a')
-# b = Scalar(-3, label='b')
-# c = Scalar(10, label='c')
-# f = Scalar(-2, label='f')
-#
-# d = a * b; d.label = 'd'
-# e = d + c; e.label = 'e'
-# L = e * f; L.label = 'L'
-#
-# print(f'L before gradient descent: {L.data}')
-#
-# L.backward()
-#
-# g = Graph(L)
-#
-# for x in [a, b, c, f]:
-#     x.data += 0.01 * x.grad
-#
-# d = a * b
-# e = d + c
-# L = e * f
-#
-# print(f'L after gradient descent: {L.data}')
-# g.show()
-
-# Neuron
-
 x1 = Scalar(2, label='x1')
 x2 = Scalar(0, label='x2')
 
diff --git a/neural_network.py b/neural_network.py
new file mode 100755
index 0000000..62f3f9c
--- /dev/null
+++ b/neural_network.py
@@ -0,0 +1,17 @@
+#!/usr/bin/env python
+
+from src.nn import MLP
+
+X = [
+    [ 0.0, 0.0, 0.0 ],
+    [ 1.0, 1.0, 1.0 ],
+    [ 2.0, 2.0, 2.0 ],
+    [ 3.0, 3.0, 3.0 ]
+]
+
+y = [ 1.0, 2.0, 3.0, 4.0 ] # X + 1
+
+n = MLP(3, [ 4, 4, 1 ])
+
+pred = [ n(x) for x in X ]
+print(pred)
diff --git a/src/nn.py b/src/nn.py
new file mode 100644
index 0000000..e5d20d4
--- /dev/null
+++ b/src/nn.py
@@ -0,0 +1,37 @@
+from .scalar import Scalar
+import random
+
+class Neuron:
+    def __init__(self, n_X):
+        self.n_X = n_X
+        self.w = [ Scalar(random.uniform(-1, 1)) for _ in range(n_X) ]
+        self.b = Scalar(random.uniform(-1, 1))
+
+    def __call__(self, X):
+        result = 0
+
+        for wi, Xi in zip(self.w, X):
+            result += wi * Xi
+
+        result += self.b
+
+        return result.tanh()
+
+class Layer:
+    def __init__(self, n_X, n_y):
+        self.neurons = [ Neuron(n_X) for _ in range(n_y) ]
+
+    def __call__(self, X):
+        result = [ n(X) for n in self.neurons ]
+        return result[0] if len(result) == 1 else result
+
+class MLP:
+    def __init__(self, n_X, layers):
+        sz = [ n_X ] + layers
+        self.layers = [ Layer(sz[i], sz[i + 1]) for i in range(len(layers)) ]
+
+    def __call__(self, X):
+        for layer in self.layers:
+            X = layer(X)
+        
+        return X