Added the files.

.idea/inspectionProfiles/Project_Default.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <profile version="1.0">
+    <option name="myName" value="Project Default" />
+    <inspection_tool class="PyUnnecessaryCastInspection" enabled="true" level="WEAK WARNING" enabled_by_default="true" />
+  </profile>
+</component>

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/misc.xml

@@ -0,0 +1,7 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="Black">
+    <option name="sdkName" value="Python 3.13" />
+  </component>
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.13" project-jdk-type="Python SDK" />
+</project>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="$PROJECT_DIR$" vcs="Git" />
+  </component>
+</project>

.idea/workspace.xml

@@ -4,35 +4,47 @@
     <option name="autoReloadType" value="SELECTIVE" />
   </component>
   <component name="ChangeListManager">
-    <list default="true" id="53d2c8fc-09f6-4596-950a-66eac2662d99" name="Changes" comment="" />
+    <list default="true" id="53d2c8fc-09f6-4596-950a-66eac2662d99" name="Changes" comment="">
+      <change afterPath="$PROJECT_DIR$/experiment-8.py" afterDir="false" />
+      <change beforePath="$PROJECT_DIR$/.idea/workspace.xml" beforeDir="false" afterPath="$PROJECT_DIR$/.idea/workspace.xml" afterDir="false" />
+      <change beforePath="$PROJECT_DIR$/multilayer-perceptron.py" beforeDir="false" afterPath="$PROJECT_DIR$/multilayer-perceptron.py" afterDir="false" />
+      <change beforePath="$PROJECT_DIR$/results/MLP-output.png" beforeDir="false" afterPath="$PROJECT_DIR$/results/MLP-output.png" afterDir="false" />
+    </list>
     <option name="SHOW_DIALOG" value="false" />
     <option name="HIGHLIGHT_CONFLICTS" value="true" />
     <option name="HIGHLIGHT_NON_ACTIVE_CHANGELIST" value="false" />
     <option name="LAST_RESOLUTION" value="IGNORE" />
   </component>
+  <component name="FileTemplateManagerImpl">
+    <option name="RECENT_TEMPLATES">
+      <list>
+        <option value="Python Script" />
+      </list>
+    </option>
+  </component>
   <component name="Git.Settings">
     <option name="RECENT_GIT_ROOT_PATH" value="$PROJECT_DIR$" />
   </component>
-  <component name="ProjectColorInfo"><![CDATA[{
-  "associatedIndex": 7
-}]]></component>
+  <component name="ProjectColorInfo">{
+  &quot;associatedIndex&quot;: 7
+}</component>
   <component name="ProjectId" id="35RSHS8xmtnia7nWZhfabhC6peP" />
   <component name="ProjectViewState">
     <option name="hideEmptyMiddlePackages" value="true" />
     <option name="showLibraryContents" value="true" />
   </component>
-  <component name="PropertiesComponent"><![CDATA[{
-  "keyToString": {
-    "ModuleVcsDetector.initialDetectionPerformed": "true",
-    "Python.Unnamed.executor": "Run",
-    "Python.multilayer-perceptron.executor": "Run",
-    "RunOnceActivity.ShowReadmeOnStart": "true",
-    "RunOnceActivity.TerminalTabsStorage.copyFrom.TerminalArrangementManager.252": "true",
-    "RunOnceActivity.git.unshallow": "true",
-    "git-widget-placeholder": "master",
-    "last_opened_file_path": "/home/arctichawk1/Desktop/Projects/Private/Classification-of-Image-Data-with-MLP-and-CNN"
+  <component name="PropertiesComponent">{
+  &quot;keyToString&quot;: {
+    &quot;ModuleVcsDetector.initialDetectionPerformed&quot;: &quot;true&quot;,
+    &quot;Python.Unnamed.executor&quot;: &quot;Run&quot;,
+    &quot;Python.multilayer-perceptron.executor&quot;: &quot;Run&quot;,
+    &quot;RunOnceActivity.ShowReadmeOnStart&quot;: &quot;true&quot;,
+    &quot;RunOnceActivity.TerminalTabsStorage.copyFrom.TerminalArrangementManager.252&quot;: &quot;true&quot;,
+    &quot;RunOnceActivity.git.unshallow&quot;: &quot;true&quot;,
+    &quot;git-widget-placeholder&quot;: &quot;master&quot;,
+    &quot;last_opened_file_path&quot;: &quot;/home/arctichawk1/Desktop/Projects/Private/Classification-of-Image-Data-with-MLP-and-CNN&quot;
   }
-}]]></component>
+}</component>
   <component name="SharedIndexes">
     <attachedChunks>
       <set>

README.md

@@ -1,4 +1,4 @@
-# Classification-of-Image-Data-with-MLP-and-CNN
+# Classification of Image Data with MLP and CNN
 
 This project implements both a multilayer perceptron and a convolutional neural network in Python; 
 the perceptron comprises an input layer, one or more hidden layers, and an output layer, 

multilayer-perceptron.py

@@ -1,8 +1,12 @@
 import numpy as np
+import matplotlib.pyplot as plt
 from torchvision import datasets
+import os
+
 
 class MLP:
     def __init__(self, input_size, hidden_size1, hidden_size2, output_size, weight_scale):
+        # initializes weights and biases for each layer
         self.W1 = np.random.randn(input_size, hidden_size1) * weight_scale
         self.b1 = np.zeros((1, hidden_size1))
         self.W2 = np.random.randn(hidden_size1, hidden_size2) * weight_scale
@@ -11,31 +15,35 @@ class MLP:
         self.b3 = np.zeros((1, output_size))
 
     def forward(self, x):
-        self.x = x       
-        self.z1 = x @ self.W1 + self.b1
-        self.a1 = self.relu(self.z1)   
-        self.z2 = self.a1 @ self.W2 + self.b2  
-        self.a2 = self.relu(self.z2)          
-        self.z3 = self.a2 @ self.W3 + self.b3  
-        self.a3 = self.softmax(self.z3)    
-        return self.a3
+        # forwards pass through the network
+        self.x = x  # input for backpropagation
+        self.z1 = x @ self.W1 + self.b1  # linear transformation for layer 1
+        self.a1 = self.relu(self.z1)  # ReLU activation
+        self.z2 = self.a1 @ self.W2 + self.b2  # linear transformation for layer 2
+        self.a2 = self.relu(self.z2)  # ReLU activation
+        self.z3 = self.a2 @ self.W3 + self.b3  # linear transformation for layer 3
+        self.a3 = self.softmax(self.z3)  # applies softmax to get class probabilities
+        return self.a3  # output of the network
 
     def backward(self, y, lr):
+        # backwards pass for weight updates using gradient descent
         m = y.shape[0]
-        y_one_hot = self.one_hot_encode(y, self.W3.shape[1])
+        y_one_hot = self.one_hot_encode(y, self.W3.shape[1]) # converts labels to one-hot encoding
 
-        dz3 = self.a3 - y_one_hot      
-        dw3 = (self.a2.T @ dz3) / m                
+        # computes gradients for each layer
+        dz3 = self.a3 - y_one_hot  # gradient for output layer
+        dw3 = (self.a2.T @ dz3) / m
         db3 = np.sum(dz3, axis=0, keepdims=True) / m
 
-        dz2 = (dz3 @ self.W3.T) * self.relu_deriv(self.z2)
-        dw2 = (self.a1.T @ dz2) / m                
+        dz2 = (dz3 @ self.W3.T) * self.relu_deriv(self.z2)  # gradient for layer 2
+        dw2 = (self.a1.T @ dz2) / m
         db2 = np.sum(dz2, axis=0, keepdims=True) / m
 
-        dz1 = (dz2 @ self.W2.T) * self.relu_deriv(self.z1)
-        dw1 = (self.x.T @ dz1) / m                 
+        dz1 = (dz2 @ self.W2.T) * self.relu_deriv(self.z1)  # gradient for layer 1
+        dw1 = (self.x.T @ dz1) / m
         db1 = np.sum(dz1, axis=0, keepdims=True) / m
 
+        # updates weights and biases using gradient descent
         self.W3 -= lr * dw3
         self.b3 -= lr * db3
         self.W2 -= lr * dw2
@@ -45,32 +53,41 @@ class MLP:
 
     @staticmethod
     def relu(x):
+        # ReLU activation
         return np.maximum(0, x)
 
     @staticmethod
     def relu_deriv(x):
+        # derivation of ReLU activation for backpropagation
         return (x > 0).astype(float)
 
     @staticmethod
     def softmax(x):
-        e_x = np.exp(x - np.max(x, axis=1, keepdims=True))
-        return e_x / np.sum(e_x, axis=1, keepdims=True)
+        # softmax function normalizes outputs to probabilities
+        e_x = np.exp(x - np.max(x, axis=1, keepdims=True))  # exponentiates inputs
+        return e_x / np.sum(e_x, axis=1, keepdims=True) # normalizes to get probabilities
 
     @staticmethod
     def one_hot_encode(y, num_classes):
+        # converts labels to one-hot encoded format
         return np.eye(num_classes)[y]
 
     @staticmethod
     def cross_entropy_loss(y, y_hat):
+        # computes cross-entropy loss between true labels and predicted probabilities
+        m = y.shape[0]
         m = y.shape[0]
         eps = 1e-12
         y_hat_clipped = np.clip(y_hat, eps, 1. - eps)
         log_probs = -np.log(y_hat_clipped[np.arange(m), y])
         return np.mean(log_probs)
 
-    def train_model(self, x_train, y_train, x_val, y_val, lr, epochs, batch_size):
+    def fit(self, x_train, y_train, x_val, y_val, lr, epochs, batch_size):
+        train_losses = []
+        val_accuracies = []
+
         for epoch in range(1, epochs + 1):
-            perm = np.random.permutation(x_train.shape[0])
+            perm = np.random.permutation(x_train.shape[0]) # Shuffle the training data
             x_train_shuffled, y_train_shuffled = x_train[perm], y_train[perm]
 
             epoch_loss = 0.0
@@ -78,56 +95,86 @@ class MLP:
 
             for i in range(num_batches):
                 start = i * batch_size
-                end   = start + batch_size
-                x_batch = x_train_shuffled[start:end]
-                y_batch = y_train_shuffled[start:end]
+                end = start + batch_size
+                x_batch = x_train_shuffled[start:end] # batch of inputs
+                y_batch = y_train_shuffled[start:end] # batch of labels
 
+                # Forward pass, backward pass, and weight update
                 self.forward(x_batch)
                 self.backward(y_batch, lr)
 
-                epoch_loss += self.cross_entropy_loss(y_batch, self.a3)
+                epoch_loss += self.cross_entropy_loss(y_batch, self.a3) # updating the epoch loss
 
-            epoch_loss /= num_batches
+            epoch_loss /= num_batches # average loss is defined
+            train_losses.append(epoch_loss)
 
             val_pred = self.predict(x_val)
-            val_acc  = np.mean(val_pred == y_val)
+            val_acc = np.mean(val_pred == y_val)
+            val_accuracies.append(val_acc) \
 
             print(f"Epoch {epoch:02d} | Training Loss: {epoch_loss:.4f} | Value Accuracy: {val_acc:.4f}")
 
-        return val_acc
+        self.plot_graph(train_losses, val_accuracies)
+        return val_accuracies[-1]
 
-    def predict(self, x):
-        probs = self.forward(x)
-        return np.argmax(probs, axis=1)
+    def plot_graph(self, train_losses, val_accuracies):
+        if not os.path.exists('results'):
+            os.makedirs('results')
 
+        fig, ax1 = plt.subplots()
 
+        ax1.set_xlabel('Epochs')
+        ax1.set_ylabel('Training Loss', color='tab:blue')
+        ax1.plot(range(1, len(train_losses) + 1), train_losses, color='tab:blue', label='Training Loss')
+        ax1.tick_params(axis='y', labelcolor='tab:blue')
+
+        ax2 = ax1.twinx()
+        ax2.set_ylabel('Validation Accuracy', color='tab:orange')
+        ax2.plot(range(1, len(val_accuracies) + 1), val_accuracies, color='tab:orange', label='Validation Accuracy')
+        ax2.tick_params(axis='y', labelcolor='tab:orange')
+
+        plt.title('Training Loss and Validation Accuracy over Epochs')
+
+        result_path = 'results/MLP-output.png'
+        fig.savefig(result_path)
+        print(f"Graph saved to: {result_path}")
+
+    def predict(self, x): # predicts class labels for the input data
+        probs = self.forward(x)  # forwards pass to get probabilities
+        return np.argmax(probs, axis=1)  # returns the class with highest probability
+
+# acquiring the FashionMNIST dataset
 train_set = datasets.FashionMNIST(root='.', train=True, download=True)
-test_set  = datasets.FashionMNIST(root='.', train=False, download=True)
+test_set = datasets.FashionMNIST(root='.', train=False, download=True)
 
+# preprocessing the data by flattening images and normalizing them.
 x_train = train_set.data.numpy().reshape(-1, 28 * 28).astype(np.float32) / 255.0
 y_train = train_set.targets.numpy()
 
-x_test  = test_set.data.numpy().reshape(-1, 28 * 28).astype(np.float32) / 255.0
-y_test  = test_set.targets.numpy()
+x_test = test_set.data.numpy().reshape(-1, 28 * 28).astype(np.float32) / 255.0
+y_test = test_set.targets.numpy()
 
+# MLP Initialization
 mlp = MLP(
-    input_size  = 28 * 28,
-    hidden_size1= 128,
-    hidden_size2= 64,
-    output_size = 10,
-    weight_scale= 1e-2
+    input_size=28 * 28,
+    hidden_size1=128,
+    hidden_size2=64,
+    output_size=10,
+    weight_scale=1e-2
 )
 
-mlp.train_model(
-    x_train  = x_train,
-    y_train  = y_train,
-    x_val    = x_test,
-    y_val    = y_test,
-    lr       = 1e-2,
-    epochs   = 10,
+# trains the model
+mlp.fit(
+    x_train=x_train,
+    y_train=y_train,
+    x_val=x_test,
+    y_val=y_test,
+    lr=1e-2,
+    epochs=10,
     batch_size=128
 )
 
+# tests the model
 test_pred = mlp.predict(x_test)
-test_acc  = np.mean(test_pred == y_test)
-print(f"\nFinal test accuracy: {test_acc:.4f}")
+test_acc = np.mean(test_pred == y_test)
+print(f"\nFinal test accuracy: {test_acc:.4f}")