diff --git a/.idea/workspace.xml b/.idea/workspace.xml
index 6ba2fea..d20b1c0 100644
--- a/.idea/workspace.xml
+++ b/.idea/workspace.xml
@@ -5,26 +5,8 @@
   </component>
   <component name="ChangeListManager">
     <list default="true" id="53d2c8fc-09f6-4596-950a-66eac2662d99" name="Changes" comment="">
-      <change afterPath="$PROJECT_DIR$/experiment-2.py" afterDir="false" />
-      <change afterPath="$PROJECT_DIR$/results/experiment-2-leaky-relu.png" afterDir="false" />
-      <change afterPath="$PROJECT_DIR$/results/experiment-2-tanh.png" afterDir="false" />
-      <change afterPath="$PROJECT_DIR$/results/experiment-3-l1.png" afterDir="false" />
-      <change afterPath="$PROJECT_DIR$/results/experiment-3-l2.png" afterDir="false" />
-      <change afterPath="$PROJECT_DIR$/results/experiment-4.png" afterDir="false" />
-      <change afterPath="$PROJECT_DIR$/results/experiment-5.png" afterDir="false" />
       <change beforePath="$PROJECT_DIR$/.idea/workspace.xml" beforeDir="false" afterPath="$PROJECT_DIR$/.idea/workspace.xml" afterDir="false" />
-      <change beforePath="$PROJECT_DIR$/experiment-1.py" beforeDir="false" afterPath="$PROJECT_DIR$/experiment-1.py" afterDir="false" />
-      <change beforePath="$PROJECT_DIR$/experiment-2-leaky-relu.py" beforeDir="false" afterPath="$PROJECT_DIR$/convolutional-neural-network-experiment-6.py" afterDir="false" />
-      <change beforePath="$PROJECT_DIR$/experiment-2-tanh.py" beforeDir="false" />
-      <change beforePath="$PROJECT_DIR$/experiment-3-l1.py" beforeDir="false" afterPath="$PROJECT_DIR$/experiment-3-l1.py" afterDir="false" />
-      <change beforePath="$PROJECT_DIR$/experiment-3-l2.py" beforeDir="false" afterPath="$PROJECT_DIR$/experiment-3-l2.py" afterDir="false" />
-      <change beforePath="$PROJECT_DIR$/experiment-4.py" beforeDir="false" afterPath="$PROJECT_DIR$/experiment-4.py" afterDir="false" />
-      <change beforePath="$PROJECT_DIR$/experiment-5.py" beforeDir="false" afterPath="$PROJECT_DIR$/experiment-5.py" afterDir="false" />
-      <change beforePath="$PROJECT_DIR$/experiment-6.py" beforeDir="false" />
-      <change beforePath="$PROJECT_DIR$/results/MLP-output.png" beforeDir="false" afterPath="$PROJECT_DIR$/results/MLP-output.png" afterDir="false" />
-      <change beforePath="$PROJECT_DIR$/results/experiment-1-1.png" beforeDir="false" afterPath="$PROJECT_DIR$/results/experiment-1-1.png" afterDir="false" />
-      <change beforePath="$PROJECT_DIR$/results/experiment-1-2.png" beforeDir="false" afterPath="$PROJECT_DIR$/results/experiment-1-2.png" afterDir="false" />
-      <change beforePath="$PROJECT_DIR$/results/experiment-1-3.png" beforeDir="false" afterPath="$PROJECT_DIR$/results/experiment-1-3.png" afterDir="false" />
+      <change beforePath="$PROJECT_DIR$/experiment-6-convolutional-neural-network.py" beforeDir="false" afterPath="$PROJECT_DIR$/experiment-6-convolutional-neural-network.py" afterDir="false" />
     </list>
     <option name="SHOW_DIALOG" value="false" />
     <option name="HIGHLIGHT_CONFLICTS" value="true" />
@@ -61,8 +43,10 @@
     "Python.experiment-2.executor": "Run",
     "Python.experiment-3-l1.executor": "Run",
     "Python.experiment-3-l2.executor": "Run",
+    "Python.experiment-3.executor": "Run",
     "Python.experiment-4.executor": "Run",
     "Python.experiment-5.executor": "Run",
+    "Python.experiment-6-convolutional-neural-network.executor": "Run",
     "Python.multilayer-perceptron.executor": "Run",
     "RunOnceActivity.ShowReadmeOnStart": "true",
     "RunOnceActivity.TerminalTabsStorage.copyFrom.TerminalArrangementManager.252": "true",
diff --git a/experiment-6-convolutional-neural-network.py b/experiment-6-convolutional-neural-network.py
index e69de29..06c624c 100644
--- a/experiment-6-convolutional-neural-network.py
+++ b/experiment-6-convolutional-neural-network.py
@@ -0,0 +1,134 @@
+import torch
+import torch.nn as nn
+import torch.optim as optim
+from torchvision import datasets, transforms
+from torch.utils.data import DataLoader
+import matplotlib.pyplot as plt
+import os
+
+class CNN:
+    def __init__(self, device=None):
+        self.device = device or torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+        self.model = self._build_model().to(self.device)
+        self.criterion = nn.CrossEntropyLoss() # cross entropy is used for loss from torch
+        self.optimizer = optim.Adam(self.model.parameters(), lr=0.001) # adam is used for optimization from torch
+
+    def _build_model(self):
+        class Net(nn.Module):
+            def __init__(self):
+                super(Net, self).__init__()
+                self.conv1 = nn.Conv2d(1, 32, 3, padding=1) # convolutional layer 1
+                self.conv2 = nn.Conv2d(32, 64, 3, padding=1) # convolutional layer 2
+                self.fc1 = nn.Linear(64 * 7 * 7, 256) # hidden layer with 256 units
+                self.fc2 = nn.Linear(256, 10) # output layer
+                self.relu = nn.ReLU() # ReLU activation from torch
+                self.pool = nn.MaxPool2d(2, 2) # pooling from torch
+
+            def forward(self, x):
+                # forwards pass through the network
+                x = self.relu(self.conv1(x))
+                x = self.pool(x)
+                x = self.relu(self.conv2(x))
+                x = self.pool(x)
+                x = x.view(x.size(0), -1)
+                x = self.relu(self.fc1(x))
+                x = self.fc2(x)
+                return x
+
+        return Net()
+
+    def fit(self, train_loader, val_loader, epochs=10):
+        self.train_losses = []
+        self.val_accuracies = []
+
+        for epoch in range(1, epochs + 1):
+            self.model.train()
+            epoch_loss = 0.0
+
+            for images, labels in train_loader:
+                images, labels = images.to(self.device), labels.to(self.device)
+                self.optimizer.zero_grad()
+                outputs = self.model(images)
+                loss = self.criterion(outputs, labels)
+                loss.backward()
+                self.optimizer.step()
+                epoch_loss += loss.item() # updating the epoch loss
+
+            self.train_losses.append(epoch_loss)
+
+            val_acc = self.evaluate(val_loader)
+            self.val_accuracies.append(val_acc)
+            print(f"Epoch {epoch:02d} | Training Loss: {epoch_loss:.4f} | Validation Accuracy: {val_acc:.4f}")
+
+        self.plot_graph(self.train_losses, self.val_accuracies)
+        return self.val_accuracies[-1]
+
+    def evaluate(self, loader):
+        # measures the accuracy of your model on a given dataset
+        self.model.eval()
+        correct = 0
+        total = 0
+        with torch.no_grad():
+            for images, labels in loader:
+                images, labels = images.to(self.device), labels.to(self.device)
+                outputs = self.model(images)
+                preds = torch.argmax(outputs, dim=1)
+                correct += (preds == labels).sum().item()
+                total += labels.size(0)
+        return correct / total
+
+    def plot_graph(self, train_losses, val_accuracies):
+        if not os.path.exists('results'):
+            os.makedirs('results') # creates results director
+
+        fig, ax1 = plt.subplots() # initializes the plot
+
+        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') # defines loss subplot
+
+        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') # defines accuracy subplot
+
+        plt.title('CNN Training Loss and Validation Accuracy over Epochs')
+
+        result_path = 'results/experiment-6-convolutional-neural-network.png' # defines the file name
+        fig.savefig(result_path)
+        print(f"Graph saved to: {result_path}")
+
+    def predict(self, loader):
+        # returns the predicted class labels for all samples in the loader, instead of summarizing them as accuracy.
+        self.model.eval()
+        all_preds = []
+        with torch.no_grad():
+            for images, _ in loader:
+                images = images.to(self.device)
+                outputs = self.model(images)
+                preds = torch.argmax(outputs, dim=1)
+                all_preds.append(preds.cpu())
+        return torch.cat(all_preds)
+
+# pre-processing the images
+transform = transforms.Compose([
+    transforms.ToTensor(),
+    transforms.Normalize((0.5,), (0.5,))
+])
+
+# acquiring the FashionMNIST dataset
+train_set = datasets.FashionMNIST(root='.', train=True, download=True, transform=transform)
+test_set = datasets.FashionMNIST(root='.', train=False, download=True, transform=transform)
+
+# splits data using dataloader with 256 batches
+train_loader = DataLoader(train_set, batch_size=256, shuffle=True)
+test_loader = DataLoader(test_set, batch_size=256, shuffle=False)
+
+# CNN initialization and training the model
+cnn = CNN()
+cnn.fit(train_loader, test_loader, epochs=10)
+
+# tests the model
+test_acc = cnn.evaluate(test_loader)
+print(f"\nFinal test accuracy: {test_acc:.4f}")
\ No newline at end of file
diff --git a/experiment-7.py b/experiment-7.py
index e69de29..9edca28 100644
--- a/experiment-7.py
+++ b/experiment-7.py
@@ -0,0 +1,136 @@
+import torch
+import torch.nn as nn
+import torch.optim as optim
+from torchvision import datasets, transforms
+from torch.utils.data import DataLoader
+import matplotlib.pyplot as plt
+import os
+
+class CNN:
+    def __init__(self, device=None):
+        self.device = device or torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+        self.model = self._build_model().to(self.device)
+        self.criterion = nn.CrossEntropyLoss() # cross entropy is used for loss from torch
+        self.optimizer = optim.Adam(self.model.parameters(), lr=0.001) # adam is used for optimization from torch
+
+    def _build_model(self):
+        class Net(nn.Module):
+            def __init__(self):
+                super(Net, self).__init__()
+                self.conv1 = nn.Conv2d(1, 32, 3, padding=1) # convolutional layer 1
+                self.conv2 = nn.Conv2d(32, 64, 3, padding=1) # convolutional layer 2
+                self.fc1 = nn.Linear(64 * 7 * 7, 256) # hidden layer with 256 units
+                self.fc2 = nn.Linear(256, 10) # output layer
+                self.relu = nn.ReLU() # ReLU activation from torch
+                self.pool = nn.MaxPool2d(2, 2) # pooling from torch
+
+            def forward(self, x):
+                # forwards pass through the network
+                x = self.relu(self.conv1(x))
+                x = self.pool(x)
+                x = self.relu(self.conv2(x))
+                x = self.pool(x)
+                x = x.view(x.size(0), -1)
+                x = self.relu(self.fc1(x))
+                x = self.fc2(x)
+                return x
+
+        return Net()
+
+    def fit(self, train_loader, val_loader, epochs=10):
+        self.train_losses = []
+        self.val_accuracies = []
+
+        for epoch in range(1, epochs + 1):
+            self.model.train()
+            epoch_loss = 0.0
+
+            for images, labels in train_loader:
+                images, labels = images.to(self.device), labels.to(self.device)
+                self.optimizer.zero_grad()
+                outputs = self.model(images)
+                loss = self.criterion(outputs, labels)
+                loss.backward()
+                self.optimizer.step()
+                epoch_loss += loss.item() # updating the epoch loss
+
+            self.train_losses.append(epoch_loss)
+
+            val_acc = self.evaluate(val_loader)
+            self.val_accuracies.append(val_acc)
+            print(f"Epoch {epoch:02d} | Training Loss: {epoch_loss:.4f} | Validation Accuracy: {val_acc:.4f}")
+
+        self.plot_graph(self.train_losses, self.val_accuracies)
+        return self.val_accuracies[-1]
+
+    def evaluate(self, loader):
+        # measures the accuracy of your model on a given dataset
+        self.model.eval()
+        correct = 0
+        total = 0
+        with torch.no_grad():
+            for images, labels in loader:
+                images, labels = images.to(self.device), labels.to(self.device)
+                outputs = self.model(images)
+                preds = torch.argmax(outputs, dim=1)
+                correct += (preds == labels).sum().item()
+                total += labels.size(0)
+        return correct / total
+
+    def plot_graph(self, train_losses, val_accuracies):
+        if not os.path.exists('results'):
+            os.makedirs('results') # creates results director
+
+        fig, ax1 = plt.subplots() # initializes the plot
+
+        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') # defines loss subplot
+
+        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') # defines accuracy subplot
+
+        plt.title('CNN Training Loss and Validation Accuracy over Epochs')
+
+        result_path = 'results/experiment-7' # defines the file name
+        fig.savefig(result_path)
+        print(f"Graph saved to: {result_path}")
+
+    def predict(self, loader):
+        # returns the predicted class labels for all samples in the loader, instead of summarizing them as accuracy.
+        self.model.eval()
+        all_preds = []
+        with torch.no_grad():
+            for images, _ in loader:
+                images = images.to(self.device)
+                outputs = self.model(images)
+                preds = torch.argmax(outputs, dim=1)
+                all_preds.append(preds.cpu())
+        return torch.cat(all_preds)
+
+# pre-processing the images and defining the data augmentation transformations
+transform = transforms.Compose([
+    transforms.RandomRotation(20),  # random rotations between -20 and 20 degrees
+    transforms.RandomHorizontalFlip(),  # random horizontal flip
+    transforms.ToTensor(),
+    transforms.Normalize((0.5,), (0.5,))
+])
+
+# acquiring the FashionMNIST dataset
+train_set = datasets.FashionMNIST(root='.', train=True, download=True, transform=transform)
+test_set = datasets.FashionMNIST(root='.', train=False, download=True, transform=transform)
+
+# splits data using dataloader with 256 batches
+train_loader = DataLoader(train_set, batch_size=256, shuffle=True)
+test_loader = DataLoader(test_set, batch_size=256, shuffle=False)
+
+# CNN initialization and training the model
+cnn = CNN()
+cnn.fit(train_loader, test_loader, epochs=10)
+
+# tests the model
+test_acc = cnn.evaluate(test_loader)
+print(f"\nFinal test accuracy: {test_acc:.4f}")
\ No newline at end of file
diff --git a/results/experiment-6-convolutional-neural-network.png b/results/experiment-6-convolutional-neural-network.png
new file mode 100644
index 0000000..a6c49d4
Binary files /dev/null and b/results/experiment-6-convolutional-neural-network.png differ
diff --git a/results/experiment-7.png b/results/experiment-7.png
new file mode 100644
index 0000000..5fa1b9e
Binary files /dev/null and b/results/experiment-7.png differ