diff --git a/Module_5/Week4/data/FashionMNIST/raw/t10k-images-idx3-ubyte b/Module_5/Week4/data/FashionMNIST/raw/t10k-images-idx3-ubyte
new file mode 100644
index 000000000..37bac79bc
Binary files /dev/null and b/Module_5/Week4/data/FashionMNIST/raw/t10k-images-idx3-ubyte differ
diff --git a/Module_5/Week4/data/FashionMNIST/raw/t10k-images-idx3-ubyte.gz b/Module_5/Week4/data/FashionMNIST/raw/t10k-images-idx3-ubyte.gz
new file mode 100644
index 000000000..667844f10
Binary files /dev/null and b/Module_5/Week4/data/FashionMNIST/raw/t10k-images-idx3-ubyte.gz differ
diff --git a/Module_5/Week4/data/FashionMNIST/raw/t10k-labels-idx1-ubyte b/Module_5/Week4/data/FashionMNIST/raw/t10k-labels-idx1-ubyte
new file mode 100644
index 000000000..2195a4d09
Binary files /dev/null and b/Module_5/Week4/data/FashionMNIST/raw/t10k-labels-idx1-ubyte differ
diff --git a/Module_5/Week4/data/FashionMNIST/raw/t10k-labels-idx1-ubyte.gz b/Module_5/Week4/data/FashionMNIST/raw/t10k-labels-idx1-ubyte.gz
new file mode 100644
index 000000000..abdddb89d
Binary files /dev/null and b/Module_5/Week4/data/FashionMNIST/raw/t10k-labels-idx1-ubyte.gz differ
diff --git a/Module_5/Week4/data/FashionMNIST/raw/train-images-idx3-ubyte b/Module_5/Week4/data/FashionMNIST/raw/train-images-idx3-ubyte
new file mode 100644
index 000000000..ff2f5a963
Binary files /dev/null and b/Module_5/Week4/data/FashionMNIST/raw/train-images-idx3-ubyte differ
diff --git a/Module_5/Week4/data/FashionMNIST/raw/train-images-idx3-ubyte.gz b/Module_5/Week4/data/FashionMNIST/raw/train-images-idx3-ubyte.gz
new file mode 100644
index 000000000..e6ee0e379
Binary files /dev/null and b/Module_5/Week4/data/FashionMNIST/raw/train-images-idx3-ubyte.gz differ
diff --git a/Module_5/Week4/data/FashionMNIST/raw/train-labels-idx1-ubyte b/Module_5/Week4/data/FashionMNIST/raw/train-labels-idx1-ubyte
new file mode 100644
index 000000000..30424ca2e
Binary files /dev/null and b/Module_5/Week4/data/FashionMNIST/raw/train-labels-idx1-ubyte differ
diff --git a/Module_5/Week4/data/FashionMNIST/raw/train-labels-idx1-ubyte.gz b/Module_5/Week4/data/FashionMNIST/raw/train-labels-idx1-ubyte.gz
new file mode 100644
index 000000000..9c4aae27b
Binary files /dev/null and b/Module_5/Week4/data/FashionMNIST/raw/train-labels-idx1-ubyte.gz differ
diff --git a/Module_5/Week4/exercise.ipynb b/Module_5/Week4/exercise.ipynb
new file mode 100644
index 000000000..d71636f49
--- /dev/null
+++ b/Module_5/Week4/exercise.ipynb
@@ -0,0 +1,643 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# SGD"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "\n",
+    "# The target function is f(w1,w2) = 0.1w_1^2 + 2w_2^2\n",
+    "def dW(W):\n",
+    "    dW1 = 2 * 0.1 * W[0]\n",
+    "    dW2 = 2 * 2 * W[1]\n",
+    "    dW = np.array([dW1, dW2])\n",
+    "    return dW\n",
+    "\n",
+    "def sgd(W, dW, lr):\n",
+    "    W = W - lr * dW\n",
+    "    return W\n",
+    "\n",
+    "def train_p1(optimizer, lr, epochs):\n",
+    "    W = np.array([-5,-2], dtype = np.float32)\n",
+    "    result = [W]\n",
+    "    for i in range(epochs):\n",
+    "        dW_ = dW(W)\n",
+    "        W = optimizer(W, dW_, lr)\n",
+    "        result.append(W)\n",
+    "    return result\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[array([-5., -2.], dtype=float32),\n",
+       " array([-4.6,  1.2]),\n",
+       " array([-4.232, -0.72 ]),\n",
+       " array([-3.89344,  0.432  ]),\n",
+       " array([-3.5819648, -0.2592   ]),\n",
+       " array([-3.29540762,  0.15552   ]),\n",
+       " array([-3.03177501, -0.093312  ]),\n",
+       " array([-2.78923301,  0.0559872 ]),\n",
+       " array([-2.56609437, -0.03359232]),\n",
+       " array([-2.36080682,  0.02015539]),\n",
+       " array([-2.17194227, -0.01209324]),\n",
+       " array([-1.99818689,  0.00725594]),\n",
+       " array([-1.83833194, -0.00435356]),\n",
+       " array([-1.69126538,  0.00261214]),\n",
+       " array([-1.55596415, -0.00156728]),\n",
+       " array([-1.43148702e+00,  9.40369969e-04]),\n",
+       " array([-1.31696806e+00, -5.64221981e-04]),\n",
+       " array([-1.21161061e+00,  3.38533189e-04]),\n",
+       " array([-1.11468176e+00, -2.03119913e-04]),\n",
+       " array([-1.02550722e+00,  1.21871948e-04]),\n",
+       " array([-9.43466646e-01, -7.31231688e-05]),\n",
+       " array([-8.67989314e-01,  4.38739013e-05]),\n",
+       " array([-7.98550169e-01, -2.63243408e-05]),\n",
+       " array([-7.34666155e-01,  1.57946045e-05]),\n",
+       " array([-6.75892863e-01, -9.47676268e-06]),\n",
+       " array([-6.21821434e-01,  5.68605761e-06]),\n",
+       " array([-5.72075719e-01, -3.41163456e-06]),\n",
+       " array([-5.26309662e-01,  2.04698074e-06]),\n",
+       " array([-4.84204889e-01, -1.22818844e-06]),\n",
+       " array([-4.45468498e-01,  7.36913066e-07]),\n",
+       " array([-4.09831018e-01, -4.42147839e-07])]"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "train_p1(sgd, lr=0.4, epochs=30)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# SGD with momentum"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def df_W(w):\n",
+    "    dw1 = 2 * 0.1 * w[0]\n",
+    "    dw2 = 2 * 2 * w[1]\n",
+    "    dw = np.array([dw1, dw2])\n",
+    "    return dw\n",
+    "\n",
+    "def sgd_momentum(w, dw, lr, v, beta):\n",
+    "    v = beta * v + (1 - beta) * dw\n",
+    "    w = w - lr * v\n",
+    "    return w, v\n",
+    "\n",
+    "def train_p2(optimizer, lr, epochs):\n",
+    "    W = np.array([-5, -2], dtype=np.float32)\n",
+    "    V = np.array([0, 0], dtype=np.float32)\n",
+    "    result = [W]\n",
+    "\n",
+    "    for _ in range(epochs):\n",
+    "        dW = df_W(W)\n",
+    "        W, V = optimizer(W, dW, lr, V, beta=0.5)\n",
+    "        result.append(W)\n",
+    "    \n",
+    "    return result"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[array([-5., -2.], dtype=float32),\n",
+       " array([-4.7,  0.4]),\n",
+       " array([-4.268,  1.12 ]),\n",
+       " array([-3.79592,  0.136  ]),\n",
+       " array([-3.3321248, -0.5192   ]),\n",
+       " array([-2.90029971, -0.22376   ]),\n",
+       " array([-2.51036919,  0.192472  ]),\n",
+       " array([-2.16478177,  0.1696216 ]),\n",
+       " array([-1.86210116, -0.04534952]),\n",
+       " array([-1.59903478, -0.09841566]),\n",
+       " array([-1.37155951, -0.00684994]),\n",
+       " array([-1.1755283 ,  0.04715285]),\n",
+       " array([-1.006981  ,  0.01757082]),\n",
+       " array([-0.86228849, -0.01830518]),\n",
+       " array([-0.73820492, -0.01427696]),\n",
+       " array([-0.63187084,  0.0048695 ]),\n",
+       " array([-0.54079155,  0.00859933]),\n",
+       " array([-4.62804416e-01,  1.45050014e-04]),\n",
+       " array([-0.39604258, -0.00425615]),\n",
+       " array([-0.33889911, -0.00134937]),\n",
+       " array([-0.28999343,  0.00172326]),\n",
+       " array([-0.24814098,  0.00119166]),\n",
+       " array([-0.2123263 , -0.00050413]),\n",
+       " array([-0.18167938, -0.00074707]),\n",
+       " array([-1.55455157e-01,  2.79448010e-05]),\n",
+       " array([-0.13301574,  0.00038192]),\n",
+       " array([-1.13815082e-01,  1.00603444e-04]),\n",
+       " array([-0.09738585, -0.00016078]),\n",
+       " array([-8.33280829e-02, -9.85353344e-05]),\n",
+       " array([-7.12995144e-02,  5.08287536e-05]),\n",
+       " array([-6.10072592e-02,  6.45162933e-05])]"
+      ]
+     },
+     "execution_count": 21,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "train_p2(sgd_momentum, lr=0.6, epochs=30)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# RMSPROP"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def df_W(W):\n",
+    "    dW1 = 2 * 0.1 * W[0]\n",
+    "    dW2 = 2 * 2 * W[1]\n",
+    "    dW = np.array([dW1, dW2])\n",
+    "    return dW\n",
+    "    \n",
+    "def RMSProp(W, dW, lr, S, gamma):\n",
+    "    epsilon = 1e-6\n",
+    "    S = gamma * S + (1 - gamma) * dW**2\n",
+    "    W = W - lr * dW / (np.sqrt(S) + epsilon)\n",
+    "    return W, S\n",
+    "\n",
+    "def train_p3(optimizer, lr, epochs):\n",
+    "    W = np.array([-5, -2], dtype=np.float32)\n",
+    "    S = np.array([0, 0], dtype=np.float32)\n",
+    "    results = [W]\n",
+    "    \n",
+    "    for _ in range(epochs):\n",
+    "        dW_ = df_W(W)\n",
+    "        W, S = optimizer(W, dW_, lr, S, gamma=0.9)\n",
+    "        results.append(W)\n",
+    "    return results"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[array([-5., -2.], dtype=float32),\n",
+       " array([-4.0513197 , -1.05131708]),\n",
+       " array([-3.43519553, -0.59152376]),\n",
+       " array([-2.95893489, -0.3294397 ]),\n",
+       " array([-2.56546089, -0.17756504]),\n",
+       " array([-2.22920358, -0.09163272]),\n",
+       " array([-1.93626564, -0.04494508]),\n",
+       " array([-1.67817504, -0.02081429]),\n",
+       " array([-1.44934809, -0.00903562]),\n",
+       " array([-1.24588029, -0.00364592]),\n",
+       " array([-1.06490135, -0.00135352]),\n",
+       " array([-9.04200650e-01, -4.56447225e-04]),\n",
+       " array([-7.61994932e-01, -1.37563947e-04]),\n",
+       " array([-6.36776983e-01, -3.62604278e-05]),\n",
+       " array([-5.27213771e-01, -8.11346375e-06]),\n",
+       " array([-4.32077091e-01, -1.47475425e-06]),\n",
+       " array([-3.50197152e-01, -2.02787524e-07]),\n",
+       " array([-2.80433359e-01, -1.84235524e-08]),\n",
+       " array([-2.21658617e-01, -7.67771777e-10]),\n",
+       " array([-1.72754375e-01,  7.80432778e-12]),\n",
+       " array([-1.32614084e-01, -5.05777072e-13]),\n",
+       " array([-1.00152823e-01,  6.19098174e-14]),\n",
+       " array([-7.43209130e-02, -1.13368674e-14]),\n",
+       " array([-5.41193712e-02,  2.80153177e-15]),\n",
+       " array([-3.86152607e-02, -8.81296300e-16]),\n",
+       " array([-2.69552510e-02,  3.39903035e-16]),\n",
+       " array([-1.83761024e-02, -1.56573095e-16]),\n",
+       " array([-1.22112361e-02,  8.44946934e-17]),\n",
+       " array([-7.89302368e-03, -5.26345869e-17]),\n",
+       " array([-4.95087715e-03,  3.74085662e-17]),\n",
+       " array([-3.00560338e-03, -3.00487798e-17])]"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "train_p3(RMSProp, lr=0.3, epochs=30)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Adam"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def df_W(W):\n",
+    "    dW1 = 2 * 0.1 * W[0]\n",
+    "    dW2 = 2 * 2 * W[1]\n",
+    "    dW = np.array([dW1, dW2])\n",
+    "    return dW\n",
+    "    \n",
+    "def Adam(W, dW, lr, V, S, beta1,beta2,t):\n",
+    "    epsilon = 1e-6\n",
+    "    V = beta1 * V + (1 - beta1) * dW\n",
+    "    S = beta2 * S + (1 - beta2) * dW**2\n",
+    "    V_ = V / (1 - beta1**t)\n",
+    "    S_ = S / (1 - beta2**t)\n",
+    "    W = W - lr * V_ / (np.sqrt(S_) + epsilon)\n",
+    "    return W, V, S\n",
+    "\n",
+    "def train_p3(optimizer, lr, epochs):\n",
+    "    W = np.array([-5, -2], dtype=np.float32)\n",
+    "    V = np.array([0, 0], dtype=np.float32)\n",
+    "    S = np.array([0, 0], dtype=np.float32)\n",
+    "    results = [W]\n",
+    "    \n",
+    "    for _ in range(epochs):\n",
+    "        dW_ = df_W(W)\n",
+    "        W, V,S = optimizer(W, dW_, lr, V, S, beta1=0.9, beta2=0.999, t=_+1)\n",
+    "        results.append(W)\n",
+    "    return results"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[array([-5., -2.], dtype=float32),\n",
+       " array([-4.8000002 , -1.80000002]),\n",
+       " array([-4.60025478, -1.60082451]),\n",
+       " array([-4.40094848, -1.40317262]),\n",
+       " array([-4.20227764, -1.20787822]),\n",
+       " array([-4.00445033, -1.01592745]),\n",
+       " array([-3.80768638, -0.82847307]),\n",
+       " array([-3.61221732, -0.64684159]),\n",
+       " array([-3.41828623, -0.47252765]),\n",
+       " array([-3.22614739, -0.30716934]),\n",
+       " array([-3.03606592, -0.15249855]),\n",
+       " array([-2.84831706, -0.01026326]),\n",
+       " array([-2.66318543,  0.11787552]),\n",
+       " array([-2.480964  ,  0.23046161]),\n",
+       " array([-2.30195279,  0.3263587 ]),\n",
+       " array([-2.12645742,  0.40484195]),\n",
+       " array([-1.95478732,  0.46564961]),\n",
+       " array([-1.7872537 ,  0.50898799]),\n",
+       " array([-1.62416726,  0.53549442]),\n",
+       " array([-1.46583566,  0.54617144]),\n",
+       " array([-1.31256067,  0.54230812]),\n",
+       " array([-1.16463526,  0.52540206]),\n",
+       " array([-1.02234036,  0.4970906 ]),\n",
+       " array([-0.88594163,  0.4590951 ]),\n",
+       " array([-0.75568617,  0.41317781]),\n",
+       " array([-0.63179919,  0.3611089 ]),\n",
+       " array([-0.51448089,  0.30464048]),\n",
+       " array([-0.40390346,  0.24548409]),\n",
+       " array([-0.30020842,  0.18528918]),\n",
+       " array([-0.20350426,  0.12562074]),\n",
+       " array([-0.11386457,  0.06793529])]"
+      ]
+     },
+     "execution_count": 20,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "train_p3(Adam, lr=0.2, epochs=30)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Vanishing Gradient"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<torch._C.Generator at 0x11e2c8e30>"
+      ]
+     },
+     "execution_count": 26,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import torch\n",
+    "from torch import nn\n",
+    "import torch.optim as optim\n",
+    "from torch.utils.data import Dataset, DataLoader\n",
+    "import torchvision\n",
+    "from torchvision.datasets import FashionMNIST\n",
+    "import torchvision.transforms as transforms\n",
+    "import numpy as np\n",
+    "device = torch.device('mps' if torch.mps.is_available() else 'cpu')\n",
+    "torch.manual_seed(42)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "device(type='mps')"
+      ]
+     },
+     "execution_count": 27,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "device"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "BATCH_SIZE = 512\n",
+    "EPOCHS = 300\n",
+    "lr = 0.01\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "train_dataset = FashionMNIST(root='./data', train=True, download=False, transform=transforms.ToTensor())\n",
+    "train_loader = DataLoader(train_dataset, BATCH_SIZE, shuffle=True)\n",
+    "test_dataset = FashionMNIST(root='./data', train=False, download=False, transform=transforms.ToTensor())\n",
+    "test_loader = DataLoader(test_dataset, BATCH_SIZE)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "class MLP(nn.Module):\n",
+    "    def __init__(self, input_dims, hidden_dims, output_dims):\n",
+    "        super(MLP, self).__init__()\n",
+    "        self.layer1 = nn.Linear(input_dims, hidden_dims)\n",
+    "        self.layer2 = nn.Linear(hidden_dims, hidden_dims)\n",
+    "        self.layer3 = nn.Linear(hidden_dims, hidden_dims)\n",
+    "        self.layer4 = nn.Linear(hidden_dims, hidden_dims)\n",
+    "        self.layer5 = nn.Linear(hidden_dims, hidden_dims)\n",
+    "        self.output = nn.Linear(hidden_dims, output_dims)\n",
+    "        self.sigmoid = nn.Sigmoid()\n",
+    "\n",
+    "    def forward(self, x):\n",
+    "        x = nn.Flatten()(x)\n",
+    "        x = self.layer1(x)\n",
+    "        x = self.sigmoid(x)\n",
+    "        x = self.layer2(x)\n",
+    "        x = self.sigmoid(x)\n",
+    "        x = self.layer3(x)\n",
+    "        x = self.sigmoid(x)\n",
+    "        x = self.layer4(x)\n",
+    "        x = self.sigmoid(x)\n",
+    "        x = self.layer5(x)\n",
+    "        x = self.sigmoid(x)\n",
+    "        out = self.output(x)\n",
+    "        return out"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model = MLP(input_dims=784, hidden_dims=128, output_dims=10).to(device)\n",
+    "criterion = nn.CrossEntropyLoss()\n",
+    "optimizer = optim.Adam(model.parameters(), lr=lr)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 47,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def train(model, train_loader, test_loader, loss_fn, optimizer, num_epochs):\n",
+    "    train_losses = []\n",
+    "    train_acc = []\n",
+    "    val_losses = []\n",
+    "    val_acc = []\n",
+    "    for epoch in range(num_epochs):\n",
+    "        model.train()\n",
+    "        t_loss = 0\n",
+    "        t_acc = 0\n",
+    "        cnt = 0\n",
+    "        for X, y in train_loader:\n",
+    "            X, y = X.to(device), y.to(device)\n",
+    "            optimizer.zero_grad()\n",
+    "            outputs = model(X)\n",
+    "            loss = loss_fn(outputs, y)\n",
+    "            loss.backward()\n",
+    "            optimizer.step()\n",
+    "            t_loss += loss.item()\n",
+    "            t_acc += (torch.argmax(outputs, 1) == y).sum().item()\n",
+    "            cnt += len(y)\n",
+    "        t_loss /= len(train_loader)\n",
+    "        train_losses.append(t_loss)\n",
+    "        t_acc /= cnt\n",
+    "        train_acc.append(t_acc)\n",
+    "\n",
+    "        model.eval()\n",
+    "        v_loss = 0\n",
+    "        v_acc = 0\n",
+    "        cnt = 0\n",
+    "        with torch.no_grad():\n",
+    "            for X, y in test_loader:\n",
+    "                X, y = X.to(device), y.to(device)\n",
+    "                outputs = model(X)\n",
+    "                loss = loss_fn(outputs, y)\n",
+    "                v_loss += loss.item()\n",
+    "                v_acc += (torch.argmax(outputs, 1)==y).sum().item()\n",
+    "                cnt += len(y)\n",
+    "        v_loss /= len(test_loader)\n",
+    "        val_losses.append(v_loss)\n",
+    "        v_acc /= cnt\n",
+    "        val_acc.append(v_acc)\n",
+    "        if epoch % 10 == 0:\n",
+    "            print(f\"Epoch {epoch+1}/{num_epochs}, Train_Loss: {t_loss:.4f}, Train_Acc: {t_acc:.4f}, Validation Loss: {v_loss:.4f}, Val_Acc: {v_acc:.4f}\")\n",
+    "    return train_losses, train_acc, val_losses, val_acc"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 48,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1/300, Train_Loss: 0.1757, Train_Acc: 0.9347, Validation Loss: 0.4328, Val_Acc: 0.8674\n",
+      "Epoch 11/300, Train_Loss: 0.1691, Train_Acc: 0.9372, Validation Loss: 0.4247, Val_Acc: 0.8771\n",
+      "Epoch 21/300, Train_Loss: 0.1528, Train_Acc: 0.9443, Validation Loss: 0.4297, Val_Acc: 0.8811\n",
+      "Epoch 31/300, Train_Loss: 0.1485, Train_Acc: 0.9457, Validation Loss: 0.4517, Val_Acc: 0.8803\n",
+      "Epoch 41/300, Train_Loss: 0.1384, Train_Acc: 0.9495, Validation Loss: 0.4729, Val_Acc: 0.8762\n",
+      "Epoch 51/300, Train_Loss: 0.1383, Train_Acc: 0.9491, Validation Loss: 0.4905, Val_Acc: 0.8763\n",
+      "Epoch 61/300, Train_Loss: 0.1247, Train_Acc: 0.9551, Validation Loss: 0.4995, Val_Acc: 0.8796\n",
+      "Epoch 71/300, Train_Loss: 0.1284, Train_Acc: 0.9529, Validation Loss: 0.4780, Val_Acc: 0.8789\n",
+      "Epoch 81/300, Train_Loss: 0.1177, Train_Acc: 0.9572, Validation Loss: 0.4979, Val_Acc: 0.8768\n",
+      "Epoch 91/300, Train_Loss: 0.1073, Train_Acc: 0.9603, Validation Loss: 0.5405, Val_Acc: 0.8806\n",
+      "Epoch 101/300, Train_Loss: 0.1040, Train_Acc: 0.9624, Validation Loss: 0.5233, Val_Acc: 0.8736\n",
+      "Epoch 111/300, Train_Loss: 0.1169, Train_Acc: 0.9575, Validation Loss: 0.5339, Val_Acc: 0.8754\n",
+      "Epoch 121/300, Train_Loss: 0.1049, Train_Acc: 0.9623, Validation Loss: 0.5359, Val_Acc: 0.8794\n",
+      "Epoch 131/300, Train_Loss: 0.1012, Train_Acc: 0.9636, Validation Loss: 0.5694, Val_Acc: 0.8760\n",
+      "Epoch 141/300, Train_Loss: 0.0959, Train_Acc: 0.9657, Validation Loss: 0.5617, Val_Acc: 0.8776\n",
+      "Epoch 151/300, Train_Loss: 0.0978, Train_Acc: 0.9642, Validation Loss: 0.5766, Val_Acc: 0.8782\n",
+      "Epoch 161/300, Train_Loss: 0.0899, Train_Acc: 0.9672, Validation Loss: 0.6099, Val_Acc: 0.8723\n",
+      "Epoch 171/300, Train_Loss: 0.1031, Train_Acc: 0.9627, Validation Loss: 0.5522, Val_Acc: 0.8811\n",
+      "Epoch 181/300, Train_Loss: 0.0921, Train_Acc: 0.9677, Validation Loss: 0.5674, Val_Acc: 0.8799\n",
+      "Epoch 191/300, Train_Loss: 0.0798, Train_Acc: 0.9714, Validation Loss: 0.5815, Val_Acc: 0.8782\n",
+      "Epoch 201/300, Train_Loss: 0.0904, Train_Acc: 0.9681, Validation Loss: 0.5960, Val_Acc: 0.8749\n",
+      "Epoch 211/300, Train_Loss: 0.0835, Train_Acc: 0.9706, Validation Loss: 0.5663, Val_Acc: 0.8769\n",
+      "Epoch 221/300, Train_Loss: 0.0806, Train_Acc: 0.9712, Validation Loss: 0.6429, Val_Acc: 0.8768\n",
+      "Epoch 231/300, Train_Loss: 0.0721, Train_Acc: 0.9740, Validation Loss: 0.6250, Val_Acc: 0.8720\n",
+      "Epoch 241/300, Train_Loss: 0.0875, Train_Acc: 0.9697, Validation Loss: 0.5724, Val_Acc: 0.8732\n",
+      "Epoch 251/300, Train_Loss: 0.0906, Train_Acc: 0.9686, Validation Loss: 0.6257, Val_Acc: 0.8758\n",
+      "Epoch 261/300, Train_Loss: 0.0688, Train_Acc: 0.9750, Validation Loss: 0.6473, Val_Acc: 0.8766\n",
+      "Epoch 271/300, Train_Loss: 0.0761, Train_Acc: 0.9737, Validation Loss: 0.6127, Val_Acc: 0.8708\n",
+      "Epoch 281/300, Train_Loss: 0.0616, Train_Acc: 0.9779, Validation Loss: 0.6905, Val_Acc: 0.8748\n",
+      "Epoch 291/300, Train_Loss: 0.0893, Train_Acc: 0.9688, Validation Loss: 0.5843, Val_Acc: 0.8683\n"
+     ]
+    }
+   ],
+   "source": [
+    "train_losses, train_acc, val_losses, val_acc = train(model, train_loader, test_loader, criterion, optimizer, EPOCHS)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 49,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1200x600 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "def plot(train_losses, train_acc, val_losses, val_acc):\n",
+    "    plt.figure(figsize=(12, 6))\n",
+    "    \n",
+    "    plt.subplot(1, 2, 1)\n",
+    "    plt.plot(train_acc, label='train_accuracy')\n",
+    "    plt.plot(val_acc, label='val_accuracy')\n",
+    "    plt.xlabel('iteration')\n",
+    "    plt.ylabel('Accuracy')\n",
+    "    plt.legend()\n",
+    "\n",
+    "    plt.subplot(1, 2, 2)\n",
+    "    plt.plot(train_losses, label='loss')\n",
+    "    plt.plot(val_losses, label='val_loss')\n",
+    "    plt.xlabel('iteration')\n",
+    "    plt.ylabel('Loss')\n",
+    "    plt.legend()\n",
+    "    \n",
+    "plot(train_losses, train_acc, val_losses, val_acc)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "aio_2024",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git "a/Module_5/Week4/\304\220\341\273\227 Huy \304\220\341\273\251c_M5W4.pdf" "b/Module_5/Week4/\304\220\341\273\227 Huy \304\220\341\273\251c_M5W4.pdf"
new file mode 100644
index 000000000..253c05277
Binary files /dev/null and "b/Module_5/Week4/\304\220\341\273\227 Huy \304\220\341\273\251c_M5W4.pdf" differ