diff --git a/M1/Statistical Learning/TP3_Logistic_Regression_and _SGD.ipynb b/M1/Statistical Learning/TP3_Logistic_Regression_and _SGD.ipynb
index a039778..ab0cdb7 100644
--- a/M1/Statistical Learning/TP3_Logistic_Regression_and _SGD.ipynb	
+++ b/M1/Statistical Learning/TP3_Logistic_Regression_and _SGD.ipynb	
@@ -487,13 +487,13 @@
    "cell_type": "code",
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2025-03-05T10:42:09.048335Z",
-     "start_time": "2025-03-05T10:42:09.043811Z"
+     "end_time": "2025-03-05T10:44:03.685253Z",
+     "start_time": "2025-03-05T10:44:03.682070Z"
     }
    },
    "source": [
     "def GD_training(X, y, num_steps, learning_rate):\n",
-    "    w, b = np.zeros(2, dtype=float), 0\n",
+    "    w, b = np.zeros(2), 0\n",
     "\n",
     "    for step in range(num_steps):\n",
     "        h = sigmoid(np.dot(X, w) + b)\n",
@@ -511,7 +511,7 @@
     "    return w, b"
    ],
    "outputs": [],
-   "execution_count": 138
+   "execution_count": 144
   },
   {
    "cell_type": "markdown",
@@ -524,8 +524,8 @@
    "cell_type": "code",
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2025-03-05T10:42:11.424750Z",
-     "start_time": "2025-03-05T10:42:10.914149Z"
+     "end_time": "2025-03-05T10:44:05.205683Z",
+     "start_time": "2025-03-05T10:44:04.457359Z"
     }
    },
    "source": [
@@ -562,14 +562,14 @@
      ]
     }
    ],
-   "execution_count": 139
+   "execution_count": 145
   },
   {
    "cell_type": "code",
    "metadata": {
     "ExecuteTime": {
-     "end_time": "2025-03-05T10:41:03.179258Z",
-     "start_time": "2025-03-05T10:41:02.929587Z"
+     "end_time": "2025-03-05T10:44:06.503264Z",
+     "start_time": "2025-03-05T10:44:06.157991Z"
     }
    },
    "source": [
@@ -599,7 +599,7 @@
      "output_type": "display_data"
     }
    ],
-   "execution_count": 137
+   "execution_count": 146
   },
   {
    "cell_type": "markdown",