diff --git a/tutorials/W1D1_Generalization/W1D1_Tutorial5.ipynb b/tutorials/W1D1_Generalization/W1D1_Tutorial5.ipynb
index 2a3d6fce8..b37965ff6 100644
--- a/tutorials/W1D1_Generalization/W1D1_Tutorial5.ipynb
+++ b/tutorials/W1D1_Generalization/W1D1_Tutorial5.ipynb
@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 6,
    "id": "12bb9e08-6996-4d6b-8b80-a7a26191c9d6",
    "metadata": {},
    "outputs": [],
@@ -12,43 +12,49 @@
     "import numpy as np\n",
     "import torch\n",
     "import torch.nn as nn\n",
-    "import torch.optim as optim"
+    "import torch.optim as optim\n",
+    "import os\n",
+    "import hashlib\n",
+    "import requests"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 7,
    "id": "85fea2ec-e1ee-4ebe-9dff-d3b253c3ba0b",
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Data retrieval and loading\n",
-    "import os\n",
-    "import hashlib\n",
-    "import requests\n",
-    "\n",
-    "fname = \"condsForSimJ2moMuscles.mat\"\n",
-    "url = \"https://osf.io/wak7e/download\"\n",
-    "expected_md5 = \"257d16c4d92759d615bf5cac75dd9a1f\"\n",
+    "# Variables for file and download URL\n",
+    "fname = \"condsForSimJ2moMuscles.mat\"  # The name of the file to be downloaded\n",
+    "url = \"https://osf.io/wak7e/download\" # URL from where the file will be downloaded\n",
+    "expected_md5 = \"257d16c4d92759d615bf5cac75dd9a1f\" # MD5 hash for verifying file integrity\n",
     "\n",
+    "# Check if the file already exists\n",
     "if not os.path.isfile(fname):\n",
-    "  try:\n",
-    "    r = requests.get(url)\n",
-    "  except requests.ConnectionError:\n",
-    "    print(\"!!! Failed to download data !!!\")\n",
-    "  else:\n",
-    "    if r.status_code != requests.codes.ok:\n",
-    "      print(\"!!! Failed to download data !!!\")\n",
-    "    elif hashlib.md5(r.content).hexdigest() != expected_md5:\n",
-    "      print(\"!!! Data download appears corrupted !!!\")\n",
+    "    try:\n",
+    "        # Attempt to download the file\n",
+    "        r = requests.get(url) # Make a GET request to the specified URL\n",
+    "    except requests.ConnectionError:\n",
+    "        # Handle connection errors during the download\n",
+    "        print(\"!!! Failed to download data !!!\")\n",
     "    else:\n",
-    "      with open(fname, \"wb\") as fid:\n",
-    "        fid.write(r.content)"
+    "        # No connection errors, proceed to check the response\n",
+    "        if r.status_code != requests.codes.ok:\n",
+    "            # Check if the HTTP response status code indicates a successful download\n",
+    "            print(\"!!! Failed to download data !!!\")\n",
+    "        elif hashlib.md5(r.content).hexdigest() != expected_md5:\n",
+    "            # Verify the integrity of the downloaded file using MD5 checksum\n",
+    "            print(\"!!! Data download appears corrupted !!!\")\n",
+    "        else:\n",
+    "            # If download is successful and data is not corrupted, save the file\n",
+    "            with open(fname, \"wb\") as fid:\n",
+    "                fid.write(r.content) # Write the downloaded content to a file"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 8,
    "id": "2baca459-5a6a-489b-90d3-dffa0a4893e5",
    "metadata": {},
    "outputs": [],
@@ -62,7 +68,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 9,
    "id": "50c15d51-8e59-4305-a2bc-e270ac349085",
    "metadata": {},
    "outputs": [
@@ -70,7 +76,7 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "/tmp/ipykernel_379228/1417502240.py:30: UserWarning: Creating a tensor from a list of numpy.ndarrays is extremely slow. Please consider converting the list to a single numpy.ndarray with numpy.array() before converting to a tensor. (Triggered internally at ../torch/csrc/utils/tensor_new.cpp:230.)\n",
+      "/tmp/ipykernel_424184/2115013347.py:30: UserWarning: Creating a tensor from a list of numpy.ndarrays is extremely slow. Please consider converting the list to a single numpy.ndarray with numpy.array() before converting to a tensor. (Triggered internally at ../torch/csrc/utils/tensor_new.cpp:230.)\n",
       "  go_envelope_all.append(torch.tensor(go_envelope_condition, dtype=torch.float32))\n"
      ]
     },
@@ -107,7 +113,7 @@
     "        muscle = condition['muscle']\n",
     "\n",
     "        # Select only muscles 5 and 6 \n",
-    "        selected_muscle_data = muscle[:, [4, 5]]  # Select columns for muscle 5 and 6, which show the nicest multiphasic activity\n",
+    "        selected_muscle_data = muscle[:, [4, 5]]  # which show the nicest multiphasic activity\n",
     "\n",
     "        go_envelope_condition.append(go_envelope)\n",
     "        plan_condition.append(plan)\n",
@@ -136,49 +142,47 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
-   "id": "b9515c13-74d5-4fb5-8614-53fbb8dcfe06",
+   "execution_count": 10,
+   "id": "417463ca-29c8-4229-baed-58dcf390747a",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Normalized Go Envelope Tensor Shape: torch.Size([216, 296, 1])\n",
-      "Normalized Plan Tensor Shape: torch.Size([216, 296, 15])\n",
-      "Normalized Muscle Tensor Shape: torch.Size([216, 296, 2])\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
-    "# Normalize and standardize a tensor\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "# Normalization and Standardization\n",
     "def normalize_and_standardize(tensor):\n",
-    "    # Normalize: Scale to 0-1 range\n",
+    "    # Normalize: scale to 0-1 range\n",
     "    min_val = tensor.min()\n",
     "    max_val = tensor.max()\n",
     "    tensor = (tensor - min_val) / (max_val - min_val)\n",
     "\n",
-    "    # Standardize: Shift to zero mean and unit variance\n",
+    "    # Standardize: shift to zero mean and unit variance\n",
     "    mean = tensor.mean()\n",
     "    std = tensor.std()\n",
     "    tensor = (tensor - mean) / std\n",
     "\n",
     "    return tensor\n",
     "\n",
-    "# Apply the function to each tensor\n",
+    "# Apply normalization and standardization to go_envelope_tensor and plan_tensor\n",
     "normalized_go_envelope_tensor = normalize_and_standardize(go_envelope_tensor)\n",
     "normalized_plan_tensor = normalize_and_standardize(plan_tensor)\n",
     "normalized_muscle_tensor = normalize_and_standardize(muscle_tensor)\n",
     "\n",
-    "# Print shapes to confirm\n",
-    "print(f\"Normalized Go Envelope Tensor Shape: {normalized_go_envelope_tensor.shape}\")\n",
-    "print(f\"Normalized Plan Tensor Shape: {normalized_plan_tensor.shape}\")\n",
-    "print(f\"Normalized Muscle Tensor Shape: {normalized_muscle_tensor.shape}\")\n"
+    "# Concatenate normalized tensors along the last dimension\n",
+    "X_train = torch.cat((normalized_go_envelope_tensor, normalized_plan_tensor), dim=2)\n",
+    "y_train = normalized_muscle_tensor\n",
+    "\n",
+    "# Convert datasets to TensorDataset and DataLoader for batch processing\n",
+    "from torch.utils.data import TensorDataset, DataLoader\n",
+    "\n",
+    "batch_size = 64  # You can adjust this based on your data size and memory constraints\n",
+    "train_data = TensorDataset(X_train, y_train)\n",
+    "train_loader = DataLoader(train_data, batch_size=batch_size, shuffle=False)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 11,
    "id": "7e2b6a95-49a0-4f10-8f63-3b85a7f7d7be",
    "metadata": {},
    "outputs": [],
@@ -244,87 +248,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
-   "id": "de475624-9823-4fd4-a591-960795badf82",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import torch\n",
-    "import torch.nn as nn\n",
-    "\n",
-    "# Define a custom Rectified Tanh activation function\n",
-    "def rectified_tanh(x):\n",
-    "    return torch.where(x > 0, x, torch.tanh(x))\n",
-    "    \n",
-    "class ComplicatedRNN(nn.Module):\n",
-    "    def __init__(self, input_size, hidden_size, output_size, g, h, tau=50):\n",
-    "        super(ComplicatedRNN, self).__init__()\n",
-    "        self.hidden_size = hidden_size\n",
-    "        self.tau = tau  # Time constant\n",
-    "\n",
-    "        # Modified weight initialization for a more chaotic regime (g >> 1)\n",
-    "        self.J = nn.Parameter(torch.randn(hidden_size, hidden_size) * (g / torch.sqrt(torch.tensor(hidden_size, dtype=torch.float))))\n",
-    "        self.B = nn.Parameter(torch.randn(hidden_size, input_size) * (h / torch.sqrt(torch.tensor(input_size, dtype=torch.float))))\n",
-    "        self.w = nn.Parameter(torch.zeros(output_size, hidden_size))\n",
-    "        self.bx = nn.Parameter(torch.zeros(hidden_size))\n",
-    "        self.bz = nn.Parameter(torch.zeros(output_size))\n",
-    "\n",
-    "        # Nonlinearity\n",
-    "        self.nonlinearity = rectified_tanh    \n",
-    "    \n",
-    "    def forward(self, x, hidden):\n",
-    "        timestep = self.tau / 10  # Timestep for Euler integration\n",
-    "        for _ in range(int(1 / timestep)):  # Adjust the range for simulation duration\n",
-    "            hidden_update = torch.matmul(self.J, hidden.T)\n",
-    "            input_update = torch.matmul(self.B, x.T)\n",
-    "            new_hidden = hidden_update + input_update + self.bx.unsqueeze(1)  \n",
-    "            new_hidden = new_hidden.T\n",
-    "    \n",
-    "            # Euler integration for continuous-time update\n",
-    "            hidden = hidden + (timestep / self.tau) * (-hidden + new_hidden)\n",
-    "        \n",
-    "        output = torch.matmul(self.w, hidden.T) + self.bz.unsqueeze(1)\n",
-    "        output = output.T\n",
-    "    \n",
-    "        return output, hidden\n",
-    "\n",
-    "    def init_hidden(self, batch_size):\n",
-    "        # Initialize hidden state with batch dimension\n",
-    "        return torch.zeros(batch_size, self.hidden_size)\n",
-    "\n",
-    "input_size = 16\n",
-    "hidden_size = 300\n",
-    "output_size = 2 # Number of muscles\n",
-    "g = 4 # Significantly larger g value for complicated model\n",
-    "h = 1.0 # h value remains the same\n",
-    "\n",
-    "complicated_model = ComplicatedRNN(input_size, hidden_size, output_size, g, h)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "711bd5b4-d92c-43e4-b3c6-fb0a6fabb369",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Convert datasets to TensorDataset and DataLoader for batch processing\n",
-    "from torch.utils.data import TensorDataset, DataLoader\n",
-    "\n",
-    "# Concatenate along the third dimension (dim=2)\n",
-    "X_train = torch.cat((normalized_go_envelope_tensor, normalized_plan_tensor), dim=2)\n",
-    "\n",
-    "# y_train remains the same\n",
-    "y_train = normalized_muscle_tensor\n",
-    "\n",
-    "batch_size = 64  # You can adjust this based on your data size and memory constraints\n",
-    "train_data = TensorDataset(X_train, y_train)\n",
-    "train_loader = DataLoader(train_data, batch_size=batch_size, shuffle=True)\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 12,
    "id": "72179104-fa01-47b6-87ea-22b40e5f544f",
    "metadata": {},
    "outputs": [],
@@ -336,14 +260,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 13,
    "id": "85120248-46b3-44c7-b8dc-9408f493bb96",
    "metadata": {},
    "outputs": [],
    "source": [
     "def compute_l2_regularization(parameters, alpha):\n",
     "    l2_reg = sum(p.pow(2.0).sum() for p in parameters)\n",
-    "    return alpha * l2_reg\n"
+    "    return alpha * l2_reg"
    ]
   },
   {
@@ -356,262 +280,112 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Epoch 1, Loss: 4938.605224609375\n",
-      "Epoch 2, Loss: 1295.0733032226562\n",
-      "Epoch 3, Loss: 965.5600967407227\n",
-      "Epoch 4, Loss: 791.5160140991211\n",
-      "Epoch 5, Loss: 687.3917083740234\n",
-      "Epoch 6, Loss: 618.6651153564453\n",
-      "Epoch 7, Loss: 566.2944068908691\n",
-      "Epoch 8, Loss: 523.9398002624512\n",
-      "Epoch 9, Loss: 485.9263610839844\n",
-      "Epoch 10, Loss: 457.67305755615234\n",
-      "Epoch 11, Loss: 434.0043525695801\n",
-      "Epoch 12, Loss: 412.8926696777344\n",
-      "Epoch 13, Loss: 395.6022033691406\n",
-      "Epoch 14, Loss: 379.44727325439453\n",
-      "Epoch 15, Loss: 364.9649772644043\n",
-      "Epoch 16, Loss: 353.11585998535156\n",
-      "Epoch 17, Loss: 342.391414642334\n",
-      "Epoch 18, Loss: 332.4645195007324\n",
-      "Epoch 19, Loss: 323.6790466308594\n",
-      "Epoch 20, Loss: 315.0000762939453\n",
-      "Epoch 21, Loss: 306.9930610656738\n",
-      "Epoch 22, Loss: 299.6181411743164\n",
-      "Epoch 23, Loss: 292.6883773803711\n",
-      "Epoch 24, Loss: 286.3407440185547\n",
-      "Epoch 25, Loss: 280.4109916687012\n",
-      "Epoch 26, Loss: 274.64086532592773\n",
-      "Epoch 27, Loss: 269.39166259765625\n",
-      "Epoch 28, Loss: 264.0611686706543\n",
-      "Epoch 29, Loss: 259.2327079772949\n",
-      "Epoch 30, Loss: 254.4429931640625\n",
-      "Epoch 31, Loss: 250.22268104553223\n",
-      "Epoch 32, Loss: 245.94900131225586\n",
-      "Epoch 33, Loss: 241.86444091796875\n",
-      "Epoch 34, Loss: 237.94250297546387\n",
-      "Epoch 35, Loss: 234.24245262145996\n",
-      "Epoch 36, Loss: 230.7466526031494\n",
-      "Epoch 37, Loss: 227.3188419342041\n",
-      "Epoch 38, Loss: 224.0238151550293\n",
-      "Epoch 39, Loss: 220.87032318115234\n",
-      "Epoch 40, Loss: 217.83648300170898\n",
-      "Epoch 41, Loss: 214.89534187316895\n",
-      "Epoch 42, Loss: 212.00468063354492\n",
-      "Epoch 43, Loss: 209.3209400177002\n",
-      "Epoch 44, Loss: 206.65435791015625\n",
-      "Epoch 45, Loss: 204.07197761535645\n",
-      "Epoch 46, Loss: 201.58534049987793\n",
-      "Epoch 47, Loss: 199.18184661865234\n",
-      "Epoch 48, Loss: 196.85686492919922\n",
-      "Epoch 49, Loss: 194.52579879760742\n",
-      "Epoch 50, Loss: 192.33079528808594\n",
-      "Epoch 51, Loss: 190.19147300720215\n",
-      "Epoch 52, Loss: 188.09815979003906\n",
-      "Epoch 53, Loss: 186.10157775878906\n",
-      "Epoch 54, Loss: 184.10002326965332\n",
-      "Epoch 55, Loss: 182.13790321350098\n",
-      "Epoch 56, Loss: 180.33533668518066\n",
-      "Epoch 57, Loss: 178.46602058410645\n",
-      "Epoch 58, Loss: 176.65903091430664\n",
-      "Epoch 59, Loss: 174.89368438720703\n",
-      "Epoch 60, Loss: 173.20452690124512\n",
-      "Epoch 61, Loss: 171.5056266784668\n",
-      "Epoch 62, Loss: 169.90063667297363\n",
-      "Epoch 63, Loss: 168.29527473449707\n",
-      "Epoch 64, Loss: 166.74669075012207\n",
-      "Epoch 65, Loss: 165.21487045288086\n",
-      "Epoch 66, Loss: 163.77407264709473\n",
-      "Epoch 67, Loss: 162.32270622253418\n",
-      "Epoch 68, Loss: 160.9250259399414\n",
-      "Epoch 69, Loss: 159.5614776611328\n",
-      "Epoch 70, Loss: 158.22580528259277\n",
-      "Epoch 71, Loss: 156.92303848266602\n",
-      "Epoch 72, Loss: 155.66594123840332\n",
-      "Epoch 73, Loss: 154.42497634887695\n",
-      "Epoch 74, Loss: 153.20358657836914\n",
-      "Epoch 75, Loss: 152.04891395568848\n",
-      "Epoch 76, Loss: 150.8815517425537\n",
-      "Epoch 77, Loss: 149.72225189208984\n",
-      "Epoch 78, Loss: 148.58679962158203\n",
-      "Epoch 79, Loss: 147.4722080230713\n",
-      "Epoch 80, Loss: 146.35778903961182\n",
-      "Epoch 81, Loss: 145.25269508361816\n",
-      "Epoch 82, Loss: 144.16508102416992\n",
-      "Epoch 83, Loss: 143.13162231445312\n",
-      "Epoch 84, Loss: 142.1336441040039\n",
-      "Epoch 85, Loss: 141.14114570617676\n",
-      "Epoch 86, Loss: 140.17386627197266\n",
-      "Epoch 87, Loss: 139.2314805984497\n",
-      "Epoch 88, Loss: 138.29072380065918\n",
-      "Epoch 89, Loss: 137.3809413909912\n",
-      "Epoch 90, Loss: 136.4768829345703\n",
-      "Epoch 91, Loss: 135.58817672729492\n",
-      "Epoch 92, Loss: 134.7273416519165\n",
-      "Epoch 93, Loss: 133.8920021057129\n",
-      "Epoch 94, Loss: 133.01887226104736\n",
-      "Epoch 95, Loss: 132.2247772216797\n",
-      "Epoch 96, Loss: 131.39577770233154\n",
-      "Epoch 97, Loss: 130.58900260925293\n",
-      "Epoch 98, Loss: 129.79766941070557\n",
-      "Epoch 99, Loss: 129.02627563476562\n",
-      "Epoch 100, Loss: 128.26723289489746\n",
-      "Epoch 101, Loss: 127.52984142303467\n",
-      "Epoch 102, Loss: 126.78628730773926\n",
-      "Epoch 103, Loss: 126.04676151275635\n",
-      "Epoch 104, Loss: 125.35252475738525\n",
-      "Epoch 105, Loss: 124.64721775054932\n",
-      "Epoch 106, Loss: 123.95791149139404\n",
-      "Epoch 107, Loss: 123.26878643035889\n",
-      "Epoch 108, Loss: 122.5993242263794\n",
-      "Epoch 109, Loss: 121.94674396514893\n",
-      "Epoch 110, Loss: 121.29479312896729\n",
-      "Epoch 111, Loss: 120.6463041305542\n",
-      "Epoch 112, Loss: 120.00781345367432\n",
-      "Epoch 113, Loss: 119.39066505432129\n",
-      "Epoch 114, Loss: 118.76280403137207\n",
-      "Epoch 115, Loss: 118.15310859680176\n",
-      "Epoch 116, Loss: 117.55627822875977\n",
-      "Epoch 117, Loss: 116.97070693969727\n",
-      "Epoch 118, Loss: 116.38850021362305\n",
-      "Epoch 119, Loss: 115.82897758483887\n",
-      "Epoch 120, Loss: 115.25263977050781\n",
-      "Epoch 121, Loss: 114.68865966796875\n",
-      "Epoch 122, Loss: 114.15333557128906\n",
-      "Epoch 123, Loss: 113.60746192932129\n",
-      "Epoch 124, Loss: 113.06210708618164\n",
-      "Epoch 125, Loss: 112.55292892456055\n",
-      "Epoch 126, Loss: 112.02379322052002\n",
-      "Epoch 127, Loss: 111.50806427001953\n",
-      "Epoch 128, Loss: 111.00693035125732\n",
-      "Epoch 129, Loss: 110.49953842163086\n",
-      "Epoch 130, Loss: 110.00808143615723\n",
-      "Epoch 131, Loss: 109.51173400878906\n",
-      "Epoch 132, Loss: 109.02832794189453\n",
-      "Epoch 133, Loss: 108.54358005523682\n",
-      "Epoch 134, Loss: 108.07943153381348\n",
-      "Epoch 135, Loss: 107.60197353363037\n",
-      "Epoch 136, Loss: 107.15058422088623\n",
-      "Epoch 137, Loss: 106.70587825775146\n",
-      "Epoch 138, Loss: 106.24018383026123\n",
-      "Epoch 139, Loss: 105.77648162841797\n",
-      "Epoch 140, Loss: 105.3301420211792\n",
-      "Epoch 141, Loss: 104.87953567504883\n",
-      "Epoch 142, Loss: 104.45178318023682\n",
-      "Epoch 143, Loss: 104.02365016937256\n",
-      "Epoch 144, Loss: 103.59323692321777\n",
-      "Epoch 145, Loss: 103.1684341430664\n",
-      "Epoch 146, Loss: 102.74189186096191\n",
-      "Epoch 147, Loss: 102.3355302810669\n",
-      "Epoch 148, Loss: 101.93471717834473\n",
-      "Epoch 149, Loss: 101.5215711593628\n",
-      "Epoch 150, Loss: 101.13100337982178\n",
-      "Epoch 151, Loss: 100.72040176391602\n",
-      "Epoch 152, Loss: 100.32776737213135\n",
-      "Epoch 153, Loss: 99.95015525817871\n",
-      "Epoch 154, Loss: 99.56613540649414\n",
-      "Epoch 155, Loss: 99.18954849243164\n",
-      "Epoch 156, Loss: 98.80320358276367\n",
-      "Epoch 157, Loss: 98.444993019104\n",
-      "Epoch 158, Loss: 98.0760908126831\n",
-      "Epoch 159, Loss: 97.71605587005615\n",
-      "Epoch 160, Loss: 97.34914875030518\n",
-      "Epoch 161, Loss: 96.98707866668701\n",
-      "Epoch 162, Loss: 96.6336669921875\n",
-      "Epoch 163, Loss: 96.2850513458252\n",
-      "Epoch 164, Loss: 95.94112396240234\n",
-      "Epoch 165, Loss: 95.60957336425781\n",
-      "Epoch 166, Loss: 95.27218914031982\n",
-      "Epoch 167, Loss: 94.92330932617188\n",
-      "Epoch 168, Loss: 94.57761287689209\n",
-      "Epoch 169, Loss: 94.2492151260376\n",
-      "Epoch 170, Loss: 93.91864681243896\n",
-      "Epoch 171, Loss: 93.59208869934082\n",
-      "Epoch 172, Loss: 93.26942348480225\n",
-      "Epoch 173, Loss: 92.95455551147461\n",
-      "Epoch 174, Loss: 92.63883399963379\n",
-      "Epoch 175, Loss: 92.32403659820557\n",
-      "Epoch 176, Loss: 91.9965991973877\n",
-      "Epoch 177, Loss: 91.68417167663574\n",
-      "Epoch 178, Loss: 91.37313079833984\n",
-      "Epoch 179, Loss: 91.0718584060669\n",
-      "Epoch 180, Loss: 90.76884365081787\n",
-      "Epoch 181, Loss: 90.47068691253662\n",
-      "Epoch 182, Loss: 90.16975021362305\n",
-      "Epoch 183, Loss: 89.8705472946167\n",
-      "Epoch 184, Loss: 89.57856273651123\n",
-      "Epoch 185, Loss: 89.28864192962646\n",
-      "Epoch 186, Loss: 88.99736022949219\n",
-      "Epoch 187, Loss: 88.71282005310059\n",
-      "Epoch 188, Loss: 88.43143844604492\n",
-      "Epoch 189, Loss: 88.15027046203613\n",
-      "Epoch 190, Loss: 87.86935043334961\n",
-      "Epoch 191, Loss: 87.59745788574219\n",
-      "Epoch 192, Loss: 87.31881332397461\n",
-      "Epoch 193, Loss: 87.04376602172852\n",
-      "Epoch 194, Loss: 86.78018951416016\n",
-      "Epoch 195, Loss: 86.50899505615234\n",
-      "Epoch 196, Loss: 86.24000358581543\n",
-      "Epoch 197, Loss: 85.98038864135742\n",
-      "Epoch 198, Loss: 85.71853733062744\n",
-      "Epoch 199, Loss: 85.45761680603027\n",
-      "Epoch 200, Loss: 85.19479846954346\n",
-      "Epoch 201, Loss: 84.93951988220215\n",
-      "Epoch 202, Loss: 84.68980407714844\n",
-      "Epoch 203, Loss: 84.44610691070557\n",
-      "Epoch 204, Loss: 84.18738269805908\n",
-      "Epoch 205, Loss: 83.95299339294434\n",
-      "Epoch 206, Loss: 83.7006425857544\n",
-      "Epoch 207, Loss: 83.4469518661499\n",
-      "Epoch 208, Loss: 83.21451568603516\n",
-      "Epoch 209, Loss: 82.9843864440918\n",
-      "Epoch 210, Loss: 82.74285221099854\n",
-      "Epoch 211, Loss: 82.51256847381592\n",
-      "Epoch 212, Loss: 82.26631736755371\n",
-      "Epoch 213, Loss: 82.03435897827148\n",
-      "Epoch 214, Loss: 81.81490516662598\n",
-      "Epoch 215, Loss: 81.59878730773926\n",
-      "Epoch 216, Loss: 81.37904834747314\n",
-      "Epoch 217, Loss: 81.1410264968872\n",
-      "Epoch 218, Loss: 80.9194164276123\n",
-      "Epoch 219, Loss: 80.71647548675537\n",
-      "Epoch 220, Loss: 80.50080871582031\n",
-      "Epoch 221, Loss: 80.25177383422852\n",
-      "Epoch 222, Loss: 80.00597858428955\n",
-      "Epoch 223, Loss: 79.77255535125732\n",
-      "Epoch 224, Loss: 79.5474739074707\n",
-      "Epoch 225, Loss: 79.31333255767822\n",
-      "Epoch 226, Loss: 79.08616733551025\n",
-      "Epoch 227, Loss: 78.8524169921875\n",
-      "Epoch 228, Loss: 78.62970924377441\n",
-      "Epoch 229, Loss: 78.41379833221436\n",
-      "Epoch 230, Loss: 78.19831657409668\n",
-      "Epoch 231, Loss: 77.9847354888916\n",
-      "Epoch 232, Loss: 77.7769718170166\n",
-      "Epoch 233, Loss: 77.56798934936523\n",
-      "Epoch 234, Loss: 77.35770893096924\n",
-      "Epoch 235, Loss: 77.15143299102783\n",
-      "Epoch 236, Loss: 76.94695091247559\n",
-      "Epoch 237, Loss: 76.74811840057373\n",
-      "Epoch 238, Loss: 76.54174900054932\n",
-      "Epoch 239, Loss: 76.33982515335083\n",
-      "Epoch 240, Loss: 76.13586521148682\n",
-      "Epoch 241, Loss: 75.93749237060547\n",
-      "Epoch 242, Loss: 75.74301242828369\n",
-      "Epoch 243, Loss: 75.54094123840332\n",
-      "Epoch 244, Loss: 75.3494176864624\n",
-      "Epoch 245, Loss: 75.15233421325684\n",
-      "Epoch 246, Loss: 74.95770645141602\n",
-      "Epoch 247, Loss: 74.76380252838135\n",
-      "Epoch 248, Loss: 74.57321357727051\n",
-      "Epoch 249, Loss: 74.38499546051025\n",
-      "Epoch 250, Loss: 74.19686317443848\n",
+      "Epoch 1, Loss: 7710.748245239258\n",
+      "Epoch 2, Loss: 929.7301177978516\n",
+      "Epoch 3, Loss: 544.5105056762695\n",
+      "Epoch 4, Loss: 374.05492782592773\n",
+      "Epoch 5, Loss: 285.55188751220703\n",
+      "Epoch 6, Loss: 230.82619667053223\n",
+      "Epoch 7, Loss: 191.3608913421631\n",
+      "Epoch 8, Loss: 162.43738174438477\n",
+      "Epoch 9, Loss: 140.06568717956543\n",
+      "Epoch 10, Loss: 121.88639545440674\n",
+      "Epoch 11, Loss: 107.5142822265625\n",
+      "Epoch 12, Loss: 95.76922607421875\n",
+      "Epoch 13, Loss: 86.28059673309326\n",
+      "Epoch 14, Loss: 78.33145523071289\n",
+      "Epoch 15, Loss: 71.9775185585022\n",
+      "Epoch 16, Loss: 66.29412603378296\n",
+      "Epoch 17, Loss: 61.23972988128662\n",
+      "Epoch 18, Loss: 56.8019323348999\n",
+      "Epoch 19, Loss: 52.792181968688965\n",
+      "Epoch 20, Loss: 49.207738399505615\n",
+      "Epoch 21, Loss: 45.88220977783203\n",
+      "Epoch 22, Loss: 42.94546365737915\n",
+      "Epoch 23, Loss: 40.18995523452759\n",
+      "Epoch 24, Loss: 37.652278900146484\n",
+      "Epoch 25, Loss: 35.350215435028076\n",
+      "Epoch 26, Loss: 33.180848598480225\n",
+      "Epoch 27, Loss: 31.17438006401062\n",
+      "Epoch 28, Loss: 29.261202096939087\n",
+      "Epoch 29, Loss: 27.48809790611267\n",
+      "Epoch 30, Loss: 25.948073148727417\n",
+      "Epoch 31, Loss: 24.479069709777832\n",
+      "Epoch 32, Loss: 23.181703329086304\n",
+      "Epoch 33, Loss: 22.116490364074707\n",
+      "Epoch 34, Loss: 21.14108633995056\n",
+      "Epoch 35, Loss: 20.169683694839478\n",
+      "Epoch 36, Loss: 19.310741901397705\n",
+      "Epoch 37, Loss: 18.46678626537323\n",
+      "Epoch 38, Loss: 17.618736386299133\n",
+      "Epoch 39, Loss: 16.812995672225952\n",
+      "Epoch 40, Loss: 16.021147847175598\n",
+      "Epoch 41, Loss: 15.490597248077393\n",
+      "Epoch 42, Loss: 14.770788073539734\n",
+      "Epoch 43, Loss: 14.16066563129425\n",
+      "Epoch 44, Loss: 13.591917157173157\n",
+      "Epoch 45, Loss: 13.036315321922302\n",
+      "Epoch 46, Loss: 12.494248747825623\n",
+      "Epoch 47, Loss: 12.031988143920898\n",
+      "Epoch 48, Loss: 11.810864210128784\n",
+      "Epoch 49, Loss: 11.269407153129578\n",
+      "Epoch 50, Loss: 10.906544089317322\n",
+      "Epoch 51, Loss: 10.518525838851929\n",
+      "Epoch 52, Loss: 10.118085384368896\n",
+      "Epoch 53, Loss: 9.72352945804596\n",
+      "Epoch 54, Loss: 9.349195122718811\n",
+      "Epoch 55, Loss: 9.016001522541046\n",
+      "Epoch 56, Loss: 8.7366943359375\n",
+      "Epoch 57, Loss: 8.680127024650574\n",
+      "Epoch 58, Loss: 8.453996121883392\n",
+      "Epoch 59, Loss: 8.199350833892822\n",
+      "Epoch 60, Loss: 7.996649324893951\n",
+      "Epoch 61, Loss: 7.738656103610992\n",
+      "Epoch 62, Loss: 7.488139033317566\n",
+      "Epoch 63, Loss: 7.241581499576569\n",
+      "Epoch 64, Loss: 7.0951069593429565\n",
+      "Epoch 65, Loss: 6.845216870307922\n",
+      "Epoch 66, Loss: 6.657032072544098\n",
+      "Epoch 67, Loss: 6.469990253448486\n",
+      "Epoch 68, Loss: 6.253470957279205\n",
+      "Epoch 69, Loss: 6.071911692619324\n",
+      "Epoch 70, Loss: 6.014991462230682\n",
+      "Epoch 71, Loss: 5.831359803676605\n",
+      "Epoch 72, Loss: 5.724007725715637\n",
+      "Epoch 73, Loss: 5.596436321735382\n",
+      "Epoch 74, Loss: 5.4878018498420715\n",
+      "Epoch 75, Loss: 5.3410831689834595\n",
+      "Epoch 76, Loss: 5.216923654079437\n",
+      "Epoch 77, Loss: 5.28024834394455\n",
+      "Epoch 78, Loss: 5.049155294895172\n",
+      "Epoch 79, Loss: 4.977992653846741\n",
+      "Epoch 80, Loss: 4.83798748254776\n",
+      "Epoch 81, Loss: 4.740262925624847\n",
+      "Epoch 82, Loss: 4.624971151351929\n",
+      "Epoch 83, Loss: 4.661925315856934\n",
+      "Epoch 84, Loss: 4.458498269319534\n",
+      "Epoch 85, Loss: 4.40021938085556\n",
+      "Epoch 86, Loss: 4.320267915725708\n",
+      "Epoch 87, Loss: 4.22625795006752\n",
+      "Epoch 88, Loss: 4.134126126766205\n",
+      "Epoch 89, Loss: 4.086700618267059\n",
+      "Epoch 90, Loss: 3.986404985189438\n",
+      "Epoch 91, Loss: 3.9596570432186127\n",
+      "Epoch 92, Loss: 3.914600431919098\n",
+      "Epoch 93, Loss: 3.796679764986038\n",
+      "Epoch 94, Loss: 3.739291489124298\n",
+      "Epoch 95, Loss: 3.7888976335525513\n",
+      "Epoch 96, Loss: 3.6333232522010803\n",
+      "Epoch 97, Loss: 3.6121875643730164\n",
+      "Epoch 98, Loss: 3.513615518808365\n",
+      "Epoch 99, Loss: 3.47792711853981\n",
+      "Epoch 100, Loss: 3.4128848910331726\n",
       "Finished Training\n"
      ]
     },
     {
      "data": {
-      "image/png": "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",
+      "image/png": "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",
       "text/plain": [
        "<Figure size 1000x600 with 1 Axes>"
       ]
@@ -624,13 +398,13 @@
     "import matplotlib.pyplot as plt\n",
     "\n",
     "# Hyperparameters for regularization\n",
-    "alpha = 1e-4  # Example value, adjust as necessary\n",
+    "alpha = 1e-4  \n",
     "beta = 0.03\n",
     "gamma = 1e-4\n",
     "\n",
     "# Training Loop\n",
-    "num_epochs = 250  # The number of times the entire dataset is passed through the network\n",
-    "epoch_losses = []  # List to store average loss of each epoch\n",
+    "num_epochs = 100  \n",
+    "epoch_losses = [] \n",
     "\n",
     "for epoch in range(num_epochs):\n",
     "    running_loss = 0.0\n",
@@ -648,7 +422,7 @@
     "            total_firing_rate_reg += firing_rate_reg\n",
     "            total_dynamic_reg += dynamic_reg\n",
     "    \n",
-    "        # Compute loss using the last output and include regularization terms:\n",
+    "        # Compute loss using the last output and include regularization terms\n",
     "        loss = criterion(output, targets[:, -1, :])\n",
     "        l2_reg = compute_l2_regularization(model.parameters(), alpha)\n",
     "        rfr_reg = beta * total_firing_rate_reg / inputs.shape[1]  # Average over time steps\n",
@@ -656,6 +430,7 @@
     "    \n",
     "        total_loss = loss + l2_reg + rfr_reg + rj_reg\n",
     "        total_loss.backward()\n",
+    "        torch.nn.utils.clip_grad_norm_(model.parameters(), max_norm=1)\n",
     "        optimizer.step()\n",
     "    \n",
     "        running_loss += total_loss.item()\n",
@@ -678,306 +453,104 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 14,
+   "id": "de475624-9823-4fd4-a591-960795badf82",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import torch\n",
+    "import torch.nn as nn\n",
+    "\n",
+    "class ComplicatedRNN(nn.Module):\n",
+    "    def __init__(self, input_size, hidden_size, output_size, g, h, tau=50):\n",
+    "        super(ComplicatedRNN, self).__init__()\n",
+    "        self.hidden_size = hidden_size\n",
+    "        self.tau = tau  # Time constant\n",
+    "\n",
+    "        # Modified weight initialization for a more chaotic regime (g >> 1)\n",
+    "        # Adjust the scale factor as per the specific requirements of the model\n",
+    "        self.J = nn.Parameter(torch.randn(hidden_size, hidden_size) * (g / torch.sqrt(torch.tensor(hidden_size, dtype=torch.float))))\n",
+    "        self.B = nn.Parameter(torch.randn(hidden_size, input_size) * (h / torch.sqrt(torch.tensor(input_size, dtype=torch.float)))) \n",
+    "        self.w = nn.Parameter(torch.zeros(output_size, hidden_size))\n",
+    "        self.bx = nn.Parameter(torch.zeros(hidden_size))\n",
+    "        self.bz = nn.Parameter(torch.zeros(output_size))\n",
+    "\n",
+    "        # Nonlinearity remains the same\n",
+    "        self.nonlinearity = torch.tanh\n",
+    "    \n",
+    "    def forward(self, x, hidden):\n",
+    "        timestep = self.tau / 10  # Timestep for Euler integration\n",
+    "        for _ in range(int(1 / timestep)):  # Adjust the range for simulation duration\n",
+    "            hidden_update = torch.matmul(self.J, hidden.T)\n",
+    "            input_update = torch.matmul(self.B, x.T)\n",
+    "            new_hidden = self.nonlinearity(hidden_update + input_update + self.bx.unsqueeze(1))\n",
+    "            new_hidden = new_hidden.T\n",
+    "\n",
+    "            # Euler integration for continuous-time update\n",
+    "            hidden = hidden + (timestep / self.tau) * (-hidden + new_hidden)\n",
+    "        \n",
+    "        output = torch.matmul(self.w, hidden.T) + self.bz.unsqueeze(1)\n",
+    "        output = output.T\n",
+    "    \n",
+    "        return output, hidden\n",
+    "\n",
+    "    def init_hidden(self):\n",
+    "        # Initialize hidden state with an additional batch dimension\n",
+    "        return torch.zeros(1, self.hidden_size)\n",
+    "\n",
+    "input_size = 7\n",
+    "hidden_size = 300\n",
+    "output_size = 2 # Number of muscles\n",
+    "g = 10.0 # Significantly larger g value for complicated model\n",
+    "h = 1.0 # h value remains the same\n",
+    "\n",
+    "complicated_model = ComplicatedRNN(input_size, hidden_size, output_size, g, h)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
    "id": "21dd9a5b-0e80-4464-aa8e-9ec54d225646",
    "metadata": {},
    "outputs": [
     {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Epoch 1, Loss: 0.6844498887658119\n",
-      "Epoch 2, Loss: 0.7684311643242836\n",
-      "Epoch 3, Loss: 0.7107953131198883\n",
-      "Epoch 4, Loss: 0.7505717277526855\n",
-      "Epoch 5, Loss: 0.7358348220586777\n",
-      "Epoch 6, Loss: 0.7848915904760361\n",
-      "Epoch 7, Loss: 0.6719830706715584\n",
-      "Epoch 8, Loss: 0.6876146793365479\n",
-      "Epoch 9, Loss: 0.8279480189085007\n",
-      "Epoch 10, Loss: 0.723111629486084\n",
-      "Epoch 11, Loss: 0.6876197457313538\n",
-      "Epoch 12, Loss: 0.7015645802021027\n",
-      "Epoch 13, Loss: 0.6643376275897026\n",
-      "Epoch 14, Loss: 0.7549911737442017\n",
-      "Epoch 15, Loss: 0.729726567864418\n",
-      "Epoch 16, Loss: 0.7364737838506699\n",
-      "Epoch 17, Loss: 0.6534652635455132\n",
-      "Epoch 18, Loss: 0.7946727126836777\n",
-      "Epoch 19, Loss: 0.7263908535242081\n",
-      "Epoch 20, Loss: 0.689399003982544\n",
-      "Epoch 21, Loss: 0.779498927295208\n",
-      "Epoch 22, Loss: 0.7836204171180725\n",
-      "Epoch 23, Loss: 0.7634584605693817\n",
-      "Epoch 24, Loss: 0.6947921067476273\n",
-      "Epoch 25, Loss: 0.6949298605322838\n",
-      "Epoch 26, Loss: 0.6603551581501961\n",
-      "Epoch 27, Loss: 0.717332735657692\n",
-      "Epoch 28, Loss: 0.7822877615690231\n",
-      "Epoch 29, Loss: 0.7155746817588806\n",
-      "Epoch 30, Loss: 0.7123168408870697\n",
-      "Epoch 31, Loss: 0.6959493309259415\n",
-      "Epoch 32, Loss: 0.6581716611981392\n",
-      "Epoch 33, Loss: 0.6910743713378906\n",
-      "Epoch 34, Loss: 0.7263199090957642\n",
-      "Epoch 35, Loss: 0.7495604008436203\n",
-      "Epoch 36, Loss: 0.6844918951392174\n",
-      "Epoch 37, Loss: 0.7002900391817093\n",
-      "Epoch 38, Loss: 0.7237478345632553\n",
-      "Epoch 39, Loss: 0.6796517595648766\n",
-      "Epoch 40, Loss: 0.7289071381092072\n",
-      "Epoch 41, Loss: 0.7311867475509644\n",
-      "Epoch 42, Loss: 0.693147674202919\n",
-      "Epoch 43, Loss: 0.764416828751564\n",
-      "Epoch 44, Loss: 0.7491090595722198\n",
-      "Epoch 45, Loss: 0.7244654446840286\n",
-      "Epoch 46, Loss: 0.7532452046871185\n",
-      "Epoch 47, Loss: 0.7225791066884995\n",
-      "Epoch 48, Loss: 0.7547371238470078\n",
-      "Epoch 49, Loss: 0.7187787890434265\n",
-      "Epoch 50, Loss: 0.6534120589494705\n",
-      "Epoch 51, Loss: 0.7539178133010864\n",
-      "Epoch 52, Loss: 0.7006526738405228\n",
-      "Epoch 53, Loss: 0.7990596666932106\n",
-      "Epoch 54, Loss: 0.7585810422897339\n",
-      "Epoch 55, Loss: 0.7597721815109253\n",
-      "Epoch 56, Loss: 0.7336041480302811\n",
-      "Epoch 57, Loss: 0.7644808888435364\n",
-      "Epoch 58, Loss: 0.7267809361219406\n",
-      "Epoch 59, Loss: 0.749725416302681\n",
-      "Epoch 60, Loss: 0.7312611639499664\n",
-      "Epoch 61, Loss: 0.7665525525808334\n",
-      "Epoch 62, Loss: 0.7100191116333008\n",
-      "Epoch 63, Loss: 0.7326457500457764\n",
-      "Epoch 64, Loss: 0.6718179658055305\n",
-      "Epoch 65, Loss: 0.6593071967363358\n",
-      "Epoch 66, Loss: 0.7239373922348022\n",
-      "Epoch 67, Loss: 0.6852187439799309\n",
-      "Epoch 68, Loss: 0.655521497130394\n",
-      "Epoch 69, Loss: 0.6690862253308296\n",
-      "Epoch 70, Loss: 0.7250047773122787\n",
-      "Epoch 71, Loss: 0.7226709648966789\n",
-      "Epoch 72, Loss: 0.7291943430900574\n",
-      "Epoch 73, Loss: 0.6971108764410019\n",
-      "Epoch 74, Loss: 0.7312247008085251\n",
-      "Epoch 75, Loss: 0.7304578572511673\n",
-      "Epoch 76, Loss: 0.7089480981230736\n",
-      "Epoch 77, Loss: 0.7299647480249405\n",
-      "Epoch 78, Loss: 0.7044151574373245\n",
-      "Epoch 79, Loss: 0.7867395579814911\n",
-      "Epoch 80, Loss: 0.7612255215644836\n",
-      "Epoch 81, Loss: 0.6921402961015701\n",
-      "Epoch 82, Loss: 0.7548394575715065\n",
-      "Epoch 83, Loss: 0.6940535008907318\n",
-      "Epoch 84, Loss: 0.7071485370397568\n",
-      "Epoch 85, Loss: 0.7580607980489731\n",
-      "Epoch 86, Loss: 0.7915467470884323\n",
-      "Epoch 87, Loss: 0.7180616408586502\n",
-      "Epoch 88, Loss: 0.7307089865207672\n",
-      "Epoch 89, Loss: 0.85804083943367\n",
-      "Epoch 90, Loss: 0.7980050295591354\n",
-      "Epoch 91, Loss: 0.6888296902179718\n",
-      "Epoch 92, Loss: 0.721487745642662\n",
-      "Epoch 93, Loss: 0.7879800945520401\n",
-      "Epoch 94, Loss: 0.7532758265733719\n",
-      "Epoch 95, Loss: 0.7829757034778595\n",
-      "Epoch 96, Loss: 0.6644150540232658\n",
-      "Epoch 97, Loss: 0.7668898403644562\n",
-      "Epoch 98, Loss: 0.724658876657486\n",
-      "Epoch 99, Loss: 0.6756115183234215\n",
-      "Epoch 100, Loss: 0.7869917452335358\n",
-      "Epoch 101, Loss: 0.7682904899120331\n",
-      "Epoch 102, Loss: 0.6664897501468658\n",
-      "Epoch 103, Loss: 0.7940731942653656\n",
-      "Epoch 104, Loss: 0.725495845079422\n",
-      "Epoch 105, Loss: 0.6645809561014175\n",
-      "Epoch 106, Loss: 0.7042224854230881\n",
-      "Epoch 107, Loss: 0.6973975896835327\n",
-      "Epoch 108, Loss: 0.8253570646047592\n",
-      "Epoch 109, Loss: 0.7656873166561127\n",
-      "Epoch 110, Loss: 0.6935658752918243\n",
-      "Epoch 111, Loss: 0.7230131179094315\n",
-      "Epoch 112, Loss: 0.7237074673175812\n",
-      "Epoch 113, Loss: 0.7603471279144287\n",
-      "Epoch 114, Loss: 0.6900924444198608\n",
-      "Epoch 115, Loss: 0.7134169638156891\n",
-      "Epoch 116, Loss: 0.661640115082264\n",
-      "Epoch 117, Loss: 0.6917726397514343\n",
-      "Epoch 118, Loss: 0.7192181795835495\n",
-      "Epoch 119, Loss: 0.6977423429489136\n",
-      "Epoch 120, Loss: 0.7274277359247208\n",
-      "Epoch 121, Loss: 0.8480104431509972\n",
-      "Epoch 122, Loss: 0.6933386772871017\n",
-      "Epoch 123, Loss: 0.7541245073080063\n",
-      "Epoch 124, Loss: 0.7055882662534714\n",
-      "Epoch 125, Loss: 0.6970310211181641\n",
-      "Epoch 126, Loss: 0.6998537927865982\n",
-      "Epoch 127, Loss: 0.8278564959764481\n",
-      "Epoch 128, Loss: 0.7816721051931381\n",
-      "Epoch 129, Loss: 0.7330120950937271\n",
-      "Epoch 130, Loss: 0.6869750171899796\n",
-      "Epoch 131, Loss: 0.7579750418663025\n",
-      "Epoch 132, Loss: 0.7600715532898903\n",
-      "Epoch 133, Loss: 0.7344505786895752\n",
-      "Epoch 134, Loss: 0.7785018235445023\n",
-      "Epoch 135, Loss: 0.7756278067827225\n",
-      "Epoch 136, Loss: 0.747446708381176\n",
-      "Epoch 137, Loss: 0.760254755616188\n",
-      "Epoch 138, Loss: 0.6822677329182625\n",
-      "Epoch 139, Loss: 0.68813157081604\n",
-      "Epoch 140, Loss: 0.6923274248838425\n",
-      "Epoch 141, Loss: 0.7932397276163101\n",
-      "Epoch 142, Loss: 0.7589260041713715\n",
-      "Epoch 143, Loss: 0.7555321753025055\n",
-      "Epoch 144, Loss: 0.7681937515735626\n",
-      "Epoch 145, Loss: 0.7454390600323677\n",
-      "Epoch 146, Loss: 0.6535535082221031\n",
-      "Epoch 147, Loss: 0.7183700203895569\n",
-      "Epoch 148, Loss: 0.6930307149887085\n",
-      "Epoch 149, Loss: 0.7217278778553009\n",
-      "Epoch 150, Loss: 0.657049223780632\n",
-      "Epoch 151, Loss: 0.6653405502438545\n",
-      "Epoch 152, Loss: 0.7023345082998276\n",
-      "Epoch 153, Loss: 0.6768929362297058\n",
-      "Epoch 154, Loss: 0.6806328594684601\n",
-      "Epoch 155, Loss: 0.6962950825691223\n",
-      "Epoch 156, Loss: 0.7654906362295151\n",
-      "Epoch 157, Loss: 0.7172591686248779\n",
-      "Epoch 158, Loss: 0.691572293639183\n",
-      "Epoch 159, Loss: 0.7255141139030457\n",
-      "Epoch 160, Loss: 0.739932045340538\n",
-      "Epoch 161, Loss: 0.6965528130531311\n",
-      "Epoch 162, Loss: 0.8295057117938995\n",
-      "Epoch 163, Loss: 0.7169296741485596\n",
-      "Epoch 164, Loss: 0.7281256467103958\n",
-      "Epoch 165, Loss: 0.6844639703631401\n",
-      "Epoch 166, Loss: 0.8493780717253685\n",
-      "Epoch 167, Loss: 0.7219818234443665\n",
-      "Epoch 168, Loss: 0.7157859653234482\n",
-      "Epoch 169, Loss: 0.6883779615163803\n",
-      "Epoch 170, Loss: 0.6922315657138824\n",
-      "Epoch 171, Loss: 0.7254915237426758\n",
-      "Epoch 172, Loss: 0.7519825547933578\n",
-      "Epoch 173, Loss: 0.7273001819849014\n",
-      "Epoch 174, Loss: 0.7210886031389236\n",
-      "Epoch 175, Loss: 0.7733265459537506\n",
-      "Epoch 176, Loss: 0.6948503255844116\n",
-      "Epoch 177, Loss: 0.7673401683568954\n",
-      "Epoch 178, Loss: 0.71981480717659\n",
-      "Epoch 179, Loss: 0.656543493270874\n",
-      "Epoch 180, Loss: 0.6616334021091461\n",
-      "Epoch 181, Loss: 0.7971215546131134\n",
-      "Epoch 182, Loss: 0.7208173722028732\n",
-      "Epoch 183, Loss: 0.7703881710767746\n",
-      "Epoch 184, Loss: 0.6653950288891792\n",
-      "Epoch 185, Loss: 0.7661297172307968\n",
-      "Epoch 186, Loss: 0.6593877449631691\n",
-      "Epoch 187, Loss: 0.7348640412092209\n",
-      "Epoch 188, Loss: 0.7650734186172485\n",
-      "Epoch 189, Loss: 0.7048304527997971\n",
-      "Epoch 190, Loss: 0.6754415482282639\n",
-      "Epoch 191, Loss: 0.703193336725235\n",
-      "Epoch 192, Loss: 0.686901330947876\n",
-      "Epoch 193, Loss: 0.6849369332194328\n",
-      "Epoch 194, Loss: 0.6888349801301956\n",
-      "Epoch 195, Loss: 0.6886181235313416\n",
-      "Epoch 196, Loss: 0.7536339610815048\n",
-      "Epoch 197, Loss: 0.7633043080568314\n",
-      "Epoch 198, Loss: 0.6748651936650276\n",
-      "Epoch 199, Loss: 0.6924779564142227\n",
-      "Epoch 200, Loss: 0.7282437533140182\n",
-      "Epoch 201, Loss: 0.7095600813627243\n",
-      "Epoch 202, Loss: 0.762402281165123\n",
-      "Epoch 203, Loss: 0.8013734295964241\n",
-      "Epoch 204, Loss: 0.6958517134189606\n",
-      "Epoch 205, Loss: 0.7107598334550858\n",
-      "Epoch 206, Loss: 0.7474528774619102\n",
-      "Epoch 207, Loss: 0.6724739298224449\n",
-      "Epoch 208, Loss: 0.655377633869648\n",
-      "Epoch 209, Loss: 0.7196144163608551\n",
-      "Epoch 210, Loss: 0.6909883618354797\n",
-      "Epoch 211, Loss: 0.6644586697220802\n",
-      "Epoch 212, Loss: 0.6937383860349655\n",
-      "Epoch 213, Loss: 0.737950399518013\n",
-      "Epoch 214, Loss: 0.7682736814022064\n",
-      "Epoch 215, Loss: 0.7689143121242523\n",
-      "Epoch 216, Loss: 0.6645479425787926\n",
-      "Epoch 217, Loss: 0.6898463219404221\n",
-      "Epoch 218, Loss: 0.7291360199451447\n",
-      "Epoch 219, Loss: 0.7570148557424545\n",
-      "Epoch 220, Loss: 0.6994991302490234\n",
-      "Epoch 221, Loss: 0.7194970101118088\n",
-      "Epoch 222, Loss: 0.6547707840800285\n",
-      "Epoch 223, Loss: 0.6512698009610176\n",
-      "Epoch 224, Loss: 0.7228247225284576\n",
-      "Epoch 225, Loss: 0.6615516021847725\n",
-      "Epoch 226, Loss: 0.7245751693844795\n",
-      "Epoch 227, Loss: 0.7196688055992126\n",
-      "Epoch 228, Loss: 0.6989023238420486\n",
-      "Epoch 229, Loss: 0.7249975055456161\n",
-      "Epoch 230, Loss: 0.7537133395671844\n",
-      "Epoch 231, Loss: 0.7554620206356049\n",
-      "Epoch 232, Loss: 0.7619994282722473\n",
-      "Epoch 233, Loss: 0.669164702296257\n",
-      "Epoch 234, Loss: 0.7237188890576363\n",
-      "Epoch 235, Loss: 0.6984163671731949\n",
-      "Epoch 236, Loss: 0.7292763441801071\n",
-      "Epoch 237, Loss: 0.6603463515639305\n",
-      "Epoch 238, Loss: 0.7101467251777649\n",
-      "Epoch 239, Loss: 0.7569788843393326\n",
-      "Epoch 240, Loss: 0.7317604124546051\n",
-      "Epoch 241, Loss: 0.7649162411689758\n",
-      "Epoch 242, Loss: 0.710281103849411\n",
-      "Epoch 243, Loss: 0.6967487782239914\n",
-      "Epoch 244, Loss: 0.6590758934617043\n",
-      "Epoch 245, Loss: 0.7105749249458313\n",
-      "Epoch 246, Loss: 0.7403308898210526\n",
-      "Epoch 247, Loss: 0.695420891046524\n",
-      "Epoch 248, Loss: 0.7680528312921524\n",
-      "Epoch 249, Loss: 0.6991064995527267\n",
-      "Epoch 250, Loss: 0.6990882903337479\n",
-      "Finished Training\n"
+     "ename": "NameError",
+     "evalue": "name 'optimizer2' is not defined",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[15], line 11\u001b[0m\n\u001b[1;32m      8\u001b[0m running_loss \u001b[38;5;241m=\u001b[39m \u001b[38;5;241m0.0\u001b[39m\n\u001b[1;32m     10\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m inputs, targets \u001b[38;5;129;01min\u001b[39;00m train_loader:\n\u001b[0;32m---> 11\u001b[0m     \u001b[43moptimizer2\u001b[49m\u001b[38;5;241m.\u001b[39mzero_grad()\n\u001b[1;32m     12\u001b[0m     batch_size \u001b[38;5;241m=\u001b[39m inputs\u001b[38;5;241m.\u001b[39msize(\u001b[38;5;241m0\u001b[39m)\n\u001b[1;32m     13\u001b[0m     h \u001b[38;5;241m=\u001b[39m complicated_model\u001b[38;5;241m.\u001b[39minit_hidden(batch_size)  \u001b[38;5;66;03m# Initialize hidden state\u001b[39;00m\n",
+      "\u001b[0;31mNameError\u001b[0m: name 'optimizer2' is not defined"
      ]
-    },
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 1000x600 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
     }
    ],
    "source": [
     "import matplotlib.pyplot as plt\n",
     "\n",
     "# Training Loop\n",
-    "num_epochs = 250  # The number of times the entire dataset is passed through the network\n",
-    "epoch_losses = []  # List to store average loss of each epoch\n",
+    "num_epochs = 250  # The number of epochs\n",
+    "epoch_losses = []  # To store average loss per epoch\n",
     "\n",
-    "# Loop over the dataset multiple times\n",
     "for epoch in range(num_epochs):\n",
-    "    running_loss = 0.0  # Initialize loss for this epoch\n",
+    "    running_loss = 0.0\n",
     "\n",
-    "    # Iterate over the training data loader which provides batches of inputs and targets\n",
     "    for inputs, targets in train_loader:\n",
-    "        optimizer.zero_grad()  # Zero the parameter gradients to prevent accumulation\n",
+    "        optimizer2.zero_grad()\n",
+    "        batch_size = inputs.size(0)\n",
+    "        h = complicated_model.init_hidden(batch_size)  # Initialize hidden state\n",
     "\n",
-    "        batch_size = inputs.size(0)  # Get the batch size from the input tensor\n",
-    "        h = model.init_hidden(batch_size)  # Initialize hidden state with the current batch size\n",
+    "        total_loss = 0.0  # Accumulate loss over time steps\n",
     "\n",
-    "        # Process each time step in the input sequence\n",
-    "        for t in range(inputs.shape[1]):  # Iterate over time steps \n",
-    "            output, h = complicated_model(inputs[:, t, :], h)  # Get output and updated hidden state\n",
+    "        for t in range(inputs.shape[1]):\n",
+    "            output, h = complicated_model(inputs[:, t, :], h)\n",
+    "            loss = criterion(output, targets[:, t, :])  # Compute loss at each time step\n",
+    "            total_loss += loss\n",
     "\n",
-    "        # Compute loss using the last output (if your task is many-to-one)\n",
-    "        loss = criterion(output, targets[:, -1, :])\n",
-    "        loss.backward()\n",
-    "        optimizer.step()\n",
+    "        total_loss.backward()  # Backpropagation on the accumulated loss\n",
+    "        optimizer2.step()\n",
     "\n",
-    "        running_loss += loss.item()\n",
+    "        running_loss += total_loss.item()\n",
     "\n",
     "    avg_loss = running_loss / len(train_loader)\n",
     "    epoch_losses.append(avg_loss)\n",
@@ -992,7 +565,7 @@
     "plt.ylabel('Loss')\n",
     "plt.title('Training Loss Over Epochs')\n",
     "plt.legend()\n",
-    "plt.show()"
+    "plt.show()\n"
    ]
   },
   {
@@ -1200,7 +773,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.5"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,
diff --git a/tutorials/W1D1_Generalization/condsForSimJ2moMuscles.mat b/tutorials/W1D1_Generalization/condsForSimJ2moMuscles.mat
new file mode 100644
index 000000000..a4594c78d
Binary files /dev/null and b/tutorials/W1D1_Generalization/condsForSimJ2moMuscles.mat differ