machinelearning

Machine learning code
git clone git://git.laack.co/machinelearning.git
Log | Files | Refs

Sigmoid.ipynb (20682B)


      1 {
      2  "cells": [
      3   {
      4    "cell_type": "code",
      5    "execution_count": 45,
      6    "metadata": {},
      7    "outputs": [
      8     {
      9      "data": {
     10       "text/plain": [
     11        "[<matplotlib.lines.Line2D at 0x7fe42672a510>]"
     12       ]
     13      },
     14      "execution_count": 45,
     15      "metadata": {},
     16      "output_type": "execute_result"
     17     },
     18     {
     19      "data": {
     20       "image/png": "iVBORw0KGgoAAAANSUhEUgAAAiMAAAGdCAYAAADAAnMpAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguNCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8fJSN1AAAACXBIWXMAAA9hAAAPYQGoP6dpAAA12UlEQVR4nO3deXhV1b3/8U8GkjAlgJGEIRIRRShIGCSCKLfXVLSQaqvXAL2COF0tpUBwAEEQsYKKiK20tFzEtgqJ4CyItii/Xm2UMtiqgAVkEk0E0UzEHDhZvz9Oc+RIEs7e2Wd+v57nPDU7a+3z3RxCPl177bXijDFGAAAAIRIf6gIAAEBsI4wAAICQIowAAICQIowAAICQIowAAICQIowAAICQIowAAICQIowAAICQSgx1Af6oq6vTZ599prZt2youLi7U5QAAAD8YY1RZWanOnTsrPr7x8Y+ICCOfffaZsrKyQl0GAACw4eDBg+ratWuj34+IMNK2bVtJnotJTU0NcTUAAMAfFRUVysrK8v4eb0xEhJH6WzOpqamEEQAAIszpplgwgRUAAIQUYQQAAIQUYQQAAIQUYQQAAIQUYQQAAIQUYQQAAIQUYQQAAISU5TDy17/+Vfn5+ercubPi4uL04osvnrbPxo0bNWDAACUnJ6tHjx566qmnbJQKAACikeUwUl1drX79+mnJkiV+td+7d69Gjhyp73//+3r//fc1ZcoU3XzzzXr99dctFwsAAJzjckmLF0uTJnn+1+UKTR1xxhhju3NcnF544QVdffXVjba5++67tXbtWn344YfeY6NHj9bXX3+t9evX+/U+FRUVSktLU3l5OSuwAgAgye2WXntNmjlT+ugjz9fNFR8vTZsmPfxw888l+f/7O+BzRkpKSpSXl+dzbMSIESopKWm0T21trSoqKnxeAABEM7dbeuklqXt3KS7u9K/ERCk/X/rnP50JIpJUVyc98oh0113OnM9fAQ8jpaWlysjI8DmWkZGhiooK1dTUNNhn/vz5SktL877YsRcAEMlqaqQbb5Rat246XFx9tbR3b6irlRYuDO4tm7B8mmbGjBkqLy/3vg4ePBjqkgAAaFRNjXTzzVK7dg0HjVatpBUrpGPHQl2pf4yRfvWr4L1fwMNIZmamysrKfI6VlZUpNTVVLVu2bLBPcnKyd4deduoFAIQDl0tasEDq2rXhsLF8uVReHuoqnfPSS8F7r8RAv8GQIUO0bt06n2N//vOfNWTIkEC/NQAAlrlcntsUixZJX34Z6mpCx/7jLdZZDiNVVVXavXu39+u9e/fq/fffV4cOHXTWWWdpxowZOnTokP74xz9Kkm677TY98cQTuuuuu3TjjTfqzTff1LPPPqu1a9c6dxUAANhQU+N5rHXNmuga1XBCEw/KOs5yGNm8ebO+//3ve78uLCyUJI0fP15PPfWUPv/8cx04cMD7/bPPPltr167V1KlT9fjjj6tr16763//9X40YMcKB8gEA8I/L5RnteOIJ6dChUFcT3uLipF/8Iojv15x1RoKFdUYAAFbV1EgTJ0rFxZEzcTRc3HmnM2uN+Pv7O+BzRgAACAbChzOcCiJWEEYAABGJ2y7OSEqSOnWSbr9dmjrV83WwEUYAABGjfvTjT3+STpwIdTWhFxcntWkjXXqpVFTk+e9IRBgBAIS1qippzBhp7drgPm4aCvHxnkBx3XWeRccaWY4r6hBGAABhpz6AvPpqqCtxTlKS1Lu39OCD0uWXSwkJoa4ofBBGAABhof4WzFNPReYISDjMvYhUhBEAQMjUr3Z6333S8eOhrub0EhM9+8/8+MfS44/Hzm2UQCOMAACCrqpKuuCC8NihtiEJCVJ6ujR5sjRtGqMcgRaWu/YCAKJP/UZzSUlS27bhE0RatJB69JBeecXzhI4xnv8tLZVmzCCIBAMjIwCAgKqpkQYPlj78MNSVeJ5W6dCB2yzhhjACAAiIqirpnHOkL74IXQ0JCdLZZ0uPPSZdeSVPsIQrwggAwFFVVVKXLlJFRWjePyeHx2cjDWEEAOCIUIWQtm2l0aO57RLJCCMAgGYpL5c6dw7u5nQ9enDrJZoQRgAAtlRVSRkZwQsh554r/f3vUlpacN4PwcOjvQAAS2pqpDPP9NweCXQQyc6W1q3zPGr7r38RRKIVIyMAAL+4XJ7JoTt2BPZ90tOlP/6RCaixhJERAECT3G7PuhzJyYELInFxnidgamulw4eZCxJrGBkBADTqmWek//7vwJ0/I0P6+GNuv8Q6wggA4BQul2cH2qNHA3P+sWOlFStYah0e3KYBAPiYMsVzS8bpIJKQ8O3+L888QxDBtxgZAQBI8oyGnHGG55FdJ7Vo4ZkHwq0YNIaREQCIcW63dM01ntEQJ4NIq1bS1197Qg5BBE1hZAQAYtizz0oFBc6eMyXFMxLSpo2z50X0YmQEAGLUqFHOB5Gnn/YsikYQgRWMjABAjHG7PXNDysudO+ePfyytXs3aILCHkREAiCHPPislJjoXRIYN8yxU9vzzBBHYx8gIAMSIUaOktWudOVfnztLevTyeC2cQRgAgyjl9W2blSmnMGGfOBUjcpgGAqObkbZmLLvIsWEYQgdMYGQGAKJWfL736avPPk5AgVVZKLVs2/1xAQxgZAYAodPbZzgSRiRM9oyEEEQQSIyMAEGXatm3+SqqtWklffcUEVQQHIyMAECVcLs8tleYGkZEjpepqggiChzACAFFg2jTP3jJ1dc07T1GRM7d3ACu4TQMAEW7QIGnLluadIzVVOnqUhcsQGoyMAEAE6969+UFk0iTPo78EEYQKIyMAEKHOPlvat89+//h4z6Z2zA1BqDEyAgARKDu7eUGkQwfPyqwEEYQDwggARJgzz5T277ffv39/6csvnasHaC7CCABEkLZtpSNH7PefPFnautW5egAnMGcEACJEmzae9T/sevZZ6b/+y7l6AKcQRgAgArRuLR07Zq9vSopnITSelkG44jYNAIS5lBT7QaRbN88TMwQRhDPCCACEsdatpdpae33792/eEzdAsBBGACBMtWljf0RkwAAmqiJyEEYAIAy1bWt/suqAAc1flRUIJsIIAISZ9HT7O++OGkUQQeQhjABAGDn7bPsLkk2ZIr3yiqPlAEFBGAGAMDFggP0Jp9OmSY895mg5QNCwzggAhIGBA6Vt2+z1LSqSCgqcrQcIJkZGACDE8vPtP/lCEEE0IIwAQAgVFkqvvmqv7x13EEQQHQgjABAiq1fbn+dRWCg98oiz9QChQhgBgBBwu6XrrrPXd8oU6dFHHS0HCCnCCACEQEqKvX6jRvHUDKIPYQQAgiw9XTpxwnq/gQNZRwTRyVYYWbJkibKzs5WSkqLc3Fxt2rSpyfaLFy9Wz5491bJlS2VlZWnq1Kn65ptvbBUMAJGsf397i5r17y9t3ux8PUA4sBxGiouLVVhYqDlz5mjr1q3q16+fRowYoS+++KLB9itXrtT06dM1Z84c7dixQ8uXL1dxcbHuueeeZhcPAJFk0CDp/fet98vOZtM7RDfLYWTRokW65ZZbNGHCBPXu3VtLly5Vq1at9OSTTzbY/m9/+5suvvhijR07VtnZ2br88ss1ZsyY046mAEA0KSy0t2dMerq0d6/z9QDhxFIYcblc2rJli/Ly8r49QXy88vLyVFJS0mCfoUOHasuWLd7w8cknn2jdunX64Q9/2Oj71NbWqqKiwucFAJHK5bI36bR1a+nwYefrAcKNpeXgjxw5IrfbrYyMDJ/jGRkZ2rlzZ4N9xo4dqyNHjmjYsGEyxujEiRO67bbbmrxNM3/+fM2dO9dKaQAQttq0sd4nIcH+zr1ApAn40zQbN27Ugw8+qN/85jfaunWrnn/+ea1du1bz5s1rtM+MGTNUXl7ufR08eDDQZQJAQGRnS8ePW+9XW+t4KUDYsjQykp6eroSEBJWVlfkcLysrU2ZmZoN97r33Xl1//fW6+eabJUl9+/ZVdXW1br31Vs2cOVPx8afmoeTkZCUnJ1spDQDCTn6+tH+/9X7FxZ6RESBWWBoZSUpK0sCBA7Vhwwbvsbq6Om3YsEFDhgxpsM+xY8dOCRwJ//4pM8ZYrRcAIkJxsb09Z/Lz7a/MCkQqSyMjklRYWKjx48dr0KBBGjx4sBYvXqzq6mpNmDBBkjRu3Dh16dJF8+fPlyTl5+dr0aJF6t+/v3Jzc7V7927de++9ys/P94YSAIgmbrc0erT1fgMGSC+/7Hw9QLizHEYKCgp0+PBhzZ49W6WlpcrJydH69eu9k1oPHDjgMxIya9YsxcXFadasWTp06JDOPPNM5efn65e//KVzVwEAYaRLF+t9unWz9+gvEA3iTATcK6moqFBaWprKy8uVmpoa6nIAoFH5+dZvzyQlMWEV0cnf39/sTQMADrE7T6Sy0vlagEhCGAEAB9idJ1JY6BkZAWIZYQQAHNChg/U+AwZIjz7qfC1ApCGMAEAzDRwoWd21IjWVCatAPcIIADTDqlX2dtQ9etT5WoBIRRgBAJvcbmnsWOv9Vq5khVXgZIQRALCpVy/rfQYOlMaMcb4WIJIRRgDAhlWrpF27rPVJS5M2bw5MPUAkI4wAgEV2b898+aXztQDRgDACABbZWe6dnXiBxhFGAMCC/HyprMxan1Gj2IkXaAphBAD8ZGe59w4dpFdeCUw9QLQgjACAH+wu9/75587XAkQbwggA+MHOY7xTprDvDOAPwggAnIadx3jPOEN67LHA1ANEG8IIADTB7mO8n33mfC1AtCKMAEAThg2z3qewkNszgBWEEQBoRE2N9O671voMHCg9+mhg6gGiFWEEABrRsaO19u3bs9w7YAdhBAAaMGWKVFVlrU9paUBKAaIeYQQAvsPlkh5/3FofHuMF7COMAMB3ZGZaa89jvEDzEEYA4CRTpkhffWWtD4/xAs1DGAGAf7Nze+aaa7g9AzQXYQQA/i0nx3qf4mLHywBiDmEEAOQJFTt2WOuzcqWUkBCYeoBYQhgBEPPs7Mh73nnSmDGBqQeINYQRADHPzpLv27c7XwcQqwgjAGKanSXfuT0DOIswAiCmWV3yvWtXbs8ATiOMAIhZdpZ837MnIKUAMY0wAiAmseQ7ED4IIwBiktU1RVjyHQgcwgiAmGNnTRGWfAcChzACIKa43dYnoLLkOxBYhBEAMeW++yRjrPVhyXcgsAgjAGKG2y098IC1PqwpAgQeYQRAzOjVy1p71hQBgoMwAiAmrFol7dplrQ9rigDBQRgBEPXcbmnsWGt9mLQKBA9hBEDUu+8+a+3j4pi0CgQTYQRAVLMzafWZZ5i0CgQTYQRAVBs2zFr7885j0ioQbIQRAFGrpkZ6911rfbZvD0wtABpHGAEQtc46y1r7mTO5PQOEAmEEQFRatUo6csT/9vHx0ty5gasHQOMIIwCijp1HeZ9+mlERIFQIIwCijtVHeVlpFQgtwgiAqGLnUV5WWgVCizACIKpYfZSXlVaB0COMAIgaxcXWH+VlpVUg9AgjAKKCnUmrPMoLhAfCCICoMHeuVFfnf3se5QXCB2EEQMRzu6V586z14VFeIHwQRgBEvNGjrbXnUV4gvBBGAEQ0l0tas8ZaHx7lBcILYQRARPvBD6y1Hz6cR3mBcGMrjCxZskTZ2dlKSUlRbm6uNm3a1GT7r7/+WhMnTlSnTp2UnJys8847T+vWrbNVMADUc7mkv/7VWp833ghMLQDsS7Taobi4WIWFhVq6dKlyc3O1ePFijRgxQh9//LE6dux4SnuXy6Uf/OAH6tixo9asWaMuXbpo//79ateunRP1A4hh/ftba3/ttYyKAOEozhhjrHTIzc3VhRdeqCeeeEKSVFdXp6ysLE2aNEnTp08/pf3SpUv1yCOPaOfOnWrRooWtIisqKpSWlqby8nKlpqbaOgeA6FJTI7Vq5X/7uDjp+HGeoAGCyd/f35Zu07hcLm3ZskV5eXnfniA+Xnl5eSopKWmwz8svv6whQ4Zo4sSJysjIUJ8+ffTggw/K7XY3+j61tbWqqKjweQHAyXr1stZ+1iyCCBCuLIWRI0eOyO12KyMjw+d4RkaGSktLG+zzySefaM2aNXK73Vq3bp3uvfdePfroo3qgiZ2s5s+fr7S0NO8rKyvLSpkAolxxsbR/v//tExOlOXMCVw+A5gn40zR1dXXq2LGjfv/732vgwIEqKCjQzJkztXTp0kb7zJgxQ+Xl5d7XwYMHA10mgAhhZ9n3Z55hVAQIZ5YmsKanpyshIUFlZWU+x8vKypSZmdlgn06dOqlFixZKOOlfgl69eqm0tFQul0tJDcwmS05OVnJyspXSAMQIq8u+9+4tXXdd4OoB0HyWRkaSkpI0cOBAbdiwwXusrq5OGzZs0JAhQxrsc/HFF2v37t2qO+lfj3/961/q1KlTg0EEABpjZ9n3bdsCUwsA51i+TVNYWKhly5bpD3/4g3bs2KHbb79d1dXVmjBhgiRp3LhxmjFjhrf97bffrqNHj2ry5Mn617/+pbVr1+rBBx/UxIkTnbsKADHB6rLvLHAGRAbL64wUFBTo8OHDmj17tkpLS5WTk6P169d7J7UeOHBA8fHfZpysrCy9/vrrmjp1qi644AJ16dJFkydP1t133+3cVQCIenaWfWeBMyAyWF5nJBRYZwTA8OHWVlsdPlzauDFg5QDwQ0DWGQGAUGDZdyC6EUYAhL2cHGvtWfYdiCyEEQBhrbhY2rHD//bx8VJRUeDqAeA8wgiAsOV2S9dfb63PqlUscAZEGsIIgLD15pueze381a0bC5wBkYgwAiBsWV1XxMrtHADhgzACICytWiUdPep/+969pZYtA1cPgMAhjAAIO2639N//ba0Py74DkYswAiDsWN0Mj2XfgcjGCqwAworbLSVa3KiitpYwAoQjVmAFEJGsTlq95hqCCBDpCCMAwoadzfCKiwNTC4DgIYwACBs/+IG19uPGscAZEA0IIwDCgp3N8JYtC0wtAIKLMAIgLFgdFWEzPCB6EEYAhJzVURE2wwOiC2EEQMj172+tPZvhAdGFMAIgpGpqpO3b/W/PZnhA9CGMAAipXr2stWczPCD6EEYAhExxsbR/v//t2QwPiE6EEQAh4XZLY8da68NmeEB0IowACAk2wwNQjzACIOjcbumBB6z1eeONwNQCIPQIIwCCbu5cycp+4YyKANEtzhgr/ySEhr9bEAMIf263lJhorU9tLWEEiET+/v5mZARAUBUUWGvPqAgQ/QgjAILG5ZKee85aH+aKANGPMAIgaNgMD0BDCCMAgoLN8AA0hjACICisjoo8/TSb4QGxgjACIOCsjop06CCNGRO4egCEF8IIgICzOiqyalVg6gAQnggjAALK6qhIUpJ02WWBqwdA+CGMAAio/v2ttf/Tn5grAsQawgiAgKmpkbZv9799t27SddcFrh4A4YkwAiBgevWy1n7HjsDUASC8EUYABERxsbR/v//te/eWWrYMXD0AwhdhBIDj3G5p7FhrfbZtC0wtAMIfYQSA4+bOlerq/G/PZnhAbCOMAHCU2y098IC1PmyGB8Q2wggAR82dKxnjf3tGRQDEGWPln43QqKioUFpamsrLy5WamhrqcgA0wu2WEhOt9amtJYwA0crf39+MjABwTEGBtfaMigCQCCMAHOJySc89Z60Pc0UASIQRAA6xuhnetdcyKgLAgzACoNmsboYXHy8VFQWuHgCRhTACoNmsbob39NNshgfgW4QRAM1idTO8Dh2kMWMCVw+AyEMYAdAsVjfDW7UqMHUAiFyEEQC2Wd0MLylJuuyywNUDIDIRRgDYYmczvD/9ibkiAE5FGAFgi9XN8Hr3lq67LnD1AIhchBEAltnZDG/btsDUAiDyEUYAWMZmeACcxEZ5ACxhMzwA/mKjPAABwWZ4AJxGGAHgNzbDAxAItsLIkiVLlJ2drZSUFOXm5mrTpk1+9SsqKlJcXJyuvvpqO28LIMRycqy1ZzM8AP6wHEaKi4tVWFioOXPmaOvWrerXr59GjBihL774osl++/bt0x133KFLLrnEdrEAQqe4WNqxw//2bIYHwF+Ww8iiRYt0yy23aMKECerdu7eWLl2qVq1a6cknn2y0j9vt1k9/+lPNnTtX3bt3b1bBAILP7Zauv95aHzbDA+AvS2HE5XJpy5YtysvL+/YE8fHKy8tTSUlJo/3uv/9+dezYUTfddJP9SgGEzJtvSseP+9/+zDPZDA+A/yw9oHfkyBG53W5lZGT4HM/IyNDOnTsb7PP2229r+fLlev/99/1+n9raWtXW1nq/rqiosFImAIeNHm2tvZX9agAgoE/TVFZW6vrrr9eyZcuUnp7ud7/58+crLS3N+8rKygpglQCasmqVdPSo/+1795ZatgxcPQCij6WRkfT0dCUkJKisrMzneFlZmTIzM09pv2fPHu3bt0/5+fneY3X/3swiMTFRH3/8sc4555xT+s2YMUOFhYXerysqKggkQAjY2QyPZd8BWGUpjCQlJWngwIHasGGD9/Hcuro6bdiwQT//+c9PaX/++efrgw8+8Dk2a9YsVVZW6vHHH280YCQnJys5OdlKaQAC4L77rLVngTMAdlhc1FkqLCzU+PHjNWjQIA0ePFiLFy9WdXW1JkyYIEkaN26cunTpovnz5yslJUV9+vTx6d+uXTtJOuU4gPBiZzM8FjgDYIflMFJQUKDDhw9r9uzZKi0tVU5OjtavX++d1HrgwAHFx7OwKxDprC77fs01jIoAsIeN8gCcwuWSrN4pPXGCdUUA+GKjPAC2WV32feZMgggA+wgjAHzYWfZ97tzA1QMg+hFGAHi53dZXTmXZdwDNRRgB4DV6tGRlFhnLvgNwAmEEgCTPpNU1a6z1Ydl3AE4gjACQJPXvb609y74DcAphBICKi6Xt2631Ydl3AE4hjAAxzs7+M9deywJnAJxDGAFi3Ny50r/3r/RLXJxUVBS4egDEHsIIEMPcbmnePGt9Zs3iUV4AziKMADFs9Ghr7RMTpTlzAlMLgNhFGAFilJ1HeZ95hlERAM4jjAAxyur+M717S9ddF5BSAMQ4wggQg6zuPyPxKC+AwCGMADHGzv4zPMoLIJAII0CMsbr/DI/yAgg0wggQQ5i0CiAcEUaAGNK9u7X2XbuyKy+AwCOMADFi1Srp0CFrffbsCUwtAHAywggQA9h/BkA4I4wAMaCgwFp7Jq0CCCbCCBDlXC7puees9WHSKoBgIowAUe6cc6y1P+88Jq0CCC7CCBDFVq2SPv3UWp/t2wNTCwA0hjACRCk7k1ZnzuT2DIDgI4wAUapXL2vt4+OluXMDUwsANIUwAkShVaukXbus92FUBEAoEEaAKGPn9kzv3tJ11wWmHgA4HcIIEGWGDbPeZ9s25+sAAH8RRoAoUlwsvfuutT5TprDSKoDQIowAUcLtlkaPttanUyfpsccCUw8A+IswAkQJO7dnDh50vg4AsIowAkQBO7dnWFMEQLiIM8aYUBdxOhUVFUpLS1N5eblSU1NDXQ4QVtxuKTHRWp/4eM+eNYQRAIHk7+9vRkaACGd1R16JNUUAhBfCCBDB7OzIe9FFrCkCILwQRoAI1qGD9T5vv+18HQDQHIQRIEKNGiVVV1vrU1zM7RkA4YcwAkSg4mJp7Vprfbg9AyBcEUaACGNncTOJ2zMAwhdhBIgwvXpZ78PtGQDhjDACRJBVq6Rdu6z1yc3l9gyA8EYYASKE2y2NHWu93zvvOF8LADiJMAJEiPPPt96H2zMAIgFhBIgAU6ZIu3db6zNqFLdnAEQGwggQ5lavlh5/3FqfDh2kV14JTD0A4DTCCBDG3G57oxuff+58LQAQKIQRIIwNG2a9z5QpUlKS46UAQMAQRoAwVVgovfuutT5nnCE99lhg6gGAQCGMAGFo9Wp7oeKzz5yvBQACjTAChBm780S4PQMgUhFGgDBjZ7n3Tp24PQMgchFGgDBSWGh9uXdJOnjQ+VoAIFgII0CYcLnsjW6wyiqASEcYAcJEmzbW+7DKKoBoQBgBwkB2tnT8uLU+mZmssgogOhBGgBAbMEDav996v08/db4WAAgFW2FkyZIlys7OVkpKinJzc7Vp06ZG2y5btkyXXHKJ2rdvr/bt2ysvL6/J9kAs+dGPpG3brPdjngiAaGI5jBQXF6uwsFBz5szR1q1b1a9fP40YMUJffPFFg+03btyoMWPG6K233lJJSYmysrJ0+eWX69ChQ80uHohkxcX2brMwTwRAtIkzxhgrHXJzc3XhhRfqiSeekCTV1dUpKytLkyZN0vTp00/b3+12q3379nriiSc0btw4v96zoqJCaWlpKi8vV2pqqpVygbDkdkuJidb7ZWdLe/c6Xg4ABIS/v78tjYy4XC5t2bJFeXl5354gPl55eXkqKSnx6xzHjh3T8ePH1aFDBytvDUQVO0/OJCURRABEJ0v/3+zIkSNyu93KyMjwOZ6RkaGdO3f6dY67775bnTt39gk031VbW6va2lrv1xUVFVbKBMJadrb0zTfW+1VWOl4KAISFoD5Ns2DBAhUVFemFF15QSkpKo+3mz5+vtLQ07ysrKyuIVQKBY/fJmcJC9p0BEL0shZH09HQlJCSorKzM53hZWZkyMzOb7Ltw4UItWLBAb7zxhi644IIm286YMUPl5eXe10HWukYUyM+39+TMoEHSo486Xw8AhAtLYSQpKUkDBw7Uhg0bvMfq6uq0YcMGDRkypNF+Dz/8sObNm6f169dr0KBBp32f5ORkpaam+ryASFZYKL36qvV+OTnS3//ueDkAEFYsz+cvLCzU+PHjNWjQIA0ePFiLFy9WdXW1JkyYIEkaN26cunTpovnz50uSHnroIc2ePVsrV65Udna2SktLJUlt2rRRGzuz+IAIs3q1vT1n0tPtjaQAQKSxHEYKCgp0+PBhzZ49W6WlpcrJydH69eu9k1oPHDig+PhvB1x++9vfyuVy6dprr/U5z5w5c3Tfffc1r3ogzLnd9tYESUiQDh92vh4ACEeW1xkJBdYZQaRKTPQEEqtqa5mwCiDyBWSdEQD+S0qyF0R4cgZArCGMAAGQlGR9F15JGjiQJ2cAxB7CCOCw5GR7QSQ7W9q82fFyACDsEUYAB7VuLblc1vulp7PUO4DYRRgBHNKmjXTsmPV+rVvz5AyA2EYYARzQpo1UXW29X1KSVFXlfD0AEElsbGIO4GStW9sbEYmP9zzCCwCxjjACNENysr05IpL9fgAQbQgjgE12H9+VpOee86yyCgAgjACWud2elVXtWr1a+slPnKsHACIdE1gBC9asaV4QKSqSvrNNEwDEPMII4Kdp06T/+i/7/e+4QyoocK4eAIgW3KYB/JCfL736qv3+hYXSI484Vw8ARBPCCHAaAwdKW7fa7z9tmrRwoXP1AEC0IYwATcjOlvbvt9+/qIhbMwBwOoQRoAFut2dV1W++sX+OZ59t3hwTAIgVTGAFvqP+iZnmBJHnniOIAIC/GBkBTjJ1qrR4sf3+cXGehdBY0AwA/EcYAf5twABp2zb7/Vu0YIl3ALCDMIKY53JJqanN27SudWt23wUAu5gzgpg2dapns7vmBJEzziCIAEBzMDKCmNW9u7R3b/POkZ3d/HMAQKxjZAQxp6ZGio9vfogYOZIgAgBOIIwgpowaJbVqJRnTvPNMndq85eEBAN/iNg1iQk2NlJbmeey2uVjMDACcRRhBVHO7pYsvlt57r/nnSknxTFRlDREAcBa3aRC1Vq3yrKTqRBDp1s0zukIQAQDnEUYQddxu6dxzpbFjnTnf5MnSvn3OnAsAcCpu0yCq/OlP0rhxzpyrRQvPbZmkJGfOBwBoGGEEUaGqyrP4mFPLsffvL23d6sy5AABN4zYNIlpNjZSeLrVt61wQWbmSIAIAwcTICCKSyyXl5Eg7djh3zrZtpa++YpIqAAQbIyOIKC6XdOmlnv1knAwikyZJFRUEEQAIBUZGEBFqaqTcXOmDD5w9b6tWntEQJqkCQOgwMoKwVlUlZWZ6QoPTQWTSJKm6miACAKHGyAjCUlWV1LWrVF7u/Lnbt5dKSwkhABAuGBlB2HC5pAULPCGhbdvABJGnn5aOHiWIAEA4YWQEIReo+SAny82V3nmHCaoAEI4IIwgJt1t69VVpzBhPGAmUM86QDh6UWrYM3HsAAJqHMIKgqqqShg8P/KJiLVp4bse0aRPY9wEANB9zRhBwNTXSjTdK8fGeuSCBDiJ//KNn/glBBAAiAyMjCIiaGs+js3/4g3TiRHDe8+qrpTVrmBcCAJGGMALHlJdLI0ZI770X3Pe9+GLpzTd5QgYAIhW3aWBb/aO4XbtKcXFSu3bBDSLDhkm1tdLbbxNEACCSMTICS6qqpNGjpXXrJGNCU8NPfyo9+SQBBACiBSMjaFJ5uXTRRVJiomf0o21bae3a0ASRe+7xzD95+mmCCABEE0ZG4OVySYsWSUuWSIcOhW7k42SpqVJRkXT55UxMBYBoRRiJYfUTTjdv9ixCFk769JE2bWKxMgCIBdymiQFut/TSS1L37p5bLfWv+gmn4RJEWrb0TIitrfUsDU8QAYDYwMhIFAnH2yynExcn3XST9KtfET4AIFYRRiKM2y299po0c6b00UfhM6ph1YAB0v/7f6ySCgAgjISd+g3kpk6V9u2LjNENf6WmSs88I115JZNRAQDfIowEUU2NNHGiVFwsHTsW6mqCo1s36fbbPeGKx3EBAA0hjDRDOD+NEipxcZ6Rj+JibsEAAPwTs0/T1C9lnpXl2U325KdM/H2F29MooZKeLt1yi2e0p67OsygaQQQA4K+YHBm56y7pkUdCXUXkatlS+v73Gf0AADgj5sIIQcQ6wgcAIJBiKoy4XASR04mPlzp0kH78Y+nxx1n7AwAQeLbmjCxZskTZ2dlKSUlRbm6uNm3a1GT71atX6/zzz1dKSor69u2rdevW2Sq2uX7zm5C8bdiq3/hu5EipstLzGLHbLR0+LP3+9wQRAEBwWA4jxcXFKiws1Jw5c7R161b169dPI0aM0BdffNFg+7/97W8aM2aMbrrpJm3btk1XX321rr76an344YfNLt6qPXuC/pZhIz7es87HzTd7Jpoa45lsWlHhWdeE2y8AgFCJM8baslq5ubm68MIL9cQTT0iS6urqlJWVpUmTJmn69OmntC8oKFB1dbVeffVV77GLLrpIOTk5Wrp0qV/vWVFRobS0NJWXlys1NdVKuT4WL/asdxHNuM0CAAgX/v7+tjQy4nK5tGXLFuXl5X17gvh45eXlqaSkpME+JSUlPu0lacSIEY22l6Ta2lpVVFT4vJzws585cpqQa+j2Sv2L2ywAgEhjKYwcOXJEbrdbGRkZPsczMjJUWlraYJ/S0lJL7SVp/vz5SktL876ysrKslNmopCTpzjsdOVVANXRL5eQXt1cAANEkLBc9mzFjhsrLy72vgwcPOnbuhx8ObSBp0ULq0UN65RXpxIlTg0b96EZ5ubRsGaMbAIDoZymMpKenKyEhQWVlZT7Hy8rKlJmZ2WCfzMxMS+0lKTk5WampqT4vJz38sFRbK82fL3Xt6rntYUdTt0sae7lc0q5d0qhRbBYHAIBkMYwkJSVp4MCB2rBhg/dYXV2dNmzYoCFDhjTYZ8iQIT7tJenPf/5zo+2DJSlJmj5dOnjQc9vDnyDB7RIAAJxnedGzwsJCjR8/XoMGDdLgwYO1ePFiVVdXa8KECZKkcePGqUuXLpo/f74kafLkyRo+fLgeffRRjRw5UkVFRdq8ebN+//vfO3slAAAgIlkOIwUFBTp8+LBmz56t0tJS5eTkaP369d5JqgcOHFB8/LcDLkOHDtXKlSs1a9Ys3XPPPTr33HP14osvqk+fPs5dBQAAiFiW1xkJBafWGQEAAMETkHVGAAAAnEYYAQAAIUUYAQAAIUUYAQAAIUUYAQAAIUUYAQAAIWV5nZFQqH/62KndewEAQODV/94+3SoiERFGKisrJcmx3XsBAEDwVFZWKi0trdHvR8SiZ3V1dfrss8/Utm1bxdnd1a4BFRUVysrK0sGDB6N2MbVov0auL/JF+zVyfZEv2q8xkNdnjFFlZaU6d+7sszr7d0XEyEh8fLy6du0asPMHYmfgcBPt18j1Rb5ov0auL/JF+zUG6vqaGhGpxwRWAAAQUoQRAAAQUjEdRpKTkzVnzhwlJyeHupSAifZr5PoiX7RfI9cX+aL9GsPh+iJiAisAAIheMT0yAgAAQo8wAgAAQoowAgAAQoowAgAAQirqw8gvf/lLDR06VK1atVK7du386mOM0ezZs9WpUye1bNlSeXl52rVrl0+bo0eP6qc//alSU1PVrl073XTTTaqqqgrAFTTNah379u1TXFxcg6/Vq1d72zX0/aKiomBckg87f87/8R//cUrtt912m0+bAwcOaOTIkWrVqpU6duyoO++8UydOnAjkpTTK6jUePXpUkyZNUs+ePdWyZUudddZZ+sUvfqHy8nKfdqH6DJcsWaLs7GylpKQoNzdXmzZtarL96tWrdf755yslJUV9+/bVunXrfL7vz89jsFm5xmXLlumSSy5R+/bt1b59e+Xl5Z3S/oYbbjjls7riiisCfRmNsnJ9Tz311Cm1p6Sk+LQJt8/QyvU19O9JXFycRo4c6W0TTp/fX//6V+Xn56tz586Ki4vTiy++eNo+Gzdu1IABA5ScnKwePXroqaeeOqWN1Z9ry0yUmz17tlm0aJEpLCw0aWlpfvVZsGCBSUtLMy+++KL5xz/+YX70ox+Zs88+29TU1HjbXHHFFaZfv37m3XffNf/3f/9nevToYcaMGROgq2ic1TpOnDhhPv/8c5/X3LlzTZs2bUxlZaW3nSSzYsUKn3YnX3+w2PlzHj58uLnlllt8ai8vL/d+/8SJE6ZPnz4mLy/PbNu2zaxbt86kp6ebGTNmBPpyGmT1Gj/44APzk5/8xLz88stm9+7dZsOGDebcc88111xzjU+7UHyGRUVFJikpyTz55JPmo48+Mrfccotp166dKSsra7D9O++8YxISEszDDz9stm/fbmbNmmVatGhhPvjgA28bf34eg8nqNY4dO9YsWbLEbNu2zezYscPccMMNJi0tzXz66afeNuPHjzdXXHGFz2d19OjRYF2SD6vXt2LFCpOamupTe2lpqU+bcPoMrV7fl19+6XNtH374oUlISDArVqzwtgmnz2/dunVm5syZ5vnnnzeSzAsvvNBk+08++cS0atXKFBYWmu3bt5tf//rXJiEhwaxfv97bxuqfmR1RH0bqrVixwq8wUldXZzIzM80jjzziPfb111+b5ORks2rVKmOMMdu3bzeSzN///ndvm9dee83ExcWZQ4cOOV57Y5yqIycnx9x4440+x/z5Sxxodq9v+PDhZvLkyY1+f926dSY+Pt7nH8zf/va3JjU11dTW1jpSu7+c+gyfffZZk5SUZI4fP+49ForPcPDgwWbixIner91ut+ncubOZP39+g+2vu+46M3LkSJ9jubm55n/+53+MMf79PAab1Wv8rhMnTpi2bduaP/zhD95j48ePN1dddZXTpdpi9fpO929ruH2Gzf38HnvsMdO2bVtTVVXlPRZOn9/J/Pk34K677jLf+973fI4VFBSYESNGeL9u7p+ZP6L+No1Ve/fuVWlpqfLy8rzH0tLSlJubq5KSEklSSUmJ2rVrp0GDBnnb5OXlKT4+Xu+9917QanWiji1btuj999/XTTfddMr3Jk6cqPT0dA0ePFhPPvnkabeAdlpzru+ZZ55Renq6+vTpoxkzZujYsWM+5+3bt68yMjK8x0aMGKGKigp99NFHzl9IE5z6u1ReXq7U1FQlJvpuNxXMz9DlcmnLli0+Pzvx8fHKy8vz/ux8V0lJiU97yfNZ1Lf35+cxmOxc43cdO3ZMx48fV4cOHXyOb9y4UR07dlTPnj11++2368svv3S0dn/Yvb6qqip169ZNWVlZuuqqq3x+jsLpM3Ti81u+fLlGjx6t1q1b+xwPh8/PjtP9DDrxZ+aPiNgoL5hKS0slyecXVf3X9d8rLS1Vx44dfb6fmJioDh06eNsEgxN1LF++XL169dLQoUN9jt9///36z//8T7Vq1UpvvPGGfvazn6mqqkq/+MUvHKv/dOxe39ixY9WtWzd17txZ//znP3X33Xfr448/1vPPP+89b0Ofb/33gsmJz/DIkSOaN2+ebr31Vp/jwf4Mjxw5Irfb3eCf7c6dOxvs09hncfLPWv2xxtoEk51r/K67775bnTt39vnH/YorrtBPfvITnX322dqzZ4/uueceXXnllSopKVFCQoKj19AUO9fXs2dPPfnkk7rgggtUXl6uhQsXaujQofroo4/UtWvXsPoMm/v5bdq0SR9++KGWL1/uczxcPj87GvsZrKioUE1Njb766qtm/533R0SGkenTp+uhhx5qss2OHTt0/vnnB6kiZ/l7fc1VU1OjlStX6t577z3leycf69+/v6qrq/XII4848oss0Nd38i/lvn37qlOnTrrsssu0Z88enXPOObbPa0WwPsOKigqNHDlSvXv31n333efzvUB+hrBnwYIFKioq0saNG30meY4ePdr733379tUFF1ygc845Rxs3btRll10WilL9NmTIEA0ZMsT79dChQ9WrVy/97ne/07x580JYmfOWL1+uvn37avDgwT7HI/nzCxcRGUamTZumG264ock23bt3t3XuzMxMSVJZWZk6derkPV5WVqacnBxvmy+++MKn34kTJ3T06FFv/+bw9/qaW8eaNWt07NgxjRs37rRtc3NzNW/ePNXW1jZ7/4JgXV+93NxcSdLu3bt1zjnnKDMz85SZ4GVlZZLkyOcnBecaKysrdcUVV6ht27Z64YUX1KJFiybbO/kZNiQ9PV0JCQneP8t6ZWVljV5LZmZmk+39+XkMJjvXWG/hwoVasGCB/vKXv+iCCy5osm337t2Vnp6u3bt3B/WXWXOur16LFi3Uv39/7d69W1J4fYbNub7q6moVFRXp/vvvP+37hOrzs6Oxn8HU1FS1bNlSCQkJzf474RfHZp+EOasTWBcuXOg9Vl5e3uAE1s2bN3vbvP766yGbwGq3juHDh5/yBEZjHnjgAdO+fXvbtdrh1J/z22+/bSSZf/zjH8aYbyewnjwT/He/+51JTU0133zzjXMX4Ae711heXm4uuugiM3z4cFNdXe3XewXjMxw8eLD5+c9/7v3a7XabLl26NDmBddSoUT7HhgwZcsoE1qZ+HoPN6jUaY8xDDz1kUlNTTUlJiV/vcfDgQRMXF2deeumlZtdrlZ3rO9mJEydMz549zdSpU40x4fcZ2r2+FStWmOTkZHPkyJHTvkcoP7+Tyc8JrH369PE5NmbMmFMmsDbn74RftTp2pjC1f/9+s23bNu/jq9u2bTPbtm3zeYy1Z8+e5vnnn/d+vWDBAtOuXTvz0ksvmX/+85/mqquuavDR3v79+5v33nvPvP322+bcc88N2aO9TdXx6aefmp49e5r33nvPp9+uXbtMXFycee21104558svv2yWLVtmPvjgA7Nr1y7zm9/8xrRq1crMnj074NfzXVavb/fu3eb+++83mzdvNnv37jUvvfSS6d69u7n00ku9feof7b388svN+++/b9avX2/OPPPMkD7aa+Uay8vLTW5urunbt6/ZvXu3z+OEJ06cMMaE7jMsKioyycnJ5qmnnjLbt283t956q2nXrp33yaXrr7/eTJ8+3dv+nXfeMYmJiWbhwoVmx44dZs6cOQ0+2nu6n8dgsnqNCxYsMElJSWbNmjU+n1X9v0GVlZXmjjvuMCUlJWbv3r3mL3/5ixkwYIA599xzgx6O7Vzf3Llzzeuvv2727NljtmzZYkaPHm1SUlLMRx995G0TTp+h1eurN2zYMFNQUHDK8XD7/CorK72/5ySZRYsWmW3btpn9+/cbY4yZPn26uf76673t6x/tvfPOO82OHTvMkiVLGny0t6k/MydEfRgZP368kXTK66233vK20b/XY6hXV1dn7r33XpORkWGSk5PNZZddZj7++GOf83755ZdmzJgxpk2bNiY1NdVMmDDBJ+AEy+nq2Lt37ynXa4wxM2bMMFlZWcbtdp9yztdee83k5OSYNm3amNatW5t+/fqZpUuXNtg20Kxe34EDB8yll15qOnToYJKTk02PHj3MnXfe6bPOiDHG7Nu3z1x55ZWmZcuWJj093UybNs3nsdhgsnqNb731VoN/pyWZvXv3GmNC+xn++te/NmeddZZJSkoygwcPNu+++673e8OHDzfjx4/3af/ss8+a8847zyQlJZnvfe97Zu3atT7f9+fnMdisXGO3bt0a/KzmzJljjDHm2LFj5vLLLzdnnnmmadGihenWrZu55ZZbHP2H3ior1zdlyhRv24yMDPPDH/7QbN261ed84fYZWv07unPnTiPJvPHGG6ecK9w+v8b+fai/pvHjx5vhw4ef0icnJ8ckJSWZ7t27+/w+rNfUn5kT4owJ8vOaAAAAJ2GdEQAAEFKEEQAAEFKEEQAAEFKEEQAAEFKEEQAAEFKEEQAAEFKEEQAAEFKEEQAAEFKEEQAAEFKEEQAAEFKEEQAAEFKEEQAAEFL/H9M9/z2z0L5iAAAAAElFTkSuQmCC",
     21       "text/plain": [
     22        "<Figure size 640x480 with 1 Axes>"
     23       ]
     24      },
     25      "metadata": {},
     26      "output_type": "display_data"
     27     }
     28    ],
     29    "source": [
     30     "# Graph a sigmoid function (logistic function) from -1 to 1\n",
     31     "# defined by the equation 1 / (1 + (e^-x)) where 5 is the constant\n",
     32     "# multiplier of x. The larger this constant the faster the change occurs.\n",
     33     "# As an example, when the constant is 1 the function looks linear, but when this is 100\n",
     34     "# it looks almost vertical.This function can never go below 0 and never above 1. \n",
     35     "\n",
     36     "# To implement this I went through the 1000 values below and 1000 above 0 where the step was\n",
     37     "# .001. This was done by going from -1000 to 1001 and dividing these values by 1000. I then\n",
     38     "# put the x and y values into a dictionary and passed those into matplotlib as the x and y\n",
     39     "# values for the graph. \n",
     40     "\n",
     41     "import matplotlib.pyplot as plt\n",
     42     "import math\n",
     43     "\n",
     44     "data = {}\n",
     45     "for i in range(-1000, 1001):\n",
     46     "    i = i / 1000\n",
     47     "    denominator = 1 + math.pow(math.e, 5*-i)\n",
     48     "    numerator = 1\n",
     49     "    data[i] = (numerator / denominator)\n",
     50     "\n",
     51     "plt.plot(data.keys(), data.values(), marker='o', linestyle='-', color='b')"
     52    ]
     53   }
     54  ],
     55  "metadata": {
     56   "kernelspec": {
     57    "display_name": "notebook",
     58    "language": "python",
     59    "name": "notebook"
     60   },
     61   "language_info": {
     62    "codemirror_mode": {
     63     "name": "ipython",
     64     "version": 3
     65    },
     66    "file_extension": ".py",
     67    "mimetype": "text/x-python",
     68    "name": "python",
     69    "nbconvert_exporter": "python",
     70    "pygments_lexer": "ipython3",
     71    "version": "3.11.2"
     72   }
     73  },
     74  "nbformat": 4,
     75  "nbformat_minor": 2
     76 }