single_neuron.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "X = np.arange(-1.0, 1.0, 0.2)\n",
    "Y = np.arange(-1.0, 1.0, 0.2)\n",
    "\n",
    "Z = np.zeros((10, 10))\n",
    "\n",
    "w_x = 2.5\n",
    "w_y = 3.0\n",
    "bias = 0\n",
    "\n",
    "for i in range(10):\n",
    "    for j in range(10):\n",
    "        \n",
    "        u = X[i]*w_x + Y[j]*w_y + bias\n",
    "        \n",
    "        y = 1/(1+np.exp(-u))\n",
    "        \n",
    "        Z[i][j] = y\n",
    "\n",
    "plt.imshow(Z, \"gray\", vmin = 0.0, vmax = 1.0)\n",
    "plt.colorbar()\n",
    "plt.show()\n",
    "        "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "X = np.arange(-10, 10, 1)\n",
    "Y = np.arange(-10, 10, 1)\n",
    "\n",
    "Z = np.zeros((20, 20))\n",
    "\n",
    "w_x = 1\n",
    "w_y = 1\n",
    "bias = 0\n",
    "\n",
    "for i in range(20):\n",
    "    for j in range(20):\n",
    "        \n",
    "        u = X[i]*w_x + Y[j]*w_y + bias\n",
    "        \n",
    "        y = np.where(u >= 0, u, 0)\n",
    "        \n",
    "        Z[i][j] = y\n",
    "\n",
    "plt.imshow(Z, \"gray\", vmin = 0.0, vmax = 10)\n",
    "plt.colorbar()\n",
    "plt.show()\n",
    "        "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAATcAAAD8CAYAAAASeuPxAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDIuMi4zLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvIxREBQAAFPRJREFUeJzt3X2MXFd9xvHvg5OAGlIScBOCbZIITFQTgUGWA4panOalGyuKoQpgoxZD3S4g3JaXVjWlciLzDy9Ko1aOEpbGckDgJKU1rIrzYgWQoUqC18FJbCdutm4gm7XsGgeHKKTpxr/+MXejYTxve+fac+b4+Uijnbn3zL1nvDuPz73nnnsUEZiZ5eYV/a6Amdnx4HAzsyw53MwsSw43M8uSw83MsuRwM7MsOdzMrO8kbZB0UNKuFusl6Z8kjUt6RNI7O23T4WZmKdgIDLVZfxUwv3gMAzd32qDDzcz6LiK2AYfbFFkGfD1qHgDOlHRuu22eUmUFqyLJwybMjrOIUC/vHxoaikOHDnVVdseOHbuBF+oWjUTEyAx2Nwd4qu71RLFsf6s3JBluZpa+Q4cOMTY21lVZSS9ExKIedtcsiNs2ghxuZlbaCRybPgHMq3s9F5hs94aezrlJGpK0t+jBWNNk/Ssl3VGsf1DS+b3sz8zScvTo0a4eFRgFPlz0mr4LOBIRLQ9JoYeWm6RZwE3AFdRSdbuk0YjYU1dsFfBMRLxZ0nLgS8AHy+7TzNIREZW13CRtApYAsyVNANcBpxb7uQXYAiwFxoHngY922mYvh6WLgfGI2FdU7nZqPRr14bYMuL54/m1gvSSF77NkloWqvsoRsaLD+gA+OZNt9nJY2qr3ommZiJgCjgCva7YxScOSxiR1d4bSzPpuuvXW6dEPvbTcuum96LqHo+gWHgFfCmI2KFI+COul5dZN78XLZSSdAryG9hfqmdkASbnl1ku4bQfmS7pA0mnAcmo9GvVGgZXF82uB7/t8m1keIuJE9pbOWOnD0oiYkrQauAeYBWyIiN2S1gFjETEK3Ap8Q9I4tRbb8ioqbWZpSLmt0tNFvBGxhVoXbf2ytXXPXwDe38s+zKx73YbNokW9DBaY+f76wSMUzKw0h5uZZaefnQXdcLiZWWn96izohsPNzEpzy83MsuPDUjPLlsPNzLLkcDOzLDnczCw708OvUuVwM7PS3HIzs9JSDpCU6+ZwM7PSHG5mliWHm5llxx0KZpYtt9zMLEsONzPLksPNzLKT+sD50hPESJon6QeSHpO0W9JfNSmzRNIRSTuLx9pm2zKzwZTy7Fe9tNymgM9GxEOSzgB2SNoaEXsayv0oIq7uYT9mlqgse0sjYj+wv3j+K0mPUZthvjHczCxTWR6W1pN0PvAO4MEmq98t6WFJd0l6a5ttDEsakzRWRZ3MUtbt4VzK4ZH6Z+i5Q0HSq4F/BT4VEc82rH4IOC8inpO0FPgOML/ZdiJiBBgptpnub9TMXpZy+PbUcpN0KrVg+2ZE/Fvj+oh4NiKeK55vAU6VNLuXfZpZOrJsuUkStRnlH4uIf2hR5vXAgYgISYuphekvyu7TzNKScsutl8PSS4A/AR6VtLNY9nfAGwEi4hbgWuATkqaAXwPLI+V/DTPrWrZjSyPix4A6lFkPrC+7DzNLW8ptFY9QMLPSHG5mlqWUw62S69zM7ORUVW+ppCFJeyWNS1rTZP0bi+GeP5X0SHFpWVtuuZlZKVV1KEiaBdwEXAFMANsljTYM5fx74M6IuFnSAmALcH677brlZmalVdRyWwyMR8S+iHgRuB1Y1rgr4LeL568BJjtt1C03s4qkfP7peJnBZ57dMLRypBiVBLUx6U/VrZsALm54//XAvZL+AjgduLzTDh1uZlbaDMLtUEQsarGu2SVljRteAWyMiBskvRv4hqSLIqLlcbHDzcxKqXBo1QQwr+71XI497FwFDBX7vV/Sq4DZwMFWG/U5NzMrraJzbtuB+ZIukHQasBwYbSjzc+AyAEm/C7wK+J92G3XLzcxKq6K3NCKmJK0G7gFmARsiYrekdcBYRIwCnwW+JunT1A5ZP9JpKKfDzcxKq6oTpbhr0JaGZWvrnu+hNp69aw43Mysl9ZtpOtzMrDSHm5llyeFmZllyuJkNqJS/vP2W7c0qzcxSDn+Hm5mVlnW4SXoS+BXwEjDVOH6smEjmH4GlwPPULr57qNf9mln/ZR1uhUsj4lCLdVdRm6t0PrWR/jdz7Ih/MxtAJ0O4tbMM+HoxVOIBSWdKOjci9p+AfZvZcZJ6h0IVA+eD2n2WdkgabrK+2b2a5jQWkjQsaazhnk9mlrAsJ2Wuc0lETEo6G9gq6fGI2Fa3vpt7NVHcuG4EQFK6bV0ze1nKh6U9t9wiYrL4eRDYTO2WwfW6uVeTmQ2glFtuPYWbpNMlnTH9HLgS2NVQbBT4sGreBRzx+TazwddtsA3qYek5wOba1R6cAnwrIu6W9HGAiLiF2m1MlgLj1C4F+WiP+zSzRKR8WNpTuEXEPuDtTZbfUvc8gE/2sh+zqqX8pRwkKfeWeoSCmZWW8n8SDjczK8U3qzSzbDnczCxLDjczy5LDzcyyk/rYUoebmZXmlpuZZcnhZmZZcriZWZYcbmYnQMpftBy5Q8HMspXyfygONzMrzeFmZllyuJlZdjxw3syy5XAzsyy5t9TMspP6YWnpCWIkXShpZ93jWUmfaiizRNKRujJre6+ymaWiqgliJA1J2itpXNKaFmU+IGmPpN2SvtVpm6VbbhGxF1hY7HQW8DS1qf0a/Sgiri67HzNLVxUttyI/bgKuoDYV6HZJoxGxp67MfOBz1OZJfqaYJ7mtKmacB7gM+K+I+FlF2zOzAVBRy20xMB4R+yLiReB2YFlDmT8HboqIZ4r9Huy00arCbTmwqcW6d0t6WNJdkt7aagOShiWNSRqrqE6WgdTnxjyZTQ+/6uYBzJ7+fheP4bpNzQGeqns9USyr9xbgLZL+Q9IDkoY61a/nDgVJpwHXUGsyNnoIOC8inpO0FPgOML/ZdiJiBBgptum/VLMBMIP/VA5FxKIW69Rs0w2vT6GWHUuAucCPJF0UEb9stcMqWm5XAQ9FxIFjahfxbEQ8VzzfApwqaXYF+zSzBFTUqp4A5tW9ngtMNinz3Yj4v4j4b2AvLRpK06oItxW0OCSV9HoV09FLWlzs7xcV7NPMElBRuG0H5ku6oDgSXA6MNpT5DnApQNFAeguwr91GezoslfRb1Ho4Pla37OPw8qzz1wKfkDQF/BpYHj45YpaNKr7OETElaTVwDzAL2BARuyWtA8YiYrRYd6WkPcBLwN9ERNuGUk/hFhHPA69rWHZL3fP1wPpe9mFmaaqyI6c4bbWlYdnauucBfKZ4dMUjFMysNA+/MrMspXyWyeFmZqU53MwsO6lfPO1wM7PSHG5mdVL+QtjMpPy7dLiZWWnuLTWz7Picm5lly+FmZllyuJlZlhxuZpad6ZtVpsrhZmalueVmZllyuJlZlhxuZpYlh5tlL+U/cjs+fBGvmWUr5d7SriaIkbRB0kFJu+qWvVbSVklPFD/PavHelUWZJyStrKriZtZ/Kc8p2+3sVxuBxklQ1wD3RcR84L7i9W+Q9FrgOuBiarNKX9cqBM1s8Ax8uEXENuBww+JlwG3F89uA9zZ56x8CWyPicEQ8A2zl2JA0swHUbbD1K9x6Oed2TkTsB4iI/ZLOblJmDvBU3euJYpmZZeBk7lBQk2VN/zUkDQPDx7c6ZlallMOtlxnnD0g6F6D4ebBJmQlgXt3rucBks41FxEhELIqIRT3UycxOoKNHj3b16Idewm0UmO79XAl8t0mZ6Vmizyo6Eq4slpnZgEv9nFu3l4JsAu4HLpQ0IWkV8EXgCklPAFcUr5G0SNI/A0TEYeALwPbisa5YZmYZSDncujrnFhErWqy6rEnZMeDP6l5vADaUqp2ZJS3lc24eoWAtpfyHa2lI+W/E4WZmpfhmlWaWLbfczCxLDjczy5LDzcyy5HAzs+z4ZpVmlq2Ue0t7GX5lZie5qkYoSBqStFfSuKRj7g1ZV+5aSSGp4xh0h5uZlVZFuEmaBdwEXAUsAFZIWtCk3BnAXwIPdlM3h5uZlVLhwPnFwHhE7IuIF4Hbqd0Mt9EXgC8DL3RTP4fbSSb1OznYYJnB39JsSWN1j/p7N3a8qa2kdwDzIuLfu62bOxTMrLQZ/Cd4qM29Gtve1FbSK4AbgY/MpG4ONzMrraLe0k43tT0DuAj4oSSA1wOjkq4p7kLUlMPNzEqp8PTFdmC+pAuAp4HlwIfq9nMEmD39WtIPgb9uF2zgc25m1oMqzt9GxBSwmtpduh8D7oyI3ZLWSbqmbN3ccjOz0qrqeIqILcCWhmVrW5Rd0s02HW5mVlrKveoONzMrJfWbVXY85yZpg6SDknbVLfuKpMclPSJps6QzW7z3SUmPStopqe3JPzMbPClfM9lNh8JGYKhh2Vbgooh4G/CfwOfavP/SiFjY5hoXMxtQAx1uEbENONyw7N6ihwPgAWrXpZjZSWagw60Lfwrc1WJdAPdK2tEw3OIYkoanh2ZUUKeTiodUWb+k/HfXU4eCpM8DU8A3WxS5JCImJZ0NbJX0eNESPEZEjAAjxXb9LTRLXOr/YZYON0krgauBy6LFJ4yIyeLnQUmbqY3+bxpuZjZ4Brq3tBlJQ8DfAtdExPMtypxe3H8JSacDVwK7mpU1s8GU8mFpN5eCbALuBy6UNCFpFbCe2mDWrcVlHrcUZd8gafoq43OAH0t6GPgJ8L2IuPu4fAoz64uUw63jYWlErGiy+NYWZSeBpcXzfcDbe6qdmSUr23NuZmYONzPLUsodCg43MyvFh6Vmli2Hm5llyeFmM5byH43ZtJT/Th1uZlaaw83MspP6zSodbmZWmltuZpYlh5uZZcnhZmbZ8UW8ZpYth5uZZcm9pWaWJbfcDEj7D8FspnzOzcyy5XAzsyylHG7dzKGwQdJBSbvqll0v6eli/oSdkpa2eO+QpL2SxiWtqbLiZtZ/R48e7erRD93MfrURGGqy/MaIWFg8tjSulDQLuAm4ClgArJC0oJfKmlk6Up8MvGO4FZMoHy6x7cXAeETsi4gXgduBZSW2Y2aJGuhwa2O1pEeKw9azmqyfAzxV93qiWNaUpGFJY5LGeqiTmZ1AOYbbzcCbgIXAfuCGJmXUZFnLTxkRIxGxKCIWlayTmZ1g2YVbRByIiJci4ijwNWqHoI0mgHl1r+cCk2X2Z2ZpqircOnU+SvqMpD3F0eJ9ks7rtM1S4Sbp3LqX7wN2NSm2HZgv6QJJpwHLgdEy+zOz9EzfrLLX3tIuOx9/CiyKiLcB3wa+3Kl+3VwKsgm4H7hQ0oSkVcCXJT0q6RHgUuDTRdk3SNpSfPApYDVwD/AYcGdE7O60PzMbHBW13Dp2PkbEDyLi+eLlA9SOBNvqeBFvRKxosvjWFmUngaV1r7cAx1wmkpuUL2Q0O55m8Lc/u6GzcCQiRornzTofL26zrVXAXZ126BEKZlbaDMLtUJvOwq47HyX9MbAIeE+nHTrczKyUCntCu+p8lHQ58HngPRHxv5026nAzs9IqCreXOx+Bp6l1Pn6ovoCkdwBfBYYi4mA3G3W4mVlpVYwbjYgpSdOdj7OADRGxW9I6YCwiRoGvAK8G/kUSwM8j4pp223W4mVlpVXWmNet8jIi1dc8vn+k2HW5mVopvVmlm2XK4mVmWHG5mliXPfmVm2fE5twGV8i/NLBUpf08cbmZWmsPNzLLkcDOzLDnczCw70zerTJXDzcxKc8vNzLLkcDOzLA10uEnaAFwNHIyIi4pldwAXFkXOBH4ZEQubvPdJ4FfAS8CUp+0zy0cOF/FuBNYDX59eEBEfnH4u6QbgSJv3XxoRh8pW0MzSNdDhFhHbJJ3fbJ1qd437APAH1VbLzAZBzr2lvwcciIgnWqwP4F5JAXy1brabY0gaBoZ7rE9bKf8vYzaIUv5O9RpuK4BNbdZfEhGTks4Gtkp6PCK2NStYBN8IQBGGZpaw1M+5lZpxHkDSKcAfAXe0KlPMY0oxocNmapOvmlkmKpqU+bgoHW7A5cDjETHRbKWk0yWdMf0cuBLY1cP+zCwxAx1ukjYB9wMXSpqQtKpYtZyGQ1JJb5A0PcnDOcCPJT0M/AT4XkTcXV3Vzazfjh492tWjH7rpLV3RYvlHmiybBJYWz/cBb++xfmaWqNTPuXmEgpmV5nAzsyw53MwsSw43M8uSw83MsuObVR5nKf/PYZa7lL9/Ax9uZtY/Djczy5LDzcyy44t4zSxbDjczy5J7S80sS265mVl2Uj/n1sv93MzsJFfV/dwkDUnaK2lc0pom618p6Y5i/YOt5nWp53Azs9KqCDdJs4CbgKuABcAKSQsaiq0CnomINwM3Al/qVDeHm5mVVtHNKhcD4xGxLyJeBG4HljWUWQbcVjz/NnBZMfteS6meczsE/Kxh2exi+W/o8PkGQdPPlYlcP1sOn+u8CrZxD7V/i268StJY3euRutnw5gBP1a2bAC5ueP/LZSJiStIR4HW0+T0kGW4R8TuNyySN5Thjfa6fC/L9bLl+rpmKiKGKNtWshdJ4LNtNmd/gw1Iz67cJYF7d67nAZKsyxcx7rwEOt9uow83M+m07MF/SBZJOozb51GhDmVFgZfH8WuD70aGnIsnD0hZazlY/4HL9XJDvZ8v1c/VFcQ5tNbVzeLOADRGxW9I6YCwiRoFbgW9IGqfWYlveabtK+SI8M7OyfFhqZllyuJlZlgYi3DoNzRhUkp6U9KiknQ3XAA0cSRskHZS0q27ZayVtlfRE8fOsftaxjBaf63pJTxe/t52SlvazjtZc8uHW5dCMQXZpRCzM4LqpjUDjdU9rgPsiYj5wX/F60Gzk2M8FcGPxe1sYEVtOcJ2sC8mHG90NzbA+i4htHHvdUf2QmduA957QSlWgxeeyATAI4dZsaMacPtWlagHcK2mHpOF+V+Y4OCci9gMUP8/uc32qtFrSI8Vh68Adbp8MBiHcZjzsYoBcEhHvpHbI/UlJv9/vCllXbgbeBCwE9gM39Lc61swghFs3QzMGUkRMFj8PApupHYLn5ICkcwGKnwf7XJ9KRMSBiHgpIo4CXyO/31sWBiHcuhmaMXAknS7pjOnnwJXArvbvGjj1Q2ZWAt/tY10qMx3YhfeR3+8tC8kPv2o1NKPP1arCOcDm4pZNpwDfioi7+1ul8iRtApYAsyVNANcBXwTulLQK+Dnw/v7VsJwWn2uJpIXUTo88CXysbxW0ljz8ysyyNAiHpWZmM+ZwM7MsOdzMLEsONzPLksPNzLLkcDOzLDnczCxL/w/+WrTiDMQnJAAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "X = np.arange(-10, 10, 1)\n",
    "Y = np.arange(-10, 10, 1)\n",
    "\n",
    "Z = np.zeros((20, 20))\n",
    "\n",
    "w_x = 1\n",
    "w_y = 1\n",
    "bias = 0\n",
    "\n",
    "for i in range(20):\n",
    "    for j in range(20):\n",
    "        \n",
    "        u = (X[i]*w_x) + (Y[j]*w_y) + bias\n",
    "        \n",
    "        y = np.where(u >= 0, 1, 0)\n",
    "        \n",
    "        Z[i][j] = y\n",
    "\n",
    "plt.imshow(Z, \"gray\", vmin = 0.0, vmax = 1)\n",
    "plt.colorbar()\n",
    "plt.show()\n",
    "        "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.7.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}