added necessary documnets

Author: root

.ipynb_checkpoints/ten-checkpoint.ipynb renamed to .ipynb_checkpoints/10_machine_learning_basics-checkpoint.ipynb

@@ -12,26 +12,26 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "##Machine learning Basics\n",
+    "<h3>Machine learning Basics</h3>\n",
     "\n",
     "\n",
-    "Artificial Intelligence:\n",
+    "<h4>Artificial Intelligence:</h4>\n",
     "    Making the machine behave more like human\n",
     "\n",
-    "Machine Learning: \n",
+    "<h4>Machine Learning:</h4> \n",
     "    Unlike the traditional algorithm based approach of programming, here we feed the machine the data and let it come up with the soultion based on the data.\n",
     "\n",
-    "Deep Neural Networks:\n",
+    "<h4>Deep Neural Networks:</h4>\n",
     "    It is bio mimicry of the human neural system (neuron) and using this technique to learn.\n",
     "    \n",
-    "General Programming approcah:\n",
+    "<h4>General Programming approcah:</h4>\n",
     "\n",
     "1. Identify the problem \n",
     "2. Generate the solution through algorithm\n",
     "3. Code\n",
     "4. Deploy\n",
     "\n",
-    "Machine learning Approach:\n",
+    "<h4>Machine learning Approach:</h4>\n",
     "\n",
     "1. Identify the problem\n",
     "2. Collect the data\n",
@@ -41,7 +41,7 @@
     "\n",
     "\n",
     "\n",
-    "Machine Learning\n",
+    "<h4>Machine Learning<h4>\n",
     "\n",
     "1. Supervised Learning:\n",
     "    a. Regression: Linear Regression\n",
@@ -63,7 +63,7 @@
     "*GAN- Drawing whole image based just on shapes\n",
     "\n",
     "\n",
-    "Neural Networks:\n",
+    "<h4>Neural Networks:</h4>\n",
     "\n",
     "components:\n",
     "\n",
@@ -95,11 +95,11 @@
     "The inputs are multiplied by the weights and then added with the biaz, The value thus obtained is fed to the activation function like sigmoid(or tan...)\n",
     "\n",
     "\n",
-    "* forward Propogation:\n",
+    "<h5>* forward Propogation:</h5>\n",
     "\n",
     "The value obtained is the output, from this output the error is found with the help of error function like cross entropy, the collective error of all the samples is the cost which is calculated with the help of cost function. \n",
     "\n",
-    "* Back Propogation\n",
+    "<h5>* Back Propogation</h5>\n",
     "Our main aim is to reduce this cost, this is obtained by using the function that reduce the error like gradient descent, that calculates the new value of weights accordingly.\n",
     "\n",
     "\n",
@@ -115,6 +115,15 @@
     "\n",
     "\n"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {

eleven.ipynb renamed to .ipynb_checkpoints/11_ML_Neural_nets_basics-checkpoint.ipynb

@@ -4,7 +4,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Deep Neural Networks:\n",
+    "<h4>Deep Neural Networks:</h4>\n",
     "\n",
     "\n",
     "1. The input in form of features is fed to the networks\n",
@@ -24,7 +24,7 @@
     "\n",
     "\n",
     "\n",
-    "Machine Learning Libraries:\n",
+    "<h4>Machine Learning Libraries:</h4>\n",
     "\n",
     "1. Tensorflow :developed by google, has good documentation and supports GPU version also.\n",
     "\n",
@@ -39,6 +39,15 @@
     "\n",
     "\n"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {

twelve.ipynb renamed to .ipynb_checkpoints/12_pandas-checkpoint.ipynb

@@ -2,16 +2,18 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
+   "execution_count": 5,
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "import pandas as pd\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -22,19 +24,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "0    1.0\n",
-      "1    2.0\n",
-      "2    3.0\n",
-      "3    4.0\n",
-      "4    5.0\n",
-      "5    6.0\n",
+      "a    1.0\n",
+      "b    2.0\n",
+      "c    3.0\n",
+      "e    4.0\n",
       "dtype: float64\n"
      ]
     }
@@ -45,8 +45,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 31,
-   "metadata": {},
+   "execution_count": 8,
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "#dataframes-2D\n",
@@ -56,7 +58,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 32,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [
     {
@@ -76,16 +78,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 36,
-   "metadata": {},
+   "execution_count": 10,
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": [
     "df=pd.DataFrame({'a':[1,2,3],'b':[2,3,4],'c':[3,4,5]},index=[1,2,3])"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 37,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [
     {
@@ -105,7 +109,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 38,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [
     {
@@ -117,7 +121,7 @@
        "Name: a, dtype: int64"
       ]
      },
-     "execution_count": 38,
+     "execution_count": 12,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -129,7 +133,9 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {},
+   "metadata": {
+    "collapsed": true
+   },
    "outputs": [],
    "source": []
   }