Introduction to machine Learning

IntroMachineLearning.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Introduction to Machine Learning"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "-by TExT Team Persistent System (<a href='https://www.persistent.com/'>www.persistent.com</a>)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Machine Learning is one of the most sought after skills these days. There has been a renewed interest in machine learning in last few years. This revival seems to be driven by strong fundamentals – loads of data being emitted by sensors across the globe, with cheap storage and lowest ever computational costs!"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## What is machine learning?\n",
    "Machine Learning is actually a lot of things. The field is quite vast and is expanding rapidly.\n",
    "Let us try to define <i>ML</i> in simple words, by answering following question.\n",
    "\n",
    "<ul type=\"circle\">\n",
    "<li><b>What happens when you search for something on Google?</b><br>\n",
    "Google shows up the most relevant web pages related to that search.</li>\n",
    "<li><b>But what really happens so that Google can show these relevant pages?</b><br>\n",
    "May be, Google looks at the past clicks from the people to understand which pages are more relevant for those searches and then serves those results on top of search.</li>\n",
    "<li><b>But, how many searches and what all kind of searches would Google handle regularly?</b><br>\n",
    "Must be a real big number – may be a trillion searches every year</li>\n",
    "<li><b>But, then how do you think Google can serve so many requests with such accuracy?</b><br>\n",
    "That sounds humanly impossible to do. Now, this is where machine learning comes into play.</li>\n",
    "</ul>\n",
    "\n",
    "<i><b>Machine Learning</b> refers to the techniques involved in dealing with vast data in the most intelligent fashion (by developing algorithms) to derive actionable insights.</i>\n",
    "\n",
    "The widely-quoted definition of <b>Machine learning</b> by Tom Mitchell best explains machine learning in a nutshell. \n",
    "\n",
    "<b>A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P if its performance at tasks in T, as measured by P, improves with experience E</b>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## How is machine learning different from Artificial Intelligence/Statistics/Deep Learning/Data Mining?"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<i>Artificail Intelligence</i> refers to the procedure of programming a computer (machine) to take rational, i.e. the basis of taking a decision. <i>AI</i> may include programs to check whether certain parameters within a program are behaving normally.\n",
    "\n",
    "<b>Machine Learning</b> is a subset of <i>AI</i> where the machine is trained to learn from it’s past experience. The past experience is developed through the data collected. Then it combines with algorithms such as Naïve Bayes, Support Vector Machine(SVM) to deliver the final results."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<i>Statistics</i> utilizes data, to carry out the analysis and present inferences. It uses techniques like regression,variance,standard deviation, conditional probability, etc. \n",
    "\n",
    "<b>Machine Learning</b> algorithms uses statistical concepts to execute machine learning. For instance, there comes a need to classify emails in a person's inbox are <i>spam</i> or <i>important</i>. Machine learning will use an algorithm that will check the frequency of the past spam mails to identify the new email as <i>spam</i> or <i>important</i>. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<i>Deep Learning</i> is associated with a machine learning algorithm (Artificial Neural Network, ANN) which uses the concept of human brain to facilitate the modeling of arbitrary functions. ANN requires a vast amount of data and this algorithm is highly flexible when it comes to model multiple outputs simultaneously."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<i>Data Mining</i> deals with searching specific information, and <b>Machine Learning</b> solely concentrates on performing a given task. In simple words, teaching someone how to dance is Machine Learning and using someone to find best dance centers in the city is <i>Data Mining</i>. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## How machines are trained?\n",
    "\n",
    "It involves a structural process where every stage builds a better version, as illusteated below:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAqEAAAEYCAIAAADj7bgpAAA+fUlEQVR42u2deZQUVZr28685fXqO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\nGA9BEARBYDwEQRAEQSmh/w9G+wzafuH+IQAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<IPython.core.display.Image object>"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from IPython.display import Image\n",
    "Image(filename=\"Images/ML_Intro_Trained.png\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## What are the steps used in Machine Learning?\n",
    "\n",
    "There are 5 basic steps used to perform a machine learning task:\n",
    "\n",
    "<ul type=\"circle\">\n",
    "<li><b>Collecting data: </b>Gathering past data forms the foundation of the future learning. The better the variety, density and volume of relevant data, better the learning prospects for the machine becomes.</li>\n",
    "<li><b>Preparing the data: </b>Any analytical process thrives on the quality of the data used. One needs to spend time determining the quality of data and then taking steps for fixing issues such as missing data and treatment of outliers.</li>\n",
    "<li><b>Training a model: </b>This step involves choosing the appropriate algorithm and representation of data in the form of the model. The cleaned data is split into two parts – train and test (proportion depending on the prerequisites); the first part (training data) is used for developing the model. The second part (test data), is used as a reference.</li>\n",
    "<li><b>Evaluating the model: </b>To test the accuracy, the second part of the data (holdout / test data) is used. This step determines the precision in the choice of the algorithm based on the outcome. A better test to check accuracy of model is to see its performance on data which was not used at all during model build.</li>\n",
    "<li><b>Improving the performance: </b>This step might involve choosing a different model altogether or introducing more variables to augment the efficiency. That’s why significant amount of time needs to be spent in data collection and preparation.</li>\n",
    "</ul>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## What are the types of Machine Learning algorithms?\n",
    "\n",
    "This is illustrated below:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAA6sAAAJVCAYAAAA4DWNYAAAAAXNSR0IArs4c6QAAAARnQU1BAACx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\nAAAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<IPython.core.display.Image object>"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from IPython.display import Image\n",
    "Image(filename=\"Images/ML_Intro_Types.png\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Supervised Learning \n",
    "\n",
    "Also termed as Predictive model, it is used to predict the future outcome based on the historical data. Predictive models are normally given clear instructions right from the beginning as in what needs to be learnt and how it needs to be learnt. These class of learning algorithms are termed as Supervised Learning.\n",
    "\n",
    "In the majority of supervised learning applications, the ultimate goal is to develop a finely tuned predictor function <b>h(x)</b> (sometimes called the “hypothesis”). <i>Learning</i> consists of using sophisticated mathematical algorithms to optimize this function so that, given input data <b>x</b> about a certain domain (say, square footage of a house), it will accurately predict some interesting value <b>h(x)</b>.\n",
    "\n",
    "Some examples of algorithms used are: <b>Nearest neighbour</b>, <b>Naïve Bayes</b>, <b>Decision Trees</b>, <b>Regression</b> etc."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Unsupervised learning:\n",
    "\n",
    "Also termed as Descriptive model, it is used to train models where no target is set and no single feature is important than the other. Typically it is tasked with finding relationships within data. There are no training examples used in this process. Instead, the system is given a set data and tasked with finding patterns and correlations therein. A good example is identifying close-knit groups of friends in social network data. Example of algorithm used here is: <b>K- Means Clustering</b> Algorithm, <hierarchical clustering</b>, <b>mixture models</b>, <b>Neural works</b>, etc."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Reinforcement learning\n",
    "\n",
    "It is an example of machine learning where the machine is trained to take specific decisions based on the business requirement with the sole motto to maximize efficiency (performance). The idea involved in reinforcement learning is: The machine/ software agent trains itself on a continual basis based on the environment it is exposed to, and applies it’s enriched knowledge to solve business problems. This continual learning process ensures less involvement of human expertise which in turn saves a lot of time!\n",
    "\n",
    "An example of algorithm used in <i>RL</i> is <b>Markov Decision Process</b>."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "There is a subtle difference between <b>Supervised Learning</b> and <b>Reinforcement Learning (RL)</b>. <i>RL</i> essentially involves learning by interacting with an environment. An RL agent learns from its past experience, rather from its continual trial and error learning process as against supervised learning where an external supervisor  provides examples."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## What are the applications of Machine Learning?\n",
    "Here are few applications of ML:\n",
    "<ul type=\"circle\">\n",
    "<li><b>Google</b> and <b>Facebook</b> uses <i>ML</i> extensively to push their respective ads to the relevant users.</li>\n",
    "\n",
    "<li><b>Banking & Financial services: </b>ML can be used to predict the customers who are likely to default  from paying loans or credit card bills. This is of paramount importance as machine learning would help the banks to identify the customers who can be granted loans and credit cards.</li>\n",
    "\n",
    "<li><b>Healthcare: </b>It is used to diagnose deadly diseases (e.g. cancer) based on the symptoms of patients and tallying them with the past data of similar kind of patients.</li>\n",
    "\n",
    "<li><b>Retail: </b>It is used to identify products which sell more frequently (fast moving) and the slow moving products which help the retailers to decide what kind of products to introduce or remove from the shelf. Also, machine learning algorithms can be used to find which two/three or more products sell together. This is done to design customer loyalty initiatives which in turn helps the retailers to develop and maintain loyal customers.</li>\n",
    "</ul>"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": false
   },
   "source": [
    "## References:\n",
    "https://www.toptal.com/machine-learning/machine-learning-theory-an-introductory-primer<br>\n",
    "http://alex.smola.org/drafts/thebook.pdf<br>\n",
    "https://www.analyticsvidhya.com/blog/2017/04/comparison-between-deep-learning-machine-learning<br>\n",
    "https://www.analyticsvidhya.com/blog/2015/06/machine-learning-basics<br>\n",
    "https://en.wikipedia.org/wiki/Unsupervised_learning<br>"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}