Chapter 1: Intro to Machine Learning

By Misganu T.
 What is Machine learning?
• Machine learning is a subset of Artificial Intelligence (AI)
which provides machines the ability to learn
automatically & improve from experience without being
explicitly programmed to do so.
• In the sense, it is the practice of getting Machines to solve
problems by gaining the ability to think.
• 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.
• If you feed a machine a good amount of data, it will learn
how to interpret, process and analyze this data by using
Machine Learning Algorithms, in order to solve real-
world problems.
 Machine Learning Terminologies
• Algorithm: A Machine Learning algorithm is a set of
rules and statistical techniques used to learn patterns from
data and draw significant information from it. It is the
logic behind a Machine Learning model.

• Model: A model is the main component of Machine

Learning. A model is trained by using a Machine Learning
Algorithm. An algorithm maps all the decisions that a
model is supposed to take based on the given input, in
order to get the correct output.
 Machine Learning Terminologies Cont.

• Predictor Variable: It is a feature(s) of the data that can be used

to predict the output.

• Response Variable: It is the feature or the output variable that

needs to be predicted by using the predictor variable(s).

• Training Data: The Machine Learning model is built using the

training data. The training data helps the model to identify key
trends and patterns essential to predict the output.

• Testing Data: After the model is trained, it must be tested to

evaluate how accurately it can predict an outcome. This is done by
the testing data set.
 History and relationships to other fields
• The roots of machine learning can be traced back to the mid-20th century when researchers
first began exploring the idea of building machines that could learn from data.

• In the 1950s and 1960s, researchers developed the first machine learning algorithms and
models, such as the perceptron algorithm and the decision tree, and applied them to a range of
problems, including pattern recognition, speech recognition, and game playing.

• In the 1970s and 1980s, machine learning research slowed down due to a lack of data and
computing power.

• However, with the advent of the internet and the explosion of digital data in the 1990s and
2000s, machine learning experienced a resurgence, and researchers developed new algorithms
and models that could handle large-scale data sets, such as deep learning neural networks.

• Today, machine learning is used in many real-world applications, including image and speech
recognition, natural language processing, recommender systems, and predictive analytics.

• It is closely related to several other fields, including: Computer Science, Mathematics,

statistics, probability theory etc.
Essential math and statistics for machine
learning
• Linear algebra: Linear algebra deals with mathematical operations on vectors and

matrices. It is used in machine learning for tasks such as matrix operations, vector

operations, and solving systems of linear equations.

• Calculus: Calculus deals with the study of how things change. It includes concepts such as

derivatives (which measure the rate of change of a function) and integrals (which measure

the area under a curve). Calculus is used in machine learning for tasks such as optimization

and calculating gradients.

• Probability theory: Probability theory deals with the study of randomness and uncertainty.

It includes concepts such as probability distributions (which describe the likelihood of

different outcomes), and conditional probability (P(A|B) = P(B|A) * P(A) / P(B)).

Probability theory is used in machine learning for tasks such as statistical inference,

generative models, and decision making.

 Cont. …
• Statistics: Statistics deals with the collection, analysis, and interpretation of data. It

includes concepts such as descriptive statistics (which summarize and describe data),

hypothesis testing (which is used to make inferences about populations based on

sample data), and regression analysis (which is used to model the relationship

between variables). Statistics is used in machine learning for tasks such as data

analysis, statistical inference, and model evaluation.

• Information theory: Information theory deals with the quantification, It includes

concepts such as entropy (which measures the uncertainty of a random variable),

mutual information (which measures the amount of information shared by two

random variables), and the Kullback-Leibler divergence (which measures the

difference between two probability distributions). Information theory is used in

machine learning for tasks such as feature selection, data compression, and data
 Cont. …
• Optimization: Optimization is the process of finding the best solution to a problem. It
includes concepts such as gradient descent (which is used to find the minimum of a
function) and stochastic gradient descent (which is a variation of gradient descent that
uses a random subset of data to estimate the gradient). Optimization is used in machine
learning for tasks such as finding the best model parameters and minimizing the loss
function.

• Graph theory: Graph theory deals with the study of networks and connectivity. It
includes concepts such as graphs (which are mathematical structures that model
relationships between objects), nodes (which are the objects in a graph), edges (which
are the connections between objects in a graph), and centrality (which measures the
importance of nodes in a graph). Graph theory is used in machine learning for tasks such
as clustering, community detection, and network analysis.
 Applications of machine learning
Machine learning has a wide range of applications across different industries and fields.
Here are some examples:

• Image and Speech Recognition: Machine learning is used to recognize images and
speech in real-time. It is used in applications such as facial recognition, voice
recognition, and object detection.

• Fraud Detection: Machine learning is used to detect fraud in financial transactions. It

can be used to identify fraudulent transactions, detect unusual patterns, and flag
suspicious activities.

• Healthcare: Machine learning is used in healthcare for diagnosis, treatment planning,

and drug development. It can be used to analyze medical images, predict patient
outcomes, and develop personalized treatment plans.

• Predictive Maintenance: Machine learning is used in industrial settings to predict when

machines will fail and need maintenance. This helps reduce downtime and improve
productivity.
 Cont. …
• Natural Language Processing: Machine learning is used in natural language

processing to enable machines to understand human language. It is used in applications

such as chatbots, voice assistants, and language translation.

• Marketing: Machine learning is used in marketing to analyze customer behavior and

preferences. It can be used to personalize marketing campaigns and recommend

products to customers.

• Autonomous Vehicles: Machine learning is used in autonomous vehicles to enable

them to perceive their environment and make decisions. It is used in applications such as

self-driving cars and drones.

• Financial Forecasting: Machine learning is used in finance to forecast stock prices,

predict market trends, and identify investment opportunities.

 Types of machine learning techniques

• A machine can learn to solve a problem

by following any one of the following
four techniques.
• These are the ways in which a machine
can learn:
1. Supervised Learning
2. Unsupervised Learning
3. Semi-supervised learning
4. Reinforcement Learning
 Supervised Learning
• Supervised learning is a technique in which we teach or
train the machine using data which is well labeled.
• To understand Supervised Learning let’s consider an
example.
As kids need guidance to solve math problems. The teachers
helped them understand what addition is and how it is done.
Similarly, you can think of supervised learning as a type of
Machine Learning that involves a guide.
• Types of problem
 Regression
 Classification
 Supervised Learning Cont.

Here we’re feeding the machine images of Tom and Jerry and the goal
is for the machine to identify and classify the images into two groups
(Tom images and Jerry images). The training data set that is fed to
the model is labeled, as in, we’re telling the machine, ‘this is how Tom
looks and this is Jerry’. By doing so you’re training the machine by
using labeled data.
 Unsupervised Learning
• “Unsupervised learning involves training by using unlabeled data
and allowing the model to act on that information without
guidance.”
• Think of unsupervised learning as a smart kid that learns without
any guidance.
• In this type of Machine Learning, the model is not fed with labeled
data, as in the model has no clue that ‘this image is Tom and this is
Jerry’, it figures out patterns and the differences between Tom and
Jerry on its own by taking intentions of data.
• Types of Problem
 Clustering
 Association
 Unsupervised Learning Cont.

For example, it identifies prominent features of Tom such as pointy

ears, bigger size, etc, to understand that this image is of type 1.
Similarly, it finds such features in Jerry and knows that this image is
of type 2. Therefore, it classifies the images into two different classes
without knowing who Tom is or Jerry is.
 Semi-supervised learning
• Semi-supervised learning offers a happy medium between
supervised and unsupervised learning.

• During training, it uses a smaller labeled data set to guide

classification and feature extraction from a larger, unlabeled
data set.

• Semi-supervised learning can solve the problem of having not

enough labeled data (or not being able to afford to label enough
data) to train a supervised learning algorithm.
• Types of problem
 Combination of tasks in both supervised and unsupervised
 Reinforcement Learning
• Reinforcement learning can be thought of as a try and error method of
learning. The machine gets a Reward or Penalty point for each action it
performs. If the option is correct, the machine gains the reward point or
gets a penalty point in case of a wrong response.
• The reinforcement learning algorithm is all about the interaction between
the environment and the learning agent. The learning agent is based on
exploration and exploitation.
• Exploration is when the learning agent acts on trial and error and
Exploitation is when it performs an action based on the knowledge gained
from the environment.
• The environment rewards the agent for every correct action, which is the
reinforcement signal. With the aim of collecting more rewards obtained,
the agent improves its environment knowledge to choose or perform the
next action.
• Types of problem
 Reward based
 Reinforcement Learning Example
Let see how Pavlov trained his dog using
reinforcement training?
Pavlov divided the training of his dog into four stages.
• In the first part, Pavlov gave meat to the dog, and in
response to the meat, the dog started salivating.
• In the next stage he created a sound with a bell, but this
time the dogs did not respond anything.
• In the third stage, he tried to train his dog by using the
bell and then giving them food. Seeing the food the dog
started salivating.
• Eventually, the dogs started salivating just after hearing
the bell, even if the food was not given as the dog was
reinforced that whenever the master will ring the bell, he
will get the food.
Reinforcement Learning Example Cont.
20