Lecture Topic 1.1.

1
06 February 2024 12:36

Introduction to Machine learning

learning
Learning is “a process that leads to change, which occurs as a result of experience and increases the potential for improved
performance and future learning” (Ambrose et al, 2010, p.3). The change in the learner may happen at the level of
knowledge, attitude or behavior. As a result of learning, learners come to see concepts, ideas, and/or the world differently.

Machine learning
A subset of artificial intelligence known as machine learning focuses primarily on the creation of algorithms that enable a
computer to independently learn from data and previous experiences. Arthur Samuel first used the term "machine
learning" in 1959. It could be summarized as follows:
• Without being explicitly programmed, machine learning enables a machine to automatically learn from data, improve
performance from experiences, and predict things.
• Machine learning algorithms create a mathematical model that, without being explicitly programmed, aids in making
predictions or decisions with the assistance of sample historical data, or training data. For the purpose of developing
predictive models, machine learning brings together statistics and computer science. Algorithms that learn from
historical data are either constructed or utilized in machine learning. The performance will rise in proportion to the
quantity of information we provide.
• A machine can learn if it can gain more data to improve its performance.
• A machine learning system builds prediction models, learns from previous data, and predicts the output of new data
whenever it receives it. The amount of data helps to build a better model that accurately predicts the output, which in
turn affects the accuracy of the predicted output.
Let's say we have a complex problem in which we need to make predictions. Instead of writing code, we just need to
feed the data to generic algorithms, which build the logic based on the data and predict the output. Our perspective on
the issue has changed as a result of machine learning. The Machine Learning algorithm's operation is depicted in the
following block diagram:

Tom M. Mitchell has defined machine learning as

"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."

Features of Machine Learning:

• Machine learning uses data to detect various patterns in a given dataset.
• It can learn from past data and improve automatically.
• It is a data-driven technology.
• Machine learning is much similar to data mining as it also deals with the huge amount of the data.
Classification of Machine Learning based on Learning Problems

ML Page 1
Classification of Machine Learning based on Learning Problems
At a broad level, machine learning can be classified into three types:
1. Supervised learning
2. Unsupervised learning
3. Reinforcement learning

1) Supervised Learning
In supervised learning, sample labeled data are provided to the machine learning system for training, and the
system then predicts the output based on the training data.
The system uses labeled data to build a model that understands the datasets and learns about each one. After
the training and processing are done, we test the model with sample data to see if it can accurately predict the
output.
The mapping of the input data to the output data is the objective of supervised learning. The managed learning
depends on oversight, and it is equivalent to when an understudy learns things in the management of the
educator.

Key Features of Supervised Learning:

1. Labeled Data:
○ The training dataset consists of input-output pairs where the desired output is already known.
2. Goal:
○ To learn a function f(x) that maps input x to output y, such that: y=f(x)
○ This function can then be used to predict the output for new inputs.
3. Feedback:
○ The model's predictions are compared with the actual labels to calculate the error, which is then used to
adjust the model to improve accuracy.

Types of Supervised Learning:

1. Classification:
○ The target variable is categorical, and the goal is to assign inputs to one of the predefined categories.
○ Examples:
 Spam detection (spam or not spam).
 Disease diagnosis (e.g., cancerous or non-cancerous).
 Sentiment analysis (positive, negative, or neutral).
2. Regression:
○ The target variable is continuous, and the goal is to predict numerical values.
○ Examples:
 Predicting house prices.
 Estimating stock market trends.
 Forecasting weather.
2) Unsupervised Learning
Unsupervised learning is a learning method in which a machine learns without any supervision.
The training is provided to the machine with the set of data that has not been labeled, classified, or categorized,
and the algorithm needs to act on that data without any supervision. The goal of unsupervised learning is to
ML Page 2
and the algorithm needs to act on that data without any supervision. The goal of unsupervised learning is to
restructure the input data into new features or a group of objects with similar patterns.
In unsupervised learning, we don't have a predetermined result. The machine tries to find useful insights from the
huge amount of data.

Key Features of Supervised Learning:

• Input: The dataset contains only input features (no labeled output).
• Goal: The model identifies patterns, clusters, or associations in the data.
Types of Unsupervised Learning:
1. Clustering:
○ Groups similar data points into clusters.
○ Example algorithms: K-Means, DBSCAN, Hierarchical Clustering.
2. Dimensionality Reduction:
○ Reduces the number of features while retaining the essential information.
○ Example algorithms: Principal Component Analysis (PCA), t-SNE.
3. Association Rule Learning:
○ Identifies relationships between variables (e.g., market basket analysis).
○ Example algorithms: Apriori, Eclat.
Examples:
• Customer segmentation based on purchasing behavior (clustering).
• Identifying hidden patterns in genomic data (dimensionality reduction).
• Market basket analysis for recommending products (association rules).

3) Reinforcement Learning
Reinforcement learning is a feedback-based learning method, in which a learning agent gets a reward for each
right action and gets a penalty for each wrong action. The agent learns automatically with these feedbacks and
improves its performance. In reinforcement learning, the agent interacts with the environment and explores it. The
goal of an agent is to get the most reward points, and hence, it improves its performance.
The key components of RL are:
1. Agent: The entity that makes decisions (e.g., a robot, software program).
2. Environment: The world or system in which the agent operates.
3. State (S): The current situation or configuration of the environment.
4. Action (A): The set of possible moves the agent can make.
5. Reward (R): The feedback signal received after taking an action.
6. Policy (π): The strategy the agent uses to decide which action to take in a given state.
7. Value Function (V): A measure of the long-term reward associated with states or state-action pairs.
8. Goal: To maximize cumulative rewards over time (e.g., achieving high scores or completing tasks efficiently).
How RL Works
• The agent observes the state of the environment.
• It selects an action based on its policy.
• The environment transitions to a new state and provides a reward.
• The agent updates its policy based on this feedback, learning to make better decisions over time.

Key Differences Among Supervised Learning, Unsupervised Learning, and Reinforcement Learning
Feature Supervised Learning Unsupervised Learning Reinforcement Learning
Definition Learns from labeled data (input- Learns from unlabeled Learns by interacting with an
output pairs). data to find hidden environment to maximize a reward
patterns. signal.
Goal Predict the outcome for new data Discover underlying Learn a sequence of actions to
based on past examples. structure, clusters, or achieve the best outcome.
associations.
Data Type Labeled data (input features + Unlabeled data (input No labeled data; relies on feedback
output labels). features only). (rewards or penalties).
Output Prediction of labels or continuous Groupings, clusters, or A policy or strategy to take actions

ML Page 3
Output Prediction of labels or continuous Groupings, clusters, or A policy or strategy to take actions
values. reduced dimensionality. in an environment.
Examples of Linear Regression, SVM, Decision K-Means, PCA, Q-Learning, Deep Q-Networks
Algorithms Trees. DBSCAN. (DQN), Policy Gradients.
Learning Learns a mapping function from Identifies patterns or Learns through trial and error,
Process inputs to outputs. structures in data. optimizing long-term rewards.
Example Use - Spam detection (classification). - Customer - Game-playing AI (e.g., Chess,
Cases - Predicting house prices segmentation Go).
(regression). (clustering). - Autonomous driving.
- Dimensionality
reduction for
visualization.
Feedback Direct feedback through labels. No feedback, purely Feedback in the form of rewards
Type exploratory. and penalties.
Exploration Focuses on minimizing error Focuses on finding Balances exploration (trying new
vs. between predictions and labels. hidden relationships or things) and exploitation (using
Exploitation grouping. known strategies).
Training Easier to implement with labeled More complex due to Computationally intensive due to
Complexity data. lack of labeled data. iterative interaction with the
environment.
Key Requires labeled data, which can Defining the usefulness Managing the exploration-
Challenge be expensive or time-consuming of discovered patterns. exploitation trade-off and ensuring
to generate. convergence.

ML Page 4