Uploaded by Rakshit Sharma

What is Machine Learning Machine Learning Basics

advertisement
What is Machine Learning? | Machine Learning Basics
Introduction to Machine Learning
In this session, we will explore the world of machine learning. We will discuss its real-life
applications, challenges faced before its emergence, how it has evolved over time, and its
importance. We will also talk about the types of machine learning, algorithms, and
breakthroughs that machine learning has brought about, and what a career in machine learning
entails.
Real-life Applications
Machine learning plays an integral role in our day-to-day lives. Some of the real-life applications
where machine learning is applied include:
Netflix recommendations
Facial recognition on Facebook
Online transaction verification on PayPal
Challenges before Machine Learning
Before machine learning became widely used, AI systems were mostly rule-based, and their
state representations had to be manually coded. The main disadvantage was that these
systems would fail outside what their roles were coded for, making them not very useful in
real-life applications.
Evolution of Machine Learning
Machine learning has evolved over time. It all started in the 1950s when Alan Turing came up
with the Turing machine. Since then, there have been several breakthroughs, including IBM
Deep Blue's win over world champion Gary Kasparov in chess and Google's AlphaGo's win over
the world champion in the game of Go.
Importance of Machine Learning
Machine learning has changed our lives in several significant ways. It allows powerful and faster
processing of complicated data, making decisions and predictions more accurate. It also
enables affordable data management and analysis of complex big data.
Types of Machine Learning
Machine learning is divided into three major types:
Supervised Learning
Unsupervised Learning
Reinforcement Learning
Supervised Learning
Supervised machine learning is a method where a model after sufficient training is able to make
predictions for the future. The model is trained using a question-answer pattern, and when new
data is encountered, it can make a prediction based on what it has learned. An example of
supervised learning is spam filtering in email clients like Microsoft Outlook and Gmail.
Unsupervised Learning
Unsupervised learning only deals with input data and analyzes it to find patterns or similarities. It
learns from observations and is able to find structures and relationships among the input data.
An example of unsupervised learning is Facebook's ability to identify people in photos by
analyzing your friends' photos.
Reinforcement Learning
Reinforcement learning allows a computer to take a decision based on past rewards for its
actions. This type of machine learning is usually used to increase the efficiency of a tool or
program.
Introduction to Machine Learning Algorithms
Machine learning is a subset of artificial intelligence that focuses on building algorithms that can
learn from data and make predictions or decisions based on that learning. In this article, we'll
cover some of the most widely used machine learning algorithms and their applications.
Types of Machine Learning
There are three main types of machine learning: supervised learning, unsupervised learning,
and reinforcement learning. In supervised learning, the algorithm is given labeled data to learn
from. In unsupervised learning, the algorithm is given unlabeled data and must find structure
within that data. In reinforcement learning, the algorithm learns by receiving feedback on its
actions.
Supervised Learning Algorithms
Supervised learning algorithms are used for classification and regression problems. In
classification, the algorithm must predict whether an observation belongs to a certain class. In
regression, the algorithm must predict a numerical value based on past data.
Naive Bayes: Used for classification problems, such as spam filtering.
Linear Regression: Used for regression problems, such as weather prediction.
Unsupervised Learning Algorithms
Unsupervised learning algorithms are used for clustering and association problems. In
clustering, the algorithm groups similar observations together. In association, the algorithm
identifies patterns of association between different variables.
K-means: Used for clustering problems, such as optimal tower placement for network providers.
Market Basket Analysis: Used for association problems, such as suggesting new items to
customers based on past purchases.
Applications of Machine Learning
Machine learning has found applications in many fields, including healthcare, finance, and
gaming. One of the most exciting developments in machine learning is the creation of artificial
intelligence systems that function like a human brain.
DeepMind Technologies: A British company that creates AI systems to detect eye diseases and
play video games.
Self-driving Cars: Cars that can travel from one point to another without human intervention.
Career Prospects in Machine Learning
Machine learning engineers are in high demand and can expect to work on projects such as
creating AI systems that make decisions on their own without being programmed.
Skills: Mathematics, statistics, and software design.
Future of Machine Learning
In the future, we can expect deeper personalization, self-driving cars, smarter investment
opportunities, and better medical diagnosis.
Understanding Machine Learning
Machine learning involves computers imitating and adapting to human-like behavior, making
decisions based on past data. It has three types: supervised, unsupervised, and reinforcement
learning. Supervised learning predicts outputs based on past data, unsupervised learning
detects hidden patterns in input data, while reinforcement learning's next course of action is
based on past feedback.
Machine Learning Algorithms
Machine learning algorithms solve problems like classification, where we determine a yes or no
prediction, and regression, where we predict a value based on past data. In unsupervised
learning, clustering divides observations into clusters, while association determines patterns of
association between different items or variables.
The Skills of a Machine Learning Engineer
A good machine learning engineer should have a strong foundation in mathematics and
statistics, software design, applying machine learning libraries and algorithms, data modeling,
and programming languages. They should also be adept at data engineering, running machine
learning experiments, deploying solutions into production, implementing custom machine
learning code, and performing feature engineering.
Trends in Machine Learning
The machine learning market is expected to grow from 1.03 billion to 8.81 billion dollars by the
year 2022, indicating a bright future for individuals skilled in the concept. The graph shows an
increased interest in topics related to machine learning, and job postings in the field have been
on the rise.
Download