0% found this document useful (0 votes)
14 views

Machine Learning

Machine learning is a type of artificial intelligence that enables computers to learn from data without being explicitly programmed. It involves training machine learning models using model training algorithms on datasets to solve problems like predicting outputs or finding patterns in data. Common machine learning tasks include supervised learning where training data includes labels, and unsupervised learning where there are no labels.

Uploaded by

tapstaps902
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
14 views

Machine Learning

Machine learning is a type of artificial intelligence that enables computers to learn from data without being explicitly programmed. It involves training machine learning models using model training algorithms on datasets to solve problems like predicting outputs or finding patterns in data. Common machine learning tasks include supervised learning where training data includes labels, and unsupervised learning where there are no labels.

Uploaded by

tapstaps902
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 6

Machine Learning

AI refers to the Broad Capability of Machines to perform activities using human like
intelligence.
Machine learning (ML) is a modern software development technique, and a type of artificial
intelligence (AI), that enables computers to solve problems by using examples of real-world
data. It allows computers to automatically learn and improve from experience without being
explicitly programmed to do so.
Video link - https://youtu.be/dZN6Jw_upS0

Summary
Machine learning is part of the broader field of artificial intelligence. This field is concerned
with the capability of machines to perform activities using human-like intelligence. Within
machine learning there are several different kinds of tasks or techniques:

 In supervised learning, every training sample from the dataset has a corresponding
label or output value associated with it. As a result, the algorithm learns to predict
labels or output values. We will explore this in-depth in this lesson.
 In unsupervised learning, there are no labels for the training data. A machine
learning algorithm tries to learn the underlying patterns or distributions that govern
the data. We will explore this in-depth in this lesson.
 In reinforcement learning, the algorithm figures out which actions to take in a
situation to maximize a reward (in the form of a number) on the way to reaching a
specific goal. This is a completely different approach than supervised and
unsupervised learning. We will dive deep into this in the next lesson.

In traditional problem-solving with software, a person analyzes a problem and engineers a


solution in code to solve that problem. For many real-world problems, this process can be
laborious (or even impossible) because a correct solution would need to take a vast number of
edge cases into consideration.

Imagine, for
example, the

challenging task of writing a program that can detect if a cat is present in an image. Solving
this in the traditional way would require careful attention to details like varying lighting
conditions, different types of cats, and various poses a cat might be in.
In machine learning, the problem solver abstracts away part of their solution as a flexible
component called a model, and uses a special program called a model training algorithm to
adjust that model to real-world data. The result is a trained model which can be used to
predict outcomes that are not part of the dataset used to train it.
In a way, machine learning automates some of the statistical reasoning and pattern-matching
the problem solver would traditionally do.

The overall goal is to use a model created by a model-training algorithm to generate


predictions or find patterns in data that can be used to solve a problem.

Machine learning is a new field created at the intersection of statistics, applied math, and
computer science. Because of the rapid and recent growth of machine learning, each of these
fields might use slightly different formal definitions of the same terms.
Terminology
Machine learning, or ML, is a modern software development technique that enables
computers to solve problems by using examples of real-world data.
In supervised learning, every training sample from the dataset has a corresponding label or
output value associated with it. As a result, the algorithm learns to predict labels or output
values.
In reinforcement learning, the algorithm figures out which actions to take in a situation to
maximize a reward (in the form of a number) on the way to reaching a specific goal.
In unsupervised learning, there are no labels for the training data. A machine learning
algorithm tries to learn the underlying patterns or distributions that govern the data.

Components of Machine Learning


Nearly all tasks solved with machine learning involve three primary components:
 A machine learning model
 A model training algorithm
 A model inference algorithm

Video link - https://youtu.be/w0R0VnImVK8


Reviewing the clay analogy of machine learning
You can understand the relationships between these components by imagining the stages of
crafting a teapot from a lump of clay.

1. First, you start with a block of raw clay. At this stage, the clay can be molded into
many different forms and be used to serve many different purposes. You decide to use
this lump of clay to make a teapot.
2. So how do you create this teapot? You inspect and analyze the raw clay and decide
how to change it to make it look more like the teapot you have in mind.

3.

Next, you mold the clay to make it look more like the teapot that is your goal.

Congratulations! You've completed your teapot. You've inspected the materials, evaluated
how to change them to reach your goal, and made the changes. The teapot is now ready for
your enjoyment.

A machine learning model, like a piece of clay, can be molded into many different forms and
serve many different purposes. A more technical definition would be that a machine learning
model is a block of code or framework that can be modified to solve different but related
problems based on the data provided.
Important
A model is an extremely generic program (or block of code), made specific by the data used
to train it. It is used to solve different problems.

Two simple examples


Example 1

Imagine you own a snow cone cart, and you have some data about the average number of
snow cones sold per day based on the high temperature. You want to better understand this
relationship to make sure you have enough inventory on hand for those high sales days.

In the graph above, you can see one example of a model, a linear regression model (indicated
by the solid line). You can see that, based on the data provided, the model predicts that as the
high temperature for the day increases so do the average number of snow cones sold. Sweet!

Example 2

Let's look at a different example that uses the same linear regression model, but with different
data and a completely different question to answer.
Imagine that you work in higher education and you want to better understand the relationship
between the cost of enrollment and the number of students attending college. In this example,
our model predicts that as the cost of tuition increases, the number of people attending
college is likely to decrease.

Using the same linear regression model (indicated by the solid line), you can see that the
number of people attending college does go down as the cost increases.
Both examples showcase that a model is a generic program made specific by the data used to
train it.
How are model training algorithms used to train a model?
In the preceding section, we talked about two key pieces of information: a model and data. In
this section, we show you how those two pieces of information are used to create a trained
model. This process is called model training.
Model training algorithms work through an interactive process
Let's revisit our clay teapot analogy. We've gotten our piece of clay, and now we want to
make a teapot. Let's look at the algorithm for molding clay and how it resembles a machine
learning algorithm:

 Think about the changes that need to be made. The first thing you would do is
inspect the raw clay and think about what changes can be made to make it look more
like a teapot. Similarly, a model training algorithm uses the model to process data and
then compares the results against some end goal, such as our clay teapot.
 Make those changes. Now, you mold the clay to make it look more like a teapot.
Similarly, a model training algorithm gently nudges specific parts of the model in a
direction that brings the model closer to achieving the goal.
 Repeat. By iterating these steps over and over, you get closer and closer to what you
want, until you determine that you’re close enough and then you can stop.

To get started, it is important to follow these two important steps

Step 1: Define a very specific task


Think back to the snow cone sales example. Now imagine that you own a frozen treats store
and you sell snow cones along with many other products. You wonder, "How do I increase
sales?" It's a valid question, but it's the opposite of a very specific task. The following
examples demonstrate how a machine learning practitioner might attempt to answer that
question.

 Question: Does adding a $1.00 charge for sprinkles on a hot fudge sundae increase
the sales of hot fudge sundaes?
 Question: Does adding a $0.50 charge for organic flavors in your snow cone increase
the sales of snow cones?

Step 2: Identify the machine learning task we might use to solve this problem

 This helps you better understand the data you need for a project.
What exactly is a machine learning task?

All model training algorithms, and the models themselves, take data as their input. Their
outputs can be very different and are classified into a few different groups, based on the task
they are designed to solve.
Often, we use the kind of data required to train a model as part of defining a machine learning
task.
In this lesson, we will focus on two common machine learning tasks:

 Supervised learning
 Unsupervised learning

You might also like