What is Supervised Learning?
Definition: In machine learning and artificial intelligence, supervised learning refers to a class of systems and
algorithms that determine a predictive model using data points with known outcomes. The model is learned
by training through an appropriate learning algorithm (such as linear regression, random forests, or neural
networks) that typically works through some optimization routine to minimize a loss or error function.
Another Definition: Supervised learning is the process of teaching a model by feeding it input data as well
as correct output data. This input/output pair is usually referred to as "labeled data."
Think of a teacher who, knowing the correct answer, will either reward marks to or take marks from a student
based on the correctness of her response to a question. Supervised learning is often used to create machine
learning models for two types of problems.
• Regression - The model finds outputs that are real variables (number which can have decimals.)
• Classification - The model finds classes in which to place its inputs.
Training, Test, and Validation
The first step in the supervised learning process is to gather labeled training data. The label is the output and
provides feedback for the algorithm. Provided enough data is available, the next step is to split this labeled
data into three sets: training, testing, and validation. The algorithm uses training set to adjust the model to
minimize the error. For example the training set may contain a variety of animal pictures with a label
associated to each picture, allowing the algorithm to compare the predicted label with the correct one.
The validation set is disjoint from the training set and allows one to independently measure the progress of
the learning algorithm. This measure can be used to determine a cutoff point in the training algorithm to
balance the accuracy of the learned model versus overfitting.
The test set is the final set and it is meant to be used only when the model has been found to be optimal on the
validation set. This set provides a ‘real world’ evaluation of the model’s performance on never-before-seen
data. Test data is a kind of ‘final exam’ for a model which has learned its training data effectively and can
generalize to new data.
Supervised Learning vs Unsupervised Learning
If supervised learning may be compared to a teacher-student relationship, unsupervised learning can be
thought of as how a child might learn language by independently finding structure from the given input. No
labels are supplied during training for unsupervised learning, and hence different learning algorithms are
required.
Parameters Machine Learning Deep Learning
Definition and It is an application and subset of AI (Artificial It is basically a subset of machine
Meaning Intelligence) that provides a system with the learning that relates the recurrent
ability to learn from its experiences and neural networks and artificial
improve accordingly without someone neural networks together.
physically programming those changes into it.
Correlation It forms the superset of the process of deep It constitutes a subset of machine
learning. learning.
Represented The data that gets represented in this case is The data that gets represented in
Data very different because machine learning makes this case is also pretty different
use of unstructured information and data. because deep learning makes use of
ANN (neural networks).
Data Points It contains thousands of different data points. It consists of big data. It means that
millions of data points are present
in it.
Process of Artificial intelligence evolves into machine Machine learning evolves into
Evolution learning. deep learning. In simpler words,
deep learning refers to how deep/
detailed machine learning can get.
Outputs It consists of numerical values, such as the It consists of everything from the
classification of scores. free-form elements (like free sound
and text) to the numerical values.
Use of Machine learning utilizes a number of Deep learning utilizes a neural
Algorithms automated algorithms. These turn into various network passing data through
model functions for predicting future actions various processing layers. These
out of data. interpret the features of the present
data and their relations.
Detection and Various data analysts detect and examine the The algorithms present in deep
Depiction of algorithms for analyzing the specified variables learning basically undergo self-
Algorithms present in data sets. depiction on data analysis when
they reach production.
Uses Machine learning is capable of helping a system Deep learning is capable of solving
when it needs to stay in the competition while various complex issues that
still learning new things parallelly. concern machine learning in a
system.
