You are on page 1of 4

WHAT IS MACHINE LEARNING?

A concept that a computer program can learn and adjust to new data without human
interference. Machine learning started from pattern recognition and the theory that computers can
learn without being programmed to perform required specific tasks.

source:https://bit.ly/3mLzew4

Artificial intelligence scientists developed an idea to see if computers could learn from data. The
iterative aspect of machine learning as important as the theory behind this was to feed the model
with new data, as they were supposed to independently adjust. Learning was done from previous
computations to produce reliable, repeatable decisions and results.

Two definitions of Machine Learning are offered. Arthur Samuel described it as: "the field of study
that gives computers the ability to learn without being explicitly programmed."

source:https://bit.ly/3xt4HIh

Tom Mitchell provides a more modern definition: "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."

© 2023 Athena Global Education. All Rights Reserved


Examples of Machine learning

Self-driving Google car


Online recommendation offers such as those from Amazon etc.
Fraud detection.

Artificial Intelligence (AI) has far surpassed the publicity of blockchain and quantum computing.
The developers use this idea in creating new Machine Learning models and they're-train the existing
models for better performance and results. The easy availability of High-Performance Computing
(HPC) has resulted in a sudden increased demand for IT professionals having Machine Learning skills.

Applications of AI with Machine Learning Concepts

Tagging a face in a Facebook photo


Using Google Directions (Google Maps) to learn real-time traffic situations and shortcuts to
reach destinations.

Planning a Learning System

• Selecting the Training Experience

• Selecting the Target Function

• Selecting a Representation for the Target Function

• Selecting a Function Approximation Algorithm

• The Final Design (Output)

Significance of Machine Learning

Various components like the availability of huge amounts of data, cheaper computational processing,
and powerful but affordable data storage led to machine learning.

© 2023 Athena Global Education. All Rights Reserved


A precise model gave the organization a chance to identify useful opportunities and helped in
avoiding unknown risks. Easy access to all these things meant that it was possible to quickly produce
models that can analyze bigger, more complex data which delivered faster, more accurate results.

The best part of this was to analyze, understand and identify a pattern in the data. The main
advantage was that the computer could be trained to do tasks that would be exhaustive
or impossible for a human being. It was a clear break from traditional analysis as machine
learning could help one to make decisions with minimum human intervention.

Statistical Methods

The development of AI applications started with the age-old traditional statistical methods. Several
such methods are successfully applied to AI programs, which are much more complex and use
techniques far beyond statistical methods.

source:https://bit.ly/3mMKAA0

The Examples of Statistical Methods used for developing AI Applications are:

© 2023 Athena Global Education. All Rights Reserved


Regression
Classification
Clustering
Probability Theories
Decision Trees

Based on limited data; the above-mentioned methods will be used. However, the data is abundant
nowadays. To explore this kind of huge data statistical methods alone will not be enough as they have
their limitations. For this more advanced methods such as deep learning were developed to solve
many complex problems.

© 2023 Athena Global Education. All Rights Reserved

You might also like