Streamlining Python Development: A Guide to a Modern Project Setup
Nikolas Perrault | Machine Learning versus Artificial Intelligence versus Deep Learning
1. M A C H I N E
L E A R N I N G V E R S U S
A R T I F I C I A L
I N T E L L I G E N C E
V E R S U S D E E P
L E A R N I N G
N I K O L A S P E R R A U L T
2. T H E R I S E O F A I
Most technology news as of late somehow relates back to
artificial intelligence. The seemingly complex and high-
brow technology is integrated into mundane items, such
as Amazon’s Alexa or Google Home. With talk of artificial
intelligence comes machine learning and deep machine
learning. The three phrases can often be conflated, but do
refer to three specific technologies.
3. N O T T H E
S A M E T H I N G
Artificial intelligence and machine
learning are related but are not the same
thing. Artificial intelligence is the broad
concept of the ability of machines to
carry out tasks in a smart way. Machine
learning is a current use of AI technology
based on the notion that machines
should be given access to data and learn
for themselves.
4. A P P L I E D O R
G E N E R A L
Artificial intelligence is typically classified into one of two
groups: applied or general. Applied AI are systems designed to
trade stocks or drive an autonomous car. It’s the more common
use of the technology. General AI are systems that can handle
any task, in theory.
5. A R T H U R S A M U E L
The emergence of machine learning as the driving force
behind AI innovations was the result of two major
breakthroughs. The first occurred in 1959 when Arthur
Samuel had the realization that it may be more useful to
teach computers to learn about the world itself, rather
than teaching it everything it needed to know. The other
major turning point was the emergence of the internet,
and the vast increase in the amount of digital information
that is now generated, stored and made available for
analysis.
6. D E E P
L E A R N I N G
Deep learning is a subset of machine
learning. Technically, it is machine
learning and functions similarly, but the
capabilities differ. Deep learning can
learn through its own form of computing.
It’s designed to analyze data continuously
with a similar logic structure to humans.
Deep learning is what powers human-like
AI. It relies on an artificial neural
network to do this. Deep refers to the
many layers that make up the neural
network. Having multiple layers is what
allows the neural networks to learn parts
of the data in a type of hierarchy.
7. N E U R A L
N E T W O R K S
Neural networks are essential to teaching computers how
to understand the world as a human does. A neural
network is a computer system that is designed to classify
information just as a human brain does. It can learn to
recognize images and categorize them based on what
elements they contain.
Deep learning results in higher accuracy but requires
more hardware and time training. Regular machine
learning requires less advanced machinery to function.