TRYEngineering - AI Adventures - 7

Deep Learning & Neural Networks
People use deep learning, a more advanced type of machine learning, to
train AI. Deep learning uses a neural network with many layers to find some
patterns that are hard to see initially. The more layers it has, the deeper it
processes. A neural network works like a human brain with nodes resembling
brain cells. However, unlike your brain, a neural network groups its nodes into
layers, and communicates with nearby nodes to process information. Through
all those layers, the node fully processes the information and " thinks " through
its response. It's like thinking about something with friends versus thinking about
it by yourself. The more people you have, the more you can figure out together
by talking to each other! If you're making an AI that works off of deep learning,
it can use its neural network to understand difficult patterns and " think " through
complex decisions.
Computer Vision
Now, AI can process information very deeply and learn how to do tasks, but
what if it could see the world around it, like real people? Computer vision a
field of AI, enables an AI program to interpret visual data like pictures or videos.
This is how it can look at images and identify what's in them, a feature that is
also used in self-driving cars! It basically gives AI eyes to see what's around it,
enabling it to comprehend what's happening in the real world!
Image Source: " The future of computer vision with the TensorFlow Object Detection API from Google " . by ShashiBellamkonda
is licensed under CC BY 2.0. https://creativecommons.org/licenses/by/2.0/?ref=openverse
The Nobel Prize in Physics
and AI Research
g
w
Artificial Intelligence: Technology
that makes machines smart, allowing
them to " think " and solve problems
like people do.
Machine Learning: Machines
improve at tasks by learning from
examples (data) instead of following
specific coded instructions.
Neural Network: A computer
program made up of many connected
parts, like a web, that work together to
learn and make decisions.
Deep Learning: A special kind of
machine learning that uses very large
neural networks with many layers to
learn from huge amounts of data.
The Nobel Prize Committee
surprised everyone by giving
the 2024 Physics Award to
John J. Hopfield and Geoffrey
E. Hinton. They won for their
important work on neural
networks, which are like the
brains of AI. In the 1980s, they
wrote papers explaining how
these networks work. Even
though their ideas were simpler
than the AI we use today, such
as ChatGPT, their work laid the
foundation for all the cool AI
technology we have now!
EXPLORE more in this
article: Why the Nobel
Prize in Physics went
to AI Research
Mission: Neural Networks in
Action
TRY: Play the AI Quick,
Draw game by Google!
Help teach it by adding
your drawings to the world's
largest doodling data set, shared
publicly to help with machine
learning research. You draw,
and a neural network tries to
guess what you're drawing. By
playing, you are helping make AI
smarter. Have fun!
https://quickdraw.withgoogle.com/
n
A
r
e
t
i
a
e
fi
c
i
c
i
h
u
a
i
e
n
I
l
n
r
n
e
a
t
l
e
L
l
p
r
i
l
e
e
g
a
N
k
n
r
a
c
n
r
e
i
e
M
N
o
n
t
L
g
D
e

https://quickdraw.withgoogle.com/ https://creativecommons.org/licenses/by/2.0/?ref=openverse https://spectrum.ieee.org/nobel-prize-in-physics?utm_source=feedotter&utm_medium=email&utm_campaign=aialert-10-16-24&utm_content=httpsspectrumieeeorgchatgptreliability&mkt_tok=NzU2LUdQSC04OTkAAAGWNJtycvAQYsNgi74jQue4ybjkVrGsQcs59VLFAiSpkAXih3DpwMq6HRSWlb2tqCTFEu3_ZB8-yJb1VUS-OEu66363iQQJDmwlvRHSPE9soOC-y-c https://spectrum.ieee.org/nobel-prize-in-physics?utm_source=feedotter&utm_medium=email&utm_campaign=aialert-10-16-24&utm_content=httpsspectrumieeeorgchatgptreliability&mkt_tok=NzU2LUdQSC04OTkAAAGWNJtycvAQYsNgi74jQue4ybjkVrGsQcs59VLFAiSpkAXih3DpwMq6HRSWlb2tqCTFEu3_ZB8-yJb1VUS-OEu66363iQQJDmwlvRHSPE9soOC-y-c https://spectrum.ieee.org/nobel-prize-in-physics?utm_source=feedotter&utm_medium=email&utm_campaign=aialert-10-16-24&utm_content=httpsspectrumieeeorgchatgptreliability&mkt_tok=NzU2LUdQSC04OTkAAAGWNJtycvAQYsNgi74jQue4ybjkVrGsQcs59VLFAiSpkAXih3DpwMq6HRSWlb2tqCTFEu3_ZB8-yJb1VUS-OEu66363iQQJDmwlvRHSPE9soOC-y-c https://spectrum.ieee.org/nobel-prize-in-physics?utm_source=feedotter&utm_medium=email&utm_campaign=aialert-10-16-24&utm_content=httpsspectrumieeeorgchatgptreliability&mkt_tok=NzU2LUdQSC04OTkAAAGWNJtycvAQYsNgi74jQue4ybjkVrGsQcs59VLFAiSpkAXih3DpwMq6HRSWlb2tqCTFEu3_ZB8-yJb1VUS-OEu66363iQQJDmwlvRHSPE9soOC-y-c

TRYEngineering - AI Adventures

Table of Contents for the Digital Edition of TRYEngineering - AI Adventures