Submitted by: shamli sharma(86)

Submitted to : Mrs.Kavita
Now the Machines
Are Learning How
to Smell
•Google researchers are training neural networks with a new
technique to predict how a molecule smells based on its chemical
structure.

•For the field of olfaction, it could help puzzle out some big and long-
standing questions.

•In the 17th century, Isaac Newton used prisms to divide the white
light of the sun into our now familiar red, orange, yellow, green, blue,
indigo, and violet rainbow. Subsequent research revealed that what
we perceive as different colours are actually different wavelengths.
•If wavelengths are the basic components of light, molecules are the
building blocks of scents.

•When they get into our noses, those molecules interact with
receptors that send signals to a small part of our brains called the
olfactory bulb.

Suddenly we think “mmm, popcorn!”

•Several other teams applied

AI to that data and
made successful predictions.
But Wiltschko’s team took a
different approach. They used
something called a graph
neural network, or GNN.
•Networks of friends on social
media sites or networks of
academic citations from
journals. They could be used
to predict who your next
friends on social media might
be

The Google team used a set of nearly

5,000 molecules from perfumers who
have expert noses and carefully
matched each molecule with
descriptions like “woody,” “jasmine,” or
“sweet.” The researchers used about
two-thirds of the data set to train the
network, then tested whether it could
predict the scents of the remaining
molecules.
•AI can pluck images directly from a person’s brain.

•Given an fMRI (functional magnetic resonance imaging) scan of

someone looking at a picture, an algorithm can reconstruct the original
picture from the scan.

•Though the results aren’t yet perfect, they are still often recognisable
and hint at what may be possible in the future.

•Functional MRI develops a map of brain activity by detecting changes

in blood flow to specific brain regions.
•Increased adoption of cloud applications, such as Dropbox and Google
Drive, by private users has increased concern about use of cloud information
for cybercrimes such as child exploitation, illegal drug trafficking and illegal
firearm transactions

•Researchers at Purdue University have developed a cloud forensic model

using machine learning to collect digital evidence related to illegal activities
on cloud storage applications.

•It is crucial to detect illegal cloud activities in motion," said Fahad Salamh,
a Ph.D. student in the Purdue Polytechnic Institute, who helped create the
system. "Our technology identifies and analyzes in real time incidents
related to these cybercrimes through transactions uploaded to cloud
storage applications."

•Through identifying and analyzing these incidents using machine learning,

cloud service providers can collect alerted logs, block the associated
accounts and report them to law enforcement based on a cloud search
warrant request.
A Duke team trained a computer to identify up to 200 species of birds
from just a photo. Given a photo of a mystery bird (top), the A.I. spits out
heat maps showing which parts of the image are most similar to typical
species features it has seen before.

It can take years of birdwatching experience to tell one species from the
next. But using an artificial intelligence technique called deep learning,
Duke University researchers have trained a computer to identify up to 200
species of birds from just a photo.

The team trained their deep neural network—algorithms based on

the way the brain works—by feeding it 11,788 photos of 200 bird
species to learn from, ranging from swimming ducks to hovering
hummingbirds.

They found their neural network is able to identify the correct species
up to 84% of the time—on par with some of its best-performing
counterparts, which don't reveal how they are able to tell, say, one
sparrow from the next.
Scientists from Skoltech have trained neural networks to evaluate and
predict the plant growth pattern taking into account the main influencing
factors and propose the optimal ratio between the nutrient requirements
and other growth-driving parameters.

Over the past few years, multiple attempts have been made to use
artificial intelligence (AI) in nearly all spheres of life. It has proven
useful, helping people to make the right decisions and achieve the
goal. Using AI to grow plants in artificial environments is no
exception. Neural networks come in a broad variety of architectures,
including their most prominent type, recurrent neural networks (RNN),
that help efficiently process directional sequences of data, such as
text, speech or time series, the latter being the most instrumental in
describing plant growth over time.
3-D computer reconstruction of a UK orchard flowering
in April 2019. Credit: University of Cambridge