Scribd
Upload
407 views10 pages

Google Tulip: Presenting by Guide

Google has been working with Wageningen University for two years to develop technology to communicate with plants using machine learning. They have created a rudimentary language called "Tulipish" to translate signals from tulips to human language and vice versa. This "Google Tulip" technology was tested successfully at the flower park Keukenhof in the Netherlands. The system architecture uses cloud IoT Core to collect audio data from tulips and perform predictions using machine learning models. When tested, tulips were able to respond to humans talking about their day and request things like water and sunlight.

Uploaded by

Aparna Gattimi
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
407 views10 pages

Google Tulip: Presenting by Guide

Google has been working with Wageningen University for two years to develop technology to communicate with plants using machine learning. They have created a rudimentary language called "Tulipish" to translate signals from tulips to human language and vice versa. This "Google Tulip" technology was tested successfully at the flower park Keukenhof in the Netherlands. The system architecture uses cloud IoT Core to collect audio data from tulips and perform predictions using machine learning models. When tested, tulips were able to respond to humans talking about their day and request things like water and sunlight.

Uploaded by

Aparna Gattimi
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 10

GOOGLE TULIP

Presenting by Guide
Aparna Gattimi Mrs.J L Sarwani
Theerpathi
18P31A0575 Associate Professor
Contents

● Introduction
● Existing System
● System Architecture
● Deployment
● Conclusion
Introduction
The plants have the ability to transfer information from one plant of root to another
plant root. For the past two years, Wageningen University has been working with
Google to use cutting edge technology to look deeper into communication with plants.
They collected an incredible amount of information using automated machine learning.
They turned this information into a new rudimentary language which is becoming more
and more sophisticated. This tulip technology is a better way to indicate to humans to
mention their needs like water or light. Using this technology, humans can
communicate with plants and plants can communicate with humans.
The Google assistant decodes the plant’s signals to the human’s language and the
human's language is decoded to the plant's signal. This tulip technology is under
testing. The world-famous flower parks, called Keukenhof, provided the perfect testing
ground. They built an advanced tool called Neural Machine Translation.
Existing System
Today Google announced that Google Assistant on the Google Home Hub has the ability to talk to
plants, in particular, tulips, “due to great advancements in artificial intelligence”. Google Tulip was
largely developed in the Netherlands, a country that produces 12.5 billion flowers a year, which is
50% of all flowers in the world. The country’s most famous flower is the Tulip. Google and the
Wageningen University and Research team were able to build on Assistant’s existing Neural
Machine Translation in order to map tulip signals to human language. After two years of training,
tulips has been added as a language to Google Home’s interpreter mode, meaning Google
Assistant now offers translation between tulips and dozens of human languages. The feature was
tested in the Netherland's world-famous flower park, Keukenhof. Users can say in order to
develop this technology google began looking at how plants communicate with one another
through their root systems. The demonstration video shows tulips listening to users talk about
their day, and ofcourse requesting lots of water and sun. Voicebot’s Bret Kinsella also commented
on the new feature, Tulips is just the beginning too. Google researchers describe Tulipish as a
rudimentary language for understanding nature and point out that the more we listen to nature,
the more we discover the amazing things it has to say. Updates involving communication with
other kinds of plants, like cacti, are already underway.
System Architecture
We use cloud IoT Core to collect the audio data from individual
tulips, and carry out predictions on Kube Flow Pipelines “on-
premises”. Their training architecture was quite simple. Google
was able to use Google Cloud Speech to Text and AutoML
Natural Language to train the machine learning models without
having to write any code. Because of connectivity problems
trying more than a million tulips together, it became a bit more
challenging to carry out real-time predictions.
Training architecture for Google Tulip takes advantage of some pre-built models and Auto ML
Natural Language which employs neural machine translation and neural architecture search.
Deployment
When the flowers need more sun, we simply call out to the
Google wind API to make that happen. This is the technology
that we announced two years ago on this exact day to employ
machine learning to predict wind and ensure clear skies in the
Netherlands, and the API is quite easy to integrate. Besides the
benefits to ducth agriculture, an unanticipated side-effect of
Google tulip has been to add closed captioning of the flowers.
Conclusion
Communication between humans and plants will be a new
achievement in the field of science, engineering, and technology. It will
lead the human to understand the need of plants to grow to develop
better which will be good for the betterment of our ecosystem,
environment as well as farmers. It will also lead us to discover new
technology and will help us to get introduced to new facts and
phenomena. So, I can conclude my view by saying that Google tulip is
a new step in the direction of future technology, artificial intelligence
and machine learning which leads us to easier, more comfortable and
extra productive life as the primary goal of science
References
[1]
Holmquist L>E., et al, “Smart-Its Friends: A Technique for Users to establish
Connections between Smart Artifacts”,in Proceedings of UBICOMP 2001, Atlanta,
GA, USA, Sept.2001.
[2] Giuseppe Ciaburro Alexis Perrier V Kishore Ayyadevera, “Hands-On Machine
Learning on Google Cloud platform”.
[3] Peter Norvig and Stuart J. Russell, “Artificial Intelligence: A Modern Approach”.
[4] Stuart J. Russell, “Human Compatible: AI and the Problem of Control”.
[5] Kames A0., et al.: An Architecture that Treats Everyday Objects as
Communicating Tangible Components.
THANK YOU
Any Queries?

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy