SlideShare a Scribd company logo
1 of 6
Download to read offline
1
Researchers are using Darwin’s theories to evolve AI, so only the
strongest algorithms survive
By.Dr.Mahboob ali khan Phd
Modern artificial intelligence is built to mimic nature—the field’s main
pursuit is replicating in a computer the same decision-making prowess
that humankind creates biologically.
For the better part of three decades, most of AI’s brain-inspired
development has surrounded “neural networks,” a term borrowed from
neurobiology that describes machine thought as the movement of data
through interconnected mathematical functions called neurons. But
nature has other good ideas, too: Computer scientists are now revisiting
an older field of study that suggests putting AI through evolutionary
processes, like those that molded the human brain over millennia, could
help us develop smarter, more efficient algorithms.
But first, back to middle-school biology class. The concept of
evolution, famously credited to Charles Darwin and refined by
countless scientists since, states that slight, random changes in an
organism’s genetic makeup will give it either an advantage or
disadvantage in the wild. If the organism’s mutation allows it to survive
2
and reproduce, that mutation is then passed along. If it doesn’t, the
mutation dies with its organism. In algorithm world, this is known as
neuroevolution. While artificial neural networks replicate the process
of learning individual concepts, neuroevolution tries to recreate the
process that built parts of the brain—i.e. the process by which only the
strong (or smart) survive.
Although neuroevolution has been around since the 1980s, the concept
is getting renewed attention as researchers dig into the archives for
different perspectives on machine learning. In the past month, Google
Brain and non-profit organization OpenAI each published unreviewed
papers on the subject, Google’s on the application of neuroevolution
principles to image recognition and OpenAI’s on using “worker”
algorithms to teach a master algorithm the best way to accomplish a
task.
Bringing biological evolution into the already complex field of AI
research can be confusing. So if it’s easier, think of algorithms as
horses. Horses learn throughout their lifetime, but they are
only evaluated on a few different metrics, like how fast they run.
Accuracy in image recognition is easy to assess as a single number, as
is the amount of time it takes a horse to run around a track. But what
actually makes that horse run faster is incredibly complicated—a vast
network of DNA that enables muscle growth, higher stamina, and even
intellect. That complexity mirrors the underlying parameters of
algorithms, or how an algorithm might be good (or bad) at image
recognition. So if you get lost anywhere in the article, just take a deep
breath and think “horses.” (This is also good life advice.)
For its research, the Google team generated 1,000 image-recognition
algorithms that were trained using modern deep neural networks to
recognize a specific set of images. Then 250 computers each chose two
algorithms and tested their accuracy by making them identify an image.
3
The algorithm with higher accuracy lived, while the one that performed
poorly was “killed.” The survivor was then copied, and its clone (or
“child”) was changed slightly—just like human DNA randomly
changes during reproduction. But instead of blue eyes or a widow’s
peak, this mutation slightly altered how the new algorithm interprets
training data. The clone was then trained using the same data as its
parent, and put back into the batch of 1,000 algorithms to start the
process over again.
Google researchers found that neuroevolution could cultivate an
algorithm with 94.6% accuracy, and recorded similar (though not
identical) results during each of four repeats of the experiment.
Mutations that improved the algorithm’s image-recognition skills were
rewarded (i.e. those algorithms survived) while mutations that
decreased performance were killed off. Just like in nature.
The differences between the five sessions also illustrated a consistent
problem. Google researcher and paper co-author Esteban Real says the
algorithms kept getting stuck halfway through the process, seemingly
unsure whether to continue evolving or scrap the mutation and start
over. Real says an analogy in nature might be the evolution of wings.
“Half a wing might not help you very much,” he says, “but a full wing
lets you fly.”
Google’s team is now working on getting the evolutionary models to
explore different mutations more fully (to build whole wings). But that
gets tricky. The team only wants the algorithm to mutate in a limited
way, so it doesn’t end up with a whole bunch of extra code that isn’t
useful. Explains Real: “The worst would be having many half-wings.”
By focusing mainly on image recognition, Google tested both
neuroevolution’s capacity for tackling something the biological brain
is great at, and its ability to solve a modern problem. OpenAI, on the
other hand, used a more pure form of evolution to undertake a different
task.
4
Rather than training thousands of algorithms to get better at one thing,
the OpenAI team wanted to use “worker” algorithms to train a master
algorithm to accomplish an unknown task, like playing a videogame
or walking in a 3D simulator. This technique isn’t the primary way to
teach machines how to make decisions, but a way to teach them how to
learn from specific information more efficiently, explains co-author
and OpenAI researcher Tim Salimans. The evolutionary algorithm is
able to monitor how its workers are learning, and it essentially learns
to learn—that is, to extract more knowledge from the same amount of
data.
To conduct their research, the OpenAI team set 1,440 worker
algorithms to the task of playing Atari. The workers played until they
reached Game Over, at which point they reported their scores to the
master. The algorithms that garnered the best scores were copied, as in
the Google research, and the copies were randomly mutated. The
mutated workers then went back into rotation and the process repeated
itself, with advantageous mutations being rewarded and bad ones
killed.
This approach also has its limitations, chief among them that the worker
algorithms only report one number, their high score, back to the master
algorithm. The algorithms with the best scores survived, but trying to
make the master aware of any specifically successful moveswould
require far too much computing power. (In biology, the parallel might
be an ant colony: Workers go out and find the most optimal solutions;
the queen is the central hub of information.) In other words, OpenAI
learned a lot about success, but less about scrappiness.
Back in the 1980s, neuroevolution and neural networks were similarly
sized fields of study, says Kenneth Stanley, an associate professor at
the University of Central California and a recent addition to Uber’s AI
team (through their acquisition of Geometric Intelligence, which he co-
founded).
5
“There was a small community of people who thought about how
brains, which are really the only proof of concept of intelligence in
nature, get into the world,” Stanley says. “Some people thought maybe
the most straightforward way to do this would be to create a
evolutionary, Darwinian-like process in a computer that acts on little
artificial brains.”
Neural networks took off when three computer scientists—David
Rumelhart, Geoffrey Hinton, and Ronald Williams—published a 1986
paper describing an algorithm that enhanced the way those networks
learned from their mistakes, called backpropagation. The findings
greatly improved the efficacy of hand-built neural nets, but an
impending AI winter—funding was slashed for purported lack of
progress—impeded further growth. It wasn’t until the mid-aughts that
Hinton and company began publishing papers that made neural
networks too enticing for the larger computer science community to
resist, showing that backpropagation allows neural networks to grow
immensely, and to in turn understand far more complex ideas. These
networks were dubbed “deep,” and deep neural networks became the
most popular flavor of modern artificial intelligence.
“Because of that, there was some loss of awareness for neuroevolution,
which was this parallel thread of evolving brains,” says Stanley.
Back in 2002, at the start of his career, Stanley wrote an algorithm
called NEAT, which allowed neural networks to evolve into larger and
more complex versions over time. His corresponding paper has more
than 1,600 citations on Google Scholar, and has been referenced in
deep neural-network design and neuroevolution research since its
publication. In 2006, Stanley published Hyper-NEAT, an algorithm
that made neuroevolution much greater in scale, inspired by DNA’s
ability to be the blueprint for billions of biological neurons with
trillions of connections, despite only having around 30,000 genes. (Fun
fact: Hyper-NEAT’s full name is Hybercube-based NeuroEvolution of
Augmenting Topologies. I challenge anyone to name a better algorithm
anagram.) Today, Stanley says it’s gratifying to see his career’s work
back in the zeitgeist.
6
Like Stanley, OpenAI and Google are now tackling two different ideas
plucked from the same field. Google’s hybrid approach combines
classic neuroevolution with the techniques, like backpropagation, that
have made deep learning so powerful today: Teach an algorithm how
to act in the world, let it evolve, and that algorithm’s child will have
most of the accrued knowledge. OpenAI’s approach was more true to
how evolution works in biology. The team only let the randomized
mutations in every generation govern how the networks improved or
failed, meaning improvement was only created through random
evolution. But both attempts had very clear goals—recognize an image,
or get a high score in a game (or make a horse run faster). How the
algorithms got there was up to nature.
“Individuals are born with the weights in their brain that they’re going
to have for their entire life,” Stanley says about OpenAI’s work. “It’s
like if we bred you, and your children, and your children’s children,
and then they knew calculus.”

More Related Content

Similar to Researchers are using Darwin’s theories to evolve AI, so only the strongest algorithms survive By.Dr.Mahboob ali khan Phd

Case study on deep learning
Case study on deep learningCase study on deep learning
Case study on deep learningHarshitBarde
 
Lebanon SoftShore Artificial Intelligence Seminar - March 38, 2014
Lebanon SoftShore Artificial Intelligence Seminar - March 38, 2014Lebanon SoftShore Artificial Intelligence Seminar - March 38, 2014
Lebanon SoftShore Artificial Intelligence Seminar - March 38, 2014lebsoftshore
 
SCONUL Summer Conference 2018 - Nicole coleman
SCONUL Summer Conference 2018 - Nicole colemanSCONUL Summer Conference 2018 - Nicole coleman
SCONUL Summer Conference 2018 - Nicole colemansconul
 
The Relationship Of AI With Human Thinking.pptx
The Relationship Of AI With Human Thinking.pptxThe Relationship Of AI With Human Thinking.pptx
The Relationship Of AI With Human Thinking.pptxssusere5168c
 
Artificial intelligent Lec 1-ai-introduction-
Artificial intelligent Lec 1-ai-introduction-Artificial intelligent Lec 1-ai-introduction-
Artificial intelligent Lec 1-ai-introduction-Taymoor Nazmy
 
What is Artificial Intelligence?
What is Artificial Intelligence?What is Artificial Intelligence?
What is Artificial Intelligence?Maad M. Mijwil
 
HOW NEURAL NETWORKS WORK
HOW NEURAL NETWORKS WORKHOW NEURAL NETWORKS WORK
HOW NEURAL NETWORKS WORKAM Publications
 
Simulation of Natural Gas leak detection system using AI
Simulation of Natural Gas leak detection system using AISimulation of Natural Gas leak detection system using AI
Simulation of Natural Gas leak detection system using AIEdgar Carrillo
 
Artificial Brain (presentation)
Artificial Brain (presentation)Artificial Brain (presentation)
Artificial Brain (presentation)Nitish Ranjan
 
Artificial Intelligence is back, Deep Learning Networks and Quantum possibili...
Artificial Intelligence is back, Deep Learning Networks and Quantum possibili...Artificial Intelligence is back, Deep Learning Networks and Quantum possibili...
Artificial Intelligence is back, Deep Learning Networks and Quantum possibili...John Mathon
 
Analytical Review on the Correlation between Ai and Neuroscience
Analytical Review on the Correlation between Ai and NeuroscienceAnalytical Review on the Correlation between Ai and Neuroscience
Analytical Review on the Correlation between Ai and NeuroscienceIOSR Journals
 
An Overview On Neural Network And Its Application
An Overview On Neural Network And Its ApplicationAn Overview On Neural Network And Its Application
An Overview On Neural Network And Its ApplicationSherri Cost
 
Artificial intelligence
Artificial intelligenceArtificial intelligence
Artificial intelligenceGautam Sharma
 
Neural Networks
Neural Networks Neural Networks
Neural Networks Eric Su
 
History of neural networks
History of neural networks History of neural networks
History of neural networks EliyasJain
 

Similar to Researchers are using Darwin’s theories to evolve AI, so only the strongest algorithms survive By.Dr.Mahboob ali khan Phd (20)

Case study on deep learning
Case study on deep learningCase study on deep learning
Case study on deep learning
 
Lebanon SoftShore Artificial Intelligence Seminar - March 38, 2014
Lebanon SoftShore Artificial Intelligence Seminar - March 38, 2014Lebanon SoftShore Artificial Intelligence Seminar - March 38, 2014
Lebanon SoftShore Artificial Intelligence Seminar - March 38, 2014
 
SCONUL Summer Conference 2018 - Nicole coleman
SCONUL Summer Conference 2018 - Nicole colemanSCONUL Summer Conference 2018 - Nicole coleman
SCONUL Summer Conference 2018 - Nicole coleman
 
AI KIMSRAD.pptx
AI KIMSRAD.pptxAI KIMSRAD.pptx
AI KIMSRAD.pptx
 
VEU_CST499_FinalReport
VEU_CST499_FinalReportVEU_CST499_FinalReport
VEU_CST499_FinalReport
 
The Relationship Of AI With Human Thinking.pptx
The Relationship Of AI With Human Thinking.pptxThe Relationship Of AI With Human Thinking.pptx
The Relationship Of AI With Human Thinking.pptx
 
Artificial intelligent Lec 1-ai-introduction-
Artificial intelligent Lec 1-ai-introduction-Artificial intelligent Lec 1-ai-introduction-
Artificial intelligent Lec 1-ai-introduction-
 
What is Artificial Intelligence?
What is Artificial Intelligence?What is Artificial Intelligence?
What is Artificial Intelligence?
 
Deep Learning
Deep LearningDeep Learning
Deep Learning
 
HOW NEURAL NETWORKS WORK
HOW NEURAL NETWORKS WORKHOW NEURAL NETWORKS WORK
HOW NEURAL NETWORKS WORK
 
Simulation of Natural Gas leak detection system using AI
Simulation of Natural Gas leak detection system using AISimulation of Natural Gas leak detection system using AI
Simulation of Natural Gas leak detection system using AI
 
Artificial Brain (presentation)
Artificial Brain (presentation)Artificial Brain (presentation)
Artificial Brain (presentation)
 
Deep Learning Demystified
Deep Learning DemystifiedDeep Learning Demystified
Deep Learning Demystified
 
Artificial Intelligence is back, Deep Learning Networks and Quantum possibili...
Artificial Intelligence is back, Deep Learning Networks and Quantum possibili...Artificial Intelligence is back, Deep Learning Networks and Quantum possibili...
Artificial Intelligence is back, Deep Learning Networks and Quantum possibili...
 
Analytical Review on the Correlation between Ai and Neuroscience
Analytical Review on the Correlation between Ai and NeuroscienceAnalytical Review on the Correlation between Ai and Neuroscience
Analytical Review on the Correlation between Ai and Neuroscience
 
Blue Brain
Blue BrainBlue Brain
Blue Brain
 
An Overview On Neural Network And Its Application
An Overview On Neural Network And Its ApplicationAn Overview On Neural Network And Its Application
An Overview On Neural Network And Its Application
 
Artificial intelligence
Artificial intelligenceArtificial intelligence
Artificial intelligence
 
Neural Networks
Neural Networks Neural Networks
Neural Networks
 
History of neural networks
History of neural networks History of neural networks
History of neural networks
 

More from Healthcare consultant

In India, Young Graduates Struggle by Dr. Mahboob Khan to Get Jobs.pdf
In India, Young Graduates Struggle by Dr. Mahboob Khan  to Get Jobs.pdfIn India, Young Graduates Struggle by Dr. Mahboob Khan  to Get Jobs.pdf
In India, Young Graduates Struggle by Dr. Mahboob Khan to Get Jobs.pdfHealthcare consultant
 
The Missing Middle class from Indian Healthcare System..pdf
The Missing Middle class from Indian Healthcare System..pdfThe Missing Middle class from Indian Healthcare System..pdf
The Missing Middle class from Indian Healthcare System..pdfHealthcare consultant
 
Chat GPT for Doctors -Revolutionizing Healthcare Communication by Dr.Mahboob.pdf
Chat GPT for Doctors -Revolutionizing Healthcare Communication by Dr.Mahboob.pdfChat GPT for Doctors -Revolutionizing Healthcare Communication by Dr.Mahboob.pdf
Chat GPT for Doctors -Revolutionizing Healthcare Communication by Dr.Mahboob.pdfHealthcare consultant
 
Hospital Management By Dr. Mahboob Khan
Hospital Management By Dr. Mahboob KhanHospital Management By Dr. Mahboob Khan
Hospital Management By Dr. Mahboob KhanHealthcare consultant
 
QUANTUM PHYSICS AND ITS POWER BY DR.MAHBOOB KHAN .pdf
QUANTUM PHYSICS AND ITS POWER BY DR.MAHBOOB KHAN .pdfQUANTUM PHYSICS AND ITS POWER BY DR.MAHBOOB KHAN .pdf
QUANTUM PHYSICS AND ITS POWER BY DR.MAHBOOB KHAN .pdfHealthcare consultant
 
Ways to increase hospital profitability By.Dr.Mahboob Khan
Ways to increase hospital profitability By.Dr.Mahboob KhanWays to increase hospital profitability By.Dr.Mahboob Khan
Ways to increase hospital profitability By.Dr.Mahboob KhanHealthcare consultant
 
Why Indian students fly out to persue career in Medicine by Dr.Mahboob Khan
Why Indian students fly out to persue career in Medicine by Dr.Mahboob KhanWhy Indian students fly out to persue career in Medicine by Dr.Mahboob Khan
Why Indian students fly out to persue career in Medicine by Dr.Mahboob KhanHealthcare consultant
 
Healthcare in a Digital Economy By. Dr. Mahboob Khan
Healthcare in a Digital Economy By. Dr. Mahboob KhanHealthcare in a Digital Economy By. Dr. Mahboob Khan
Healthcare in a Digital Economy By. Dr. Mahboob KhanHealthcare consultant
 
Couch Potato Syndrome by Dr. Mahboob Khan
Couch Potato Syndrome by Dr. Mahboob KhanCouch Potato Syndrome by Dr. Mahboob Khan
Couch Potato Syndrome by Dr. Mahboob KhanHealthcare consultant
 
The Rise of METAVERSE in Healthcare By.Dr.Mahboob Khan
The Rise of METAVERSE in Healthcare By.Dr.Mahboob Khan The Rise of METAVERSE in Healthcare By.Dr.Mahboob Khan
The Rise of METAVERSE in Healthcare By.Dr.Mahboob Khan Healthcare consultant
 
Robotic Process Automation in Healthcare-An Urgency! By.Dr.Mahboob Khan
Robotic Process Automation in Healthcare-An Urgency! By.Dr.Mahboob KhanRobotic Process Automation in Healthcare-An Urgency! By.Dr.Mahboob Khan
Robotic Process Automation in Healthcare-An Urgency! By.Dr.Mahboob KhanHealthcare consultant
 
Chained Globalization Issues in Healthcare by Dr.Mahboob Khan
Chained Globalization Issues in Healthcare by Dr.Mahboob KhanChained Globalization Issues in Healthcare by Dr.Mahboob Khan
Chained Globalization Issues in Healthcare by Dr.Mahboob KhanHealthcare consultant
 
New Standards of Care By.Dr.Mahboob Khan
New Standards of Care By.Dr.Mahboob KhanNew Standards of Care By.Dr.Mahboob Khan
New Standards of Care By.Dr.Mahboob KhanHealthcare consultant
 
Ways That Quantum Technology Could transform Health Care. By.Dr.Mahboob Khan
Ways That Quantum Technology Could transform Health Care. By.Dr.Mahboob KhanWays That Quantum Technology Could transform Health Care. By.Dr.Mahboob Khan
Ways That Quantum Technology Could transform Health Care. By.Dr.Mahboob KhanHealthcare consultant
 
How is COVID-19 Reshaping the role of Institutional strategy? By.Dr.Mahboob Khan
How is COVID-19 Reshaping the role of Institutional strategy? By.Dr.Mahboob KhanHow is COVID-19 Reshaping the role of Institutional strategy? By.Dr.Mahboob Khan
How is COVID-19 Reshaping the role of Institutional strategy? By.Dr.Mahboob KhanHealthcare consultant
 
Retaining Healthcare Quality During COVID-19 and Future of Care Delivery. By....
Retaining Healthcare Quality During COVID-19 and Future of Care Delivery. By....Retaining Healthcare Quality During COVID-19 and Future of Care Delivery. By....
Retaining Healthcare Quality During COVID-19 and Future of Care Delivery. By....Healthcare consultant
 

More from Healthcare consultant (20)

In India, Young Graduates Struggle by Dr. Mahboob Khan to Get Jobs.pdf
In India, Young Graduates Struggle by Dr. Mahboob Khan  to Get Jobs.pdfIn India, Young Graduates Struggle by Dr. Mahboob Khan  to Get Jobs.pdf
In India, Young Graduates Struggle by Dr. Mahboob Khan to Get Jobs.pdf
 
The Missing Middle class from Indian Healthcare System..pdf
The Missing Middle class from Indian Healthcare System..pdfThe Missing Middle class from Indian Healthcare System..pdf
The Missing Middle class from Indian Healthcare System..pdf
 
Chat GPT for Doctors -Revolutionizing Healthcare Communication by Dr.Mahboob.pdf
Chat GPT for Doctors -Revolutionizing Healthcare Communication by Dr.Mahboob.pdfChat GPT for Doctors -Revolutionizing Healthcare Communication by Dr.Mahboob.pdf
Chat GPT for Doctors -Revolutionizing Healthcare Communication by Dr.Mahboob.pdf
 
Hospital Management By Dr. Mahboob Khan
Hospital Management By Dr. Mahboob KhanHospital Management By Dr. Mahboob Khan
Hospital Management By Dr. Mahboob Khan
 
Leadership lessons
Leadership lessonsLeadership lessons
Leadership lessons
 
The Psychopathic CEO
The Psychopathic CEO The Psychopathic CEO
The Psychopathic CEO
 
QUANTUM PHYSICS AND ITS POWER BY DR.MAHBOOB KHAN .pdf
QUANTUM PHYSICS AND ITS POWER BY DR.MAHBOOB KHAN .pdfQUANTUM PHYSICS AND ITS POWER BY DR.MAHBOOB KHAN .pdf
QUANTUM PHYSICS AND ITS POWER BY DR.MAHBOOB KHAN .pdf
 
Ways to increase hospital profitability By.Dr.Mahboob Khan
Ways to increase hospital profitability By.Dr.Mahboob KhanWays to increase hospital profitability By.Dr.Mahboob Khan
Ways to increase hospital profitability By.Dr.Mahboob Khan
 
Why Indian students fly out to persue career in Medicine by Dr.Mahboob Khan
Why Indian students fly out to persue career in Medicine by Dr.Mahboob KhanWhy Indian students fly out to persue career in Medicine by Dr.Mahboob Khan
Why Indian students fly out to persue career in Medicine by Dr.Mahboob Khan
 
Healthcare in a Digital Economy By. Dr. Mahboob Khan
Healthcare in a Digital Economy By. Dr. Mahboob KhanHealthcare in a Digital Economy By. Dr. Mahboob Khan
Healthcare in a Digital Economy By. Dr. Mahboob Khan
 
Winning strategy-By.Dr. Mahboob Khan
Winning strategy-By.Dr. Mahboob Khan Winning strategy-By.Dr. Mahboob Khan
Winning strategy-By.Dr. Mahboob Khan
 
Couch Potato Syndrome by Dr. Mahboob Khan
Couch Potato Syndrome by Dr. Mahboob KhanCouch Potato Syndrome by Dr. Mahboob Khan
Couch Potato Syndrome by Dr. Mahboob Khan
 
The Rise of METAVERSE in Healthcare By.Dr.Mahboob Khan
The Rise of METAVERSE in Healthcare By.Dr.Mahboob Khan The Rise of METAVERSE in Healthcare By.Dr.Mahboob Khan
The Rise of METAVERSE in Healthcare By.Dr.Mahboob Khan
 
Robotic Process Automation in Healthcare-An Urgency! By.Dr.Mahboob Khan
Robotic Process Automation in Healthcare-An Urgency! By.Dr.Mahboob KhanRobotic Process Automation in Healthcare-An Urgency! By.Dr.Mahboob Khan
Robotic Process Automation in Healthcare-An Urgency! By.Dr.Mahboob Khan
 
The art of filing by Dr.Mahboob Khan
The art of filing by Dr.Mahboob Khan The art of filing by Dr.Mahboob Khan
The art of filing by Dr.Mahboob Khan
 
Chained Globalization Issues in Healthcare by Dr.Mahboob Khan
Chained Globalization Issues in Healthcare by Dr.Mahboob KhanChained Globalization Issues in Healthcare by Dr.Mahboob Khan
Chained Globalization Issues in Healthcare by Dr.Mahboob Khan
 
New Standards of Care By.Dr.Mahboob Khan
New Standards of Care By.Dr.Mahboob KhanNew Standards of Care By.Dr.Mahboob Khan
New Standards of Care By.Dr.Mahboob Khan
 
Ways That Quantum Technology Could transform Health Care. By.Dr.Mahboob Khan
Ways That Quantum Technology Could transform Health Care. By.Dr.Mahboob KhanWays That Quantum Technology Could transform Health Care. By.Dr.Mahboob Khan
Ways That Quantum Technology Could transform Health Care. By.Dr.Mahboob Khan
 
How is COVID-19 Reshaping the role of Institutional strategy? By.Dr.Mahboob Khan
How is COVID-19 Reshaping the role of Institutional strategy? By.Dr.Mahboob KhanHow is COVID-19 Reshaping the role of Institutional strategy? By.Dr.Mahboob Khan
How is COVID-19 Reshaping the role of Institutional strategy? By.Dr.Mahboob Khan
 
Retaining Healthcare Quality During COVID-19 and Future of Care Delivery. By....
Retaining Healthcare Quality During COVID-19 and Future of Care Delivery. By....Retaining Healthcare Quality During COVID-19 and Future of Care Delivery. By....
Retaining Healthcare Quality During COVID-19 and Future of Care Delivery. By....
 

Recently uploaded

Nanoparticles synthesis and characterization​ ​
Nanoparticles synthesis and characterization​  ​Nanoparticles synthesis and characterization​  ​
Nanoparticles synthesis and characterization​ ​kaibalyasahoo82800
 
Caco-2 cell permeability assay for drug absorption
Caco-2 cell permeability assay for drug absorptionCaco-2 cell permeability assay for drug absorption
Caco-2 cell permeability assay for drug absorptionPriyansha Singh
 
G9 Science Q4- Week 1-2 Projectile Motion.ppt
G9 Science Q4- Week 1-2 Projectile Motion.pptG9 Science Q4- Week 1-2 Projectile Motion.ppt
G9 Science Q4- Week 1-2 Projectile Motion.pptMAESTRELLAMesa2
 
Work, Energy and Power for class 10 ICSE Physics
Work, Energy and Power for class 10 ICSE PhysicsWork, Energy and Power for class 10 ICSE Physics
Work, Energy and Power for class 10 ICSE Physicsvishikhakeshava1
 
Unlocking the Potential: Deep dive into ocean of Ceramic Magnets.pptx
Unlocking  the Potential: Deep dive into ocean of Ceramic Magnets.pptxUnlocking  the Potential: Deep dive into ocean of Ceramic Magnets.pptx
Unlocking the Potential: Deep dive into ocean of Ceramic Magnets.pptxanandsmhk
 
Grafana in space: Monitoring Japan's SLIM moon lander in real time
Grafana in space: Monitoring Japan's SLIM moon lander  in real timeGrafana in space: Monitoring Japan's SLIM moon lander  in real time
Grafana in space: Monitoring Japan's SLIM moon lander in real timeSatoshi NAKAHIRA
 
Presentation Vikram Lander by Vedansh Gupta.pptx
Presentation Vikram Lander by Vedansh Gupta.pptxPresentation Vikram Lander by Vedansh Gupta.pptx
Presentation Vikram Lander by Vedansh Gupta.pptxgindu3009
 
Natural Polymer Based Nanomaterials
Natural Polymer Based NanomaterialsNatural Polymer Based Nanomaterials
Natural Polymer Based NanomaterialsAArockiyaNisha
 
Analytical Profile of Coleus Forskohlii | Forskolin .pptx
Analytical Profile of Coleus Forskohlii | Forskolin .pptxAnalytical Profile of Coleus Forskohlii | Forskolin .pptx
Analytical Profile of Coleus Forskohlii | Forskolin .pptxSwapnil Therkar
 
SOLUBLE PATTERN RECOGNITION RECEPTORS.pptx
SOLUBLE PATTERN RECOGNITION RECEPTORS.pptxSOLUBLE PATTERN RECOGNITION RECEPTORS.pptx
SOLUBLE PATTERN RECOGNITION RECEPTORS.pptxkessiyaTpeter
 
Is RISC-V ready for HPC workload? Maybe?
Is RISC-V ready for HPC workload? Maybe?Is RISC-V ready for HPC workload? Maybe?
Is RISC-V ready for HPC workload? Maybe?Patrick Diehl
 
Stunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCR
Stunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCRStunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCR
Stunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCRDelhi Call girls
 
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...Lokesh Kothari
 
Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.aasikanpl
 
Boyles law module in the grade 10 science
Boyles law module in the grade 10 scienceBoyles law module in the grade 10 science
Boyles law module in the grade 10 sciencefloriejanemacaya1
 
Bentham & Hooker's Classification. along with the merits and demerits of the ...
Bentham & Hooker's Classification. along with the merits and demerits of the ...Bentham & Hooker's Classification. along with the merits and demerits of the ...
Bentham & Hooker's Classification. along with the merits and demerits of the ...Nistarini College, Purulia (W.B) India
 
Recombinant DNA technology (Immunological screening)
Recombinant DNA technology (Immunological screening)Recombinant DNA technology (Immunological screening)
Recombinant DNA technology (Immunological screening)PraveenaKalaiselvan1
 
Biopesticide (2).pptx .This slides helps to know the different types of biop...
Biopesticide (2).pptx  .This slides helps to know the different types of biop...Biopesticide (2).pptx  .This slides helps to know the different types of biop...
Biopesticide (2).pptx .This slides helps to know the different types of biop...RohitNehra6
 

Recently uploaded (20)

Nanoparticles synthesis and characterization​ ​
Nanoparticles synthesis and characterization​  ​Nanoparticles synthesis and characterization​  ​
Nanoparticles synthesis and characterization​ ​
 
Caco-2 cell permeability assay for drug absorption
Caco-2 cell permeability assay for drug absorptionCaco-2 cell permeability assay for drug absorption
Caco-2 cell permeability assay for drug absorption
 
G9 Science Q4- Week 1-2 Projectile Motion.ppt
G9 Science Q4- Week 1-2 Projectile Motion.pptG9 Science Q4- Week 1-2 Projectile Motion.ppt
G9 Science Q4- Week 1-2 Projectile Motion.ppt
 
The Philosophy of Science
The Philosophy of ScienceThe Philosophy of Science
The Philosophy of Science
 
Work, Energy and Power for class 10 ICSE Physics
Work, Energy and Power for class 10 ICSE PhysicsWork, Energy and Power for class 10 ICSE Physics
Work, Energy and Power for class 10 ICSE Physics
 
9953056974 Young Call Girls In Mahavir enclave Indian Quality Escort service
9953056974 Young Call Girls In Mahavir enclave Indian Quality Escort service9953056974 Young Call Girls In Mahavir enclave Indian Quality Escort service
9953056974 Young Call Girls In Mahavir enclave Indian Quality Escort service
 
Unlocking the Potential: Deep dive into ocean of Ceramic Magnets.pptx
Unlocking  the Potential: Deep dive into ocean of Ceramic Magnets.pptxUnlocking  the Potential: Deep dive into ocean of Ceramic Magnets.pptx
Unlocking the Potential: Deep dive into ocean of Ceramic Magnets.pptx
 
Grafana in space: Monitoring Japan's SLIM moon lander in real time
Grafana in space: Monitoring Japan's SLIM moon lander  in real timeGrafana in space: Monitoring Japan's SLIM moon lander  in real time
Grafana in space: Monitoring Japan's SLIM moon lander in real time
 
Presentation Vikram Lander by Vedansh Gupta.pptx
Presentation Vikram Lander by Vedansh Gupta.pptxPresentation Vikram Lander by Vedansh Gupta.pptx
Presentation Vikram Lander by Vedansh Gupta.pptx
 
Natural Polymer Based Nanomaterials
Natural Polymer Based NanomaterialsNatural Polymer Based Nanomaterials
Natural Polymer Based Nanomaterials
 
Analytical Profile of Coleus Forskohlii | Forskolin .pptx
Analytical Profile of Coleus Forskohlii | Forskolin .pptxAnalytical Profile of Coleus Forskohlii | Forskolin .pptx
Analytical Profile of Coleus Forskohlii | Forskolin .pptx
 
SOLUBLE PATTERN RECOGNITION RECEPTORS.pptx
SOLUBLE PATTERN RECOGNITION RECEPTORS.pptxSOLUBLE PATTERN RECOGNITION RECEPTORS.pptx
SOLUBLE PATTERN RECOGNITION RECEPTORS.pptx
 
Is RISC-V ready for HPC workload? Maybe?
Is RISC-V ready for HPC workload? Maybe?Is RISC-V ready for HPC workload? Maybe?
Is RISC-V ready for HPC workload? Maybe?
 
Stunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCR
Stunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCRStunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCR
Stunning ➥8448380779▻ Call Girls In Panchshil Enclave Delhi NCR
 
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
Labelling Requirements and Label Claims for Dietary Supplements and Recommend...
 
Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
Call Girls in Mayapuri Delhi 💯Call Us 🔝9953322196🔝 💯Escort.
 
Boyles law module in the grade 10 science
Boyles law module in the grade 10 scienceBoyles law module in the grade 10 science
Boyles law module in the grade 10 science
 
Bentham & Hooker's Classification. along with the merits and demerits of the ...
Bentham & Hooker's Classification. along with the merits and demerits of the ...Bentham & Hooker's Classification. along with the merits and demerits of the ...
Bentham & Hooker's Classification. along with the merits and demerits of the ...
 
Recombinant DNA technology (Immunological screening)
Recombinant DNA technology (Immunological screening)Recombinant DNA technology (Immunological screening)
Recombinant DNA technology (Immunological screening)
 
Biopesticide (2).pptx .This slides helps to know the different types of biop...
Biopesticide (2).pptx  .This slides helps to know the different types of biop...Biopesticide (2).pptx  .This slides helps to know the different types of biop...
Biopesticide (2).pptx .This slides helps to know the different types of biop...
 

Researchers are using Darwin’s theories to evolve AI, so only the strongest algorithms survive By.Dr.Mahboob ali khan Phd

  • 1. 1 Researchers are using Darwin’s theories to evolve AI, so only the strongest algorithms survive By.Dr.Mahboob ali khan Phd Modern artificial intelligence is built to mimic nature—the field’s main pursuit is replicating in a computer the same decision-making prowess that humankind creates biologically. For the better part of three decades, most of AI’s brain-inspired development has surrounded “neural networks,” a term borrowed from neurobiology that describes machine thought as the movement of data through interconnected mathematical functions called neurons. But nature has other good ideas, too: Computer scientists are now revisiting an older field of study that suggests putting AI through evolutionary processes, like those that molded the human brain over millennia, could help us develop smarter, more efficient algorithms. But first, back to middle-school biology class. The concept of evolution, famously credited to Charles Darwin and refined by countless scientists since, states that slight, random changes in an organism’s genetic makeup will give it either an advantage or disadvantage in the wild. If the organism’s mutation allows it to survive
  • 2. 2 and reproduce, that mutation is then passed along. If it doesn’t, the mutation dies with its organism. In algorithm world, this is known as neuroevolution. While artificial neural networks replicate the process of learning individual concepts, neuroevolution tries to recreate the process that built parts of the brain—i.e. the process by which only the strong (or smart) survive. Although neuroevolution has been around since the 1980s, the concept is getting renewed attention as researchers dig into the archives for different perspectives on machine learning. In the past month, Google Brain and non-profit organization OpenAI each published unreviewed papers on the subject, Google’s on the application of neuroevolution principles to image recognition and OpenAI’s on using “worker” algorithms to teach a master algorithm the best way to accomplish a task. Bringing biological evolution into the already complex field of AI research can be confusing. So if it’s easier, think of algorithms as horses. Horses learn throughout their lifetime, but they are only evaluated on a few different metrics, like how fast they run. Accuracy in image recognition is easy to assess as a single number, as is the amount of time it takes a horse to run around a track. But what actually makes that horse run faster is incredibly complicated—a vast network of DNA that enables muscle growth, higher stamina, and even intellect. That complexity mirrors the underlying parameters of algorithms, or how an algorithm might be good (or bad) at image recognition. So if you get lost anywhere in the article, just take a deep breath and think “horses.” (This is also good life advice.) For its research, the Google team generated 1,000 image-recognition algorithms that were trained using modern deep neural networks to recognize a specific set of images. Then 250 computers each chose two algorithms and tested their accuracy by making them identify an image.
  • 3. 3 The algorithm with higher accuracy lived, while the one that performed poorly was “killed.” The survivor was then copied, and its clone (or “child”) was changed slightly—just like human DNA randomly changes during reproduction. But instead of blue eyes or a widow’s peak, this mutation slightly altered how the new algorithm interprets training data. The clone was then trained using the same data as its parent, and put back into the batch of 1,000 algorithms to start the process over again. Google researchers found that neuroevolution could cultivate an algorithm with 94.6% accuracy, and recorded similar (though not identical) results during each of four repeats of the experiment. Mutations that improved the algorithm’s image-recognition skills were rewarded (i.e. those algorithms survived) while mutations that decreased performance were killed off. Just like in nature. The differences between the five sessions also illustrated a consistent problem. Google researcher and paper co-author Esteban Real says the algorithms kept getting stuck halfway through the process, seemingly unsure whether to continue evolving or scrap the mutation and start over. Real says an analogy in nature might be the evolution of wings. “Half a wing might not help you very much,” he says, “but a full wing lets you fly.” Google’s team is now working on getting the evolutionary models to explore different mutations more fully (to build whole wings). But that gets tricky. The team only wants the algorithm to mutate in a limited way, so it doesn’t end up with a whole bunch of extra code that isn’t useful. Explains Real: “The worst would be having many half-wings.” By focusing mainly on image recognition, Google tested both neuroevolution’s capacity for tackling something the biological brain is great at, and its ability to solve a modern problem. OpenAI, on the other hand, used a more pure form of evolution to undertake a different task.
  • 4. 4 Rather than training thousands of algorithms to get better at one thing, the OpenAI team wanted to use “worker” algorithms to train a master algorithm to accomplish an unknown task, like playing a videogame or walking in a 3D simulator. This technique isn’t the primary way to teach machines how to make decisions, but a way to teach them how to learn from specific information more efficiently, explains co-author and OpenAI researcher Tim Salimans. The evolutionary algorithm is able to monitor how its workers are learning, and it essentially learns to learn—that is, to extract more knowledge from the same amount of data. To conduct their research, the OpenAI team set 1,440 worker algorithms to the task of playing Atari. The workers played until they reached Game Over, at which point they reported their scores to the master. The algorithms that garnered the best scores were copied, as in the Google research, and the copies were randomly mutated. The mutated workers then went back into rotation and the process repeated itself, with advantageous mutations being rewarded and bad ones killed. This approach also has its limitations, chief among them that the worker algorithms only report one number, their high score, back to the master algorithm. The algorithms with the best scores survived, but trying to make the master aware of any specifically successful moveswould require far too much computing power. (In biology, the parallel might be an ant colony: Workers go out and find the most optimal solutions; the queen is the central hub of information.) In other words, OpenAI learned a lot about success, but less about scrappiness. Back in the 1980s, neuroevolution and neural networks were similarly sized fields of study, says Kenneth Stanley, an associate professor at the University of Central California and a recent addition to Uber’s AI team (through their acquisition of Geometric Intelligence, which he co- founded).
  • 5. 5 “There was a small community of people who thought about how brains, which are really the only proof of concept of intelligence in nature, get into the world,” Stanley says. “Some people thought maybe the most straightforward way to do this would be to create a evolutionary, Darwinian-like process in a computer that acts on little artificial brains.” Neural networks took off when three computer scientists—David Rumelhart, Geoffrey Hinton, and Ronald Williams—published a 1986 paper describing an algorithm that enhanced the way those networks learned from their mistakes, called backpropagation. The findings greatly improved the efficacy of hand-built neural nets, but an impending AI winter—funding was slashed for purported lack of progress—impeded further growth. It wasn’t until the mid-aughts that Hinton and company began publishing papers that made neural networks too enticing for the larger computer science community to resist, showing that backpropagation allows neural networks to grow immensely, and to in turn understand far more complex ideas. These networks were dubbed “deep,” and deep neural networks became the most popular flavor of modern artificial intelligence. “Because of that, there was some loss of awareness for neuroevolution, which was this parallel thread of evolving brains,” says Stanley. Back in 2002, at the start of his career, Stanley wrote an algorithm called NEAT, which allowed neural networks to evolve into larger and more complex versions over time. His corresponding paper has more than 1,600 citations on Google Scholar, and has been referenced in deep neural-network design and neuroevolution research since its publication. In 2006, Stanley published Hyper-NEAT, an algorithm that made neuroevolution much greater in scale, inspired by DNA’s ability to be the blueprint for billions of biological neurons with trillions of connections, despite only having around 30,000 genes. (Fun fact: Hyper-NEAT’s full name is Hybercube-based NeuroEvolution of Augmenting Topologies. I challenge anyone to name a better algorithm anagram.) Today, Stanley says it’s gratifying to see his career’s work back in the zeitgeist.
  • 6. 6 Like Stanley, OpenAI and Google are now tackling two different ideas plucked from the same field. Google’s hybrid approach combines classic neuroevolution with the techniques, like backpropagation, that have made deep learning so powerful today: Teach an algorithm how to act in the world, let it evolve, and that algorithm’s child will have most of the accrued knowledge. OpenAI’s approach was more true to how evolution works in biology. The team only let the randomized mutations in every generation govern how the networks improved or failed, meaning improvement was only created through random evolution. But both attempts had very clear goals—recognize an image, or get a high score in a game (or make a horse run faster). How the algorithms got there was up to nature. “Individuals are born with the weights in their brain that they’re going to have for their entire life,” Stanley says about OpenAI’s work. “It’s like if we bred you, and your children, and your children’s children, and then they knew calculus.”