Since “2001: A Space Odyssey,” people have wondered: could machines like HAL 9000 eventually exist that can process information with human-like intelligence?
Researchers at Michigan State University say that true, human-level intelligence remains a long way off, but their new paper published in The American Naturalist explores how computers could begin to evolve learning in the same way as natural organisms did – with implications for many fields, including artificial intelligence.
“We know that all organisms are capable of some form of learning, we just weren’t sure how those abilities first evolved. Now we can watch these major evolutionary events unfold before us in a virtual world,” said Anselmo Pontes, MSU computer science researcher and lead author. “Understanding how learning behavior evolved helps us figure out how it works and provides insights to other fields such as neuroscience, education, psychology, animal behavior, and even AI. It also supplies clues to how our brains work and could even lead to robots that learn from experiences as effectively as humans do.”
According to Fred Dyer, MSU integrative biology professor and co-author, these findings have the potential for huge implications.
“We’re untangling the story of how our own cognition came to be and how that can shape the future,” Dyer said. “Understanding our own origins can lead us to developing robots that can watch and learn rather than being programmed for each individual task.”
The results are the first demonstration that shows the evolution of associative learning in an artificial organism without a brain.
Here is a video showing the process.
“Our inspiration was the way animals learn landmarks and use them to navigate their environments,” Pontes said. “For example, in laboratory experiments, honeybees learn to associate certain colors or shapes with directions and navigate complex mazes.”
Since the evolution of learning cannot be observed through fossils – and would take more than a lifetime to watch in nature – the MSU interdisciplinary team composed of biologists and computer scientists used a digital evolution program that allowed them to observe tens of thousands of generations of evolution in just a few hours, a feat unachievable with living systems.
In this case, organisms evolved to learn and use environmental signals to help them navigate the environment and find food.
“Learning is crucial to most behaviors, but we couldn’t directly observe how learning got started in the first place from our purely instinctual ancestors,” Dyer said. “We built in various selection pressures that we thought might play a role and watched what happened in the computer.”
While the environment was simulated, the evolution was real. The programs that controlled the digital organism were subject to genetic variation from mutation, inheritance and competitive selection. Organisms were tasked to follow a trail alongside signals that – if interpreted correctly – pointed where the path went next.
In the beginning of the simulation, organisms were “blank slates,” incapable of sensing, moving or learning. Every time an organism reproduced, its descendants could suffer mutations that changed their behavior. Most mutations were lethal. Some did nothing. But the rare traits that allowed an organism to better follow the trail resulted in the organism collecting more resources, reproducing more often and, thus, gaining share in the population.
Over the generations, organisms evolved more and more complex behaviors. First came simple movements allowing them to stumble into food. Next was the ability to sense and distinguish different types of signals, followed by the reflexive ability to correct errors, such as trying an incorrect path, backing up and trying another.
A few organisms evolved the ability to learn by association. If one of these organisms made a wrong turn it would correct the error, but it would also learn from that mistake and associate the specific signal it saw with the direction it now knew it should have gone. From then on, it would navigate the entire trail without any further mistakes. Some organisms could even relearn when tricked by switching signals mid-trail.
“Evolution in nature might take too long to study,” Pontes said, “but evolution is just an algorithm, so it can be replicated in a computer. We were not just able to see how certain environments fostered the evolution of learning, but we saw populations evolve through the same behavioral phases that previous scientists speculated should happen but didn’t have the technology to see.”
Other MSU co-authors include Robert Mobley, Charles Ofria and Christoph Adami. This project was developed through the BEACON Center for the Study of Evolution in Action, which brings together biologists, computer scientists and engineers to illuminate and harness the power of evolution.
“Pontes and colleagues have evolved associated learning in a computer from the raw ingredients of mutation, inheritance and competitive selection,” said George Gilchrist, program director at the National Science Foundation, which funds the BEACON science and technology center. “This opens the door to creating artificial intelligence systems without the limitations imposed by human design.”
The Latest on: Evolution of artificial intelligence
via Google News
The Latest on: Evolution of artificial intelligence
- Artificial Intelligence Products Market Report 2021 Growth Factors, Research Methodology With Impact of COIVD-19 and Global Forecast 2025on January 21, 2021 at 6:58 am
Final Report will add the analysis of the impact of COVID-19 on this industry." “Artificial Intelligence Products ...
- Artificial Intelligence: With Great Power Comes Great Responsibilityon January 15, 2021 at 10:28 am
AI is an evolution, and we are just at the beginning. The choice is not when, but how we join that evolution, Capgemini says.
- An Exceptional Year Of Organizational Evolution For T&T Group: An Update from its HR and Administration Headon January 14, 2021 at 7:56 am
Regardless of the critical period of retrenchment our organization - like many others - was going through, we ensured that we shed none of ...
- Scanmarket expands analytics capabilities with the acquisition of artificial intelligence company MIA Dataon January 14, 2021 at 4:00 am
Scanmarket is pleased to announce the acquisition of MIA Data, an analytics technology company specializing in ...
- #BizTrends2021: Evolution of workforce skills demand - what the future holdson January 13, 2021 at 4:00 pm
When reflecting on the fourth industrial revolution, or Industry 4.0, a number of things immediately spring to mind. These include the industrial internet of things (IIoT), artificial intelligence (AI ...
- Chief of US Army Futures Command: The service is experiencing a technological evolutionon January 11, 2021 at 6:59 pm
The Army Modernization Strategy revolves heavily around what we call the 3+2 model, (artificial intelligence, robotics and autonomy, along with networks and data) — all critical technological areas of ...
- Why ethics should guide artificial intelligence useon January 11, 2021 at 1:58 pm
Artificial Intelligence (AI) refers to the theory and development of computer systems able to perform tasks that normally require human intelligence. AI makes it possible for machines to learn from ...
- Mercedes-Benz Hyperscreen User Interface Is Massive, Employs Artificial Intelligenceon January 7, 2021 at 5:13 am
Mercedes-Benz Set to debut in the upcoming Mercedes-Benz EQS S-class EV sedan, the MBUX Hyperscreen system is the latest evolution ... vehicle control and artificial intelligence functions of ...
- The reality of AI in healthcare: promises, roles, evolution, and moreon January 4, 2021 at 2:18 am
The reality of AI in healthcare: promises, roles, evolution, and more By Ankit Maheshwari | 4th Jan 2021 Artificial Intelligence (AI) has had a profound impact on numerous sectors.
- Artificial intelligence finds surprising patterns in Earth's biological mass extinctionson December 20, 2020 at 4:01 pm
Artificial intelligence finds surprising patterns in Earth's biological mass extinctions Date: December 21, 2020 Source: Tokyo Institute of Technology Summary: The idea that mass extinctions allow ...
via Bing News