The Out Of Africa Inhabitants Are The New Species of Hominids, Which AI Accidentally Discovered

A scientific finding that’s cropping up perhaps upstage the globally believed theory of evolution. Scientists and evolutionary biologists from Estonia and Spain have used deep learning to build a revolutionary model for gauging human evolutionary patterns. Neanderthals and Denisovan bred with humans have always been a well-known fact, but now a third species has been uncovered.

History reminds us that humans came into existence when a Denisovan father and Neanderthal mother bred and a “homosapien” was born as their child. The findings of the research point now that we are a mix of all these three species.

AIM Daily XO

Join our editors every weekday evening as they steer you through the most significant news of the day, introduce you to fresh perspectives, and provide unexpected moments of joy
Your newsletter subscriptions are subject to AIM Privacy Policy and Terms and Conditions.

According to Jaume Bertranpetit, an Institute of Evolutionary Biology one of the lead researcher say that about 80000 years ago, the so-called Out of Africa occurred, when part of the human population, which already consisted of modern humans, abandoned the African continent and migrated to other continents, giving rise to all the current populations.

He further added that the modern humans crossbred with Neanderthals in all the continents, except Africa, with the Denisovans in Oceania and probably in South-East Asia, although the evidence of cross-breeding with a third extinct species had not been confirmed with any certainty.

Download our Mobile App

How AI Found Out The Third Species

    • By combining deep learning algorithms and statistical methods, investigators identified the third species in the genome of Asian individuals, the footprint of a new hominid who cross-bred with its ancestors’ tens of thousands of years ago
    • This finding explained that the hybrid found in the caves of Denisova,  the offspring of a Neanderthal mother and a Denisovan father was not an isolated case but rather was part of a more general introgression process
    • Evidence in the form of demographic analysis, one churned by deep learning and sprinkled with some statistical analysis. Their algorithm devised and compared numerous complex demographic models to make predictions about the history of interbreeding events in Eurasia
    • Deep Learning made it possible to make the transition from DNA to the demographics of ancestral populations
    • Then the researchers fed the algorithm, multiple sets of genome sequences that were derived from both the contemporary and ancient DNA, which enabled the neural network to create a large set of possible demographic histories. After that statistical analysis calculated which among these histories were the most probable ones
    • The piecing together of this genetic jigsaw puzzle yielded the proposed “third archaic introgression”, meaning a third hybridisation event among ancient

Why Was Deep Learning Used?

  • As demographic models analysed were much more complex than anything else till date and as there were also no statistic tools available to analyse them.
  • The only alternative that could reciprocate similar capability was Deep learning, which as an algorithm can help in imitating the way in which the nervous system of mammals works, with different artificial neurons that specialised and learned to detect, in data, patterns that are important for performing any given task.
  • So, the researchers used the very same capability of its to get the algorithm to learn to predict human demographics using genomes obtained through hundreds of thousands of simulations.
  • This research is also touted as first to successfully use deep learning to explain human history, biology, genomics and evolution. 

Interesting Facts

  • Deep learning was used to teach the algorithm to predict human demographics through hundreds of thousands of simulations.
  • The research also bolstered a suggestion that the two extinct species often bred enough to produce a genetically distinguishable hybrid population and concluded that Ancient Human Groups Mated With The Mysterious Denisovans At Least Twice.
  • Genetic analysis conducted in the research also suggested two populations of Denisovans.
  • An extinct group of hominids closely related to Neanderthals existed outside of Africa during the Pleistocene and both those populations interacted and interbred with anatomically modern humans.
  • Dried deep within the DNA of Asian individuals was the genetic clue that pointed towards the existence of an unknown human ancestor and the startling fact was that it was not the humans who reached this startling conjecture, but rather an artificially intelligent algorithm which achieved this feat.
  • Scientists also extracted Denisovan DNA from a well-preserved finger bone which was found in the Siberian cave.


Deep learning is acting as a key to decipher the secrets of human evolution, recessively registered in four walls of ancient DNA. Even though, while the study on the history of interaction between modern humans and archaic hominin contemporaries remains something to vouch for, one should restrain from making claims of genetic mixing from an unknown extinct archaic hominid population.

Sign up for The Deep Learning Podcast

by Vijayalakshmi Anandan

The Deep Learning Curve is a technology-based podcast hosted by Vijayalakshmi Anandan - Video Presenter and Podcaster at Analytics India Magazine. This podcast is the narrator's journey of curiosity and discovery in the world of technology.

Martin F.R.
Martin Fredrick Raj worked as a Technology Journalist at Analytics India Magazine. He usually likes to write detail-oriented articles which are well-researched in articulated formats. Other than covering updates on analytics, artificial intelligence & data science, his interests also include covering politics, economics, finance, consumer electronics, global affairs and issues regarding public policy matters. When not writing any articles, he usually delves into reading biographies of successful entrepreneurs or experiments with his new culinary ideas.

Our Upcoming Events

24th Mar, 2023 | Webinar
Women-in-Tech: Are you ready for the Techade

27-28th Apr, 2023 I Bangalore
Data Engineering Summit (DES) 2023

23 Jun, 2023 | Bangalore
MachineCon India 2023 [AI100 Awards]

21 Jul, 2023 | New York
MachineCon USA 2023 [AI100 Awards]

3 Ways to Join our Community

Telegram group

Discover special offers, top stories, upcoming events, and more.

Discord Server

Stay Connected with a larger ecosystem of data science and ML Professionals

Subscribe to our Daily newsletter

Get our daily awesome stories & videos in your inbox

Council Post: From Promise to Peril: The Pros and Cons of Generative AI

Most people associate ‘Generative AI’ with some type of end-of-the-world scenario. In actuality, generative AI exists to facilitate your work rather than to replace it. Its applications are showing up more frequently in daily life. There is probably a method to incorporate generative AI into your work, regardless of whether you operate as a marketer, programmer, designer, or business owner.