New research proposes a new direction to overcome limitations of machine learning
Babies can help unlock the next generation of artificial intelligence (AI), according to Trinity neuroscientists and colleagues who have just published new guiding principles for improving AI.
The research, published today in the journal Nature Machine Intelligence, examines the neuroscience and psychology of infant learning and distils three principles to guide the next generation of AI, which will help overcome the most pressing limitations of machine learning.
Dr Lorijn Zaadnoordijk, Marie Skodowska-Curie Research Fellow at Trinity College explained:
Artificial intelligence (AI) has made tremendous progress in the last decade, giving us smart speakers, autopilots in cars, ever-smarter apps, and enhanced medical diagnosis. These exciting developments in AI have been achieved thanks to machine learning which uses enormous datasets to train artificial neural network models. However, progress is stalling in many areas because the datasets that machines learn from must be painstakingly curated by humans. But we know that learning can be done much more efficiently, because infants don’t learn this way! They learn by experiencing the world around them, sometimes by even seeing something just once.
In their article ‘Lessons from infant learning for unsupervised machine learning’, Dr Lorijn Zaadnoordijk and Professor Rhodri Cusack, from the Trinity College Institute of Neuroscience (TCIN), and Dr Tarek R. Besold from TU Eindhoven, the Netherlands, argue that better ways to learn from unstructured data are needed. For the first time, they make concrete proposals about what particular insights from infant learning can be fruitfully applied in machine learning and how exactly to apply these learnings.
Machines, they say, will need in-built preferences to shape their learning from the beginning. They will need to learn from richer datasets that capture how the world is looking, sounding, smelling, tasting and feeling. And, like infants, they will need to have a developmental trajectory, where experiences and networks change as they “grow up”.
Dr Tarek R. Besold, Researcher, Philosophy & Ethics group at TU Eindhoven, said:
As AI researchers we often draw metaphorical parallels between our systems and the mental development of human babies and children. It is high time to take these analogies more seriously and look at the rich knowledge of infant development from psychology and neuroscience, which may help us overcome the most pressing limitations of machine learning.
Professor Rhodri Cusack, The Thomas Mitchell Professor of Cognitive Neuroscience, Director of Trinity College Institute of Neuroscience, added:
Artificial neural networks were in parts inspired by the brain. Similar to infants, they rely on learning, but current implementations are very different from human (and animal) learning. Through interdisciplinary research, babies can help unlock the next generation of AI.
Original Article: Are babies the key to the next generation of artificial intelligence?
More from: Trinity College Dublin | Eindhoven University of Technology
The Latest on: Limitations of machine learning
- Machine language predicts bird migration and identifies birds by their callson March 27, 2023 at 2:04 am
Machine learning is also changing many fields that may seem surprising. One example is my discipline, ornithology the study of birds. It isn't just solving some of the biggest challenges associated ...
- An 'ecosystem' of tools to boost machine learning-based design of metal–organic frameworkson March 24, 2023 at 8:19 am
A team of chemists and computer scientists from the Swiss Federal Institute of Technology Lausanne, the University of California and Institut des Sciences et Ingenierie Chimiques, Ecole, have ...
- Scientists are using machine learning to forecast bird migration and identify birds in flight by their callson March 24, 2023 at 8:15 am
With chatbots like ChatGPT making a splash, machine learning is playing an increasingly prominent role in our lives. For many of us, it's been a mixed bag. We rejoice when our Spotify For You playlist ...
- How machine learning is helping scientists forecast bird migrationon March 24, 2023 at 7:15 am
As billions of birds migrate to their breeding grounds this spring, people will engage with these flights in new ways, thanks to BirdCast and Merlin.
- Machine intelligence and humanity benefit from 'spiral' of mutual learning, says proponent of 'cognitive physics'on March 17, 2023 at 11:00 am
Deyi Li from the Chinese Association for Artificial Intelligence believes that humans and machines have a mutually beneficial relationship.
- Machine intelligence and humanity benefit from ‘spiral’ of mutual learning, says AI researcher and proponent of ‘cognitive physics’on March 16, 2023 at 5:00 pm
Deyi Li from the Chinese Association for Artificial Intelligence believes that humans and machines have a mutually beneficial relationship. His paper on machine intelligence, which was published Feb.
- Deep Learning vs. Machine Learning: What's the Difference?on March 15, 2023 at 11:30 am
Deep learning and machine learning are two important fields in artificial intelligence. But how do they differ?
- Noam Chomsky: The False Promise of ChatGPTon March 11, 2023 at 11:16 am
By Noam Chomsky, Ian Roberts and Jeffrey Watumull Dr. Chomsky and Dr. Roberts are professors of linguistics. Dr. Watumull is a director of artificial intelligence at a science and technology company.
- Data Analytics and Machine Learning Concentrationon March 1, 2022 at 10:24 am
Students learn the limitations and potential of statistics ... This course offers students a practical introduction to using Machine Learning algorithms, tools, and techniques for solving problems ...
- Machine Learning: The New Language Of Leadershipon October 25, 2018 at 4:38 am
Paul Lipman has worked in the cyber world for over a decade and is currently CEO of BullGuard, a global leader in smart home cybersecurity. A more immediate and perhaps even more profound impact ...
via Bing News
The Latest on: Limitations of machine learning
[google_news title=”” keyword=”limitations of machine learning” num_posts=”10″ blurb_length=”0″ show_thumb=”left”]
via Google News