
via University of Glasgow
Creating human-like AI is about more than mimicking human behaviour – technology must also be able to process information, or ‘think’, like humans too if it is to be fully relied upon.
New research, published in the journal Patterns and led by the University of Glasgow’s School of Psychology and Neuroscience, uses 3D modelling to analyse the way Deep Neural Networks – part of the broader family of machine learning – process information, to visualise how their information processing matches that of humans.
It is hoped this new work will pave the way for the creation of more dependable AI technology that will process information like humans and make errors that we can understand and predict.
One of the challenges still facing AI development is how to better understand the process of machine thinking, and whether it matches how humans process information, in order to ensure accuracy. Deep Neural Networks are often presented as the current best model of human decision-making behaviour, achieving or even exceeding human performance in some tasks. However, even deceptively simple visual discrimination tasks can reveal clear inconsistencies and errors from the AI models, when compared to humans.
Currently, Deep Neural Network technology is used in applications such a face recognition, and while it is very successful in these areas, scientists still do not fully understand how these networks process information, and therefore when errors may occur.
In this new study, the research team addressed this problem by modelling the visual stimulus that the Deep Neural Network was given, transforming it in multiple ways so they could demonstrate a similarity of recognition, via processing similar information between humans and the AI model.
Professor Philippe Schyns, senior author of the study and Head of the University of Glasgow’s Institute of Neuroscience and Technology, said: “When building AI models that behave “like” humans, for instance to recognise a person’s face whenever they see it as a human would do, we have to make sure that the AI model uses the same information from the face as another human would do to recognise it. If the AI doesn’t do this, we could have the illusion that the system works just like humans do, but then find it gets things wrong in some new or untested circumstances.”
The researchers used a series of modifiable 3D faces, and asked humans to rate the similarity of these randomly generated faces to four familiar identities. They then used this information to test whether the Deep Neural Networks made the same ratings for the same reasons – testing not only whether humans and AI made the same decisions, but also whether it was based on the same information. Importantly, with their approach the researchers can visualise these results as the 3D faces that drive the behaviour of humans and networks. For example, a network that correctly classified 2,000 identities was driven by a heavily caricaturised face, showing it identified the faces processing very different face information than humans.
Researchers hope this work will pave the way for more dependable AI technology that behaves more like humans and makes fewer unpredictable errors.
Original Article: DEVELOPING AN AI THAT ‘THINKS’ LIKE HUMANS
More from: University of Glasgow
The Latest Updates from Bing News & Google News
Go deeper with Bing News on:
Human-like AI
- AI Is Like … Nuclear Weapons?on March 26, 2023 at 9:53 am
He had run the calculations, and there was a real possibility, he told his Manhattan Project colleagues in 1942, that when they detonated the world’s first nuclear bomb, the blast would set off a ...
- Human babies still show more common sense than AI … for nowon March 26, 2023 at 7:01 am
NYU psychologists are taking strides toward making artificial intelligence smarter, by testing whether algorithms with visual perception can beat babies at common sense tasks.
- The AI hype is warranted: how will California policy follow suit?on March 26, 2023 at 5:00 am
Catlin argues artificial intelligence will exacerbate existing tech battles while also introducing a whole new set of policy problems.
- Why government is the key to unlocking AI’s true potentialon March 26, 2023 at 5:00 am
Governments possess the key building blocks to unleash AI’s potential — data — but first, governments must learn how to walk with tech before running.
- The Godfather Of Virtual Reality Says Concerns About AI Taking Over The World Is The Stuff Of Sci-Fi Movies Like 'The Matrix'on March 25, 2023 at 5:28 am
In a world inundated with doomsday predictions about artificial intelligence, or AI, the godfather of virtual reality, Jaron Lanier, weighs in on the growing concerns about chatbots. What Happened: ...
Go deeper with Google Headlines on:
Human-like AI
[google_news title=”” keyword=”human-like AI” num_posts=”5″ blurb_length=”0″ show_thumb=”left”]
Go deeper with Bing News on:
Human-like AI artificial intelligence
- Most Jobs Soon To Be ‘Influenced’ By Artificial Intelligence, Research Out Of OpenAI And University Of Pennsylvania Suggestson March 26, 2023 at 9:41 am
Jobs requiring college education will see the highest impacts, and in many cases, at least half of peoples’ tasks may be affected by generative AI.
- There’s No Such Thing as Artificial Intelligenceon March 25, 2023 at 6:53 pm
Artificial intelligence in particular conjures the notion of thinking machines. But no machine can think, and no software is truly intelligent. The phrase alone may be one of the most successful ...
- Have We Created Artificial Intelligence or Artificial Life?on March 25, 2023 at 7:46 am
We have all been reading and hearing a lot about artificial intelligence (AI) recently because it is an absolute game-changer. As AI developers madly rush forward to develop and deploy AIs, we are ...
- "Godfather of artificial intelligence" weighs in on the past and potential of AIon March 25, 2023 at 6:30 am
Geoffrey Hinton, who works with Google and mentors AI's rising stars, started researching artificial intelligence over 40 years ago.
- Artificial Intelligence: A new quantum computing platform for small businesseson March 25, 2023 at 4:08 am
Small business owners' adoption of AI could increase effectiveness and efficiency in their business operations to attain organic growth.
Go deeper with Google Headlines on:
Human-like AI artificial intelligence
[google_news title=”” keyword=”human-like AI artificial intelligence” num_posts=”5″ blurb_length=”0″ show_thumb=”left”]