
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
- People Now See AI-Generated Faces as More Real Than Human Oneson November 30, 2023 at 5:09 pm
AI-generated faces are now indistinguishable from real human ones and can be perceived as more trustworthy. The phenomenon of AI faces being perceived as more "human" ...
- Keeping the human at the centre of an AI-powered workplace: HRPA conferenceon November 30, 2023 at 3:31 pm
Conversations around automation and artificial intelligence are eclipsing the existing challenges in the workplace related to, for instance, work-life balance, employee burnout and management of ...
- webAI Launches futureOS: Navigator, a Defining Moment for Human-Centric AI OSon November 30, 2023 at 12:42 pm
November 30, 2023) – webAI, the future of human-centered AI OS, is thrilled to announce the official launch of early access to the first version of its pioneering product, futureOS: Navigator. The ...
- NMPA: Generative AI is ‘the greatest risk to the human creative class that has ever existed’on November 30, 2023 at 12:27 pm
The National Music Publishers Association says it’s members are “not opposed” to AI, but it has some suggestions on how it should be governed.
- AI & Human Collaboration: How New Job Opportunities Can Be Createdon November 30, 2023 at 12:02 pm
OPINION: Opportunities for human-AI collaboration will rise tremendously in areas like predictive maintenance, quality control, process optimisation and Digital Twins.
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
- How Artificial Intelligence Could Transform Health Careon November 30, 2023 at 4:19 pm
Bob Wachter comments on the potential of new generative artificial intelligence tools to transform the health care environment in a way previous technologies could not.
- Stealing fire from the gods: Artificial Intelligence and the evolution of thoughton November 30, 2023 at 12:34 pm
It would be ironic if, to gain more power and control over the world, we used our human intelligence to create AI systems and devices which, for all the benefits they bring, end up managing our lives ...
- When Artificial Intelligence Mimics the Human Brainon November 30, 2023 at 7:54 am
Stepping aside from the complexity of the science, one thing is clear: The line between artificial and natural intelligence is blurring. This research opens doors to new possibilities, from developing ...
- Five of the Top Artificial Intelligence Stocks to Buy and Hold for 2024on November 30, 2023 at 7:32 am
At the moment, companies, like VERSES AI Inc. (NEO: VERS) (OTCQB: VRSSF) are racing toward Artificial General Intelligence (AGI), where AI can perform all human cognitive skills better than the ...
- Meet the Company That's at the Heart of the Artificial Intelligence (AI) Revolutionon November 29, 2023 at 10:17 pm
As investors, it's sometimes helpful to trace down all of the inputs of a value chain for a particular product. This especially rings true for a huge movement like artificial intelligence (AI), as ...
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”]