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 can reveal new cell biology just by looking at imageson August 1, 2022 at 1:11 pm
Humans are good at looking at images and finding patterns or making comparisons. Look at a collection of dog photos, for example, and you can sort them by color, by ear size, by face shape, and so on.
- No code, no problem—we try to beat an AI at its own game with new toolson August 1, 2022 at 6:00 am
And some people even think that an AI has attained sentience. (Spoiler alert: It has not .) And as Ars' Matt Ford recently pointed out here, artificial intelligence may be artificial, but it's not ...
- AI predicts what 'last selfies' before end of the world will look like. Pics, video insideon August 1, 2022 at 3:30 am
A video created by the AI program shows a battered, bruised and disfigured man appears to look around what seems like a post-apocalyptic world before smiling painfully for a selfie.
- How the last Selfie ever taken on Earth would look like: This is what AI "thinks"on July 31, 2022 at 10:13 pm
TikTok account “Robot Overloads” used OpenAI's DALL-E AI to generate what it thinks the last selfie ever taken on Earth would look like.
- Your favourite Instagram face might not be a human. How AI is taking over influencer roleson July 31, 2022 at 9:29 pm
The CGI (computer-generated imagery) technology isn't new. But it has only recently been used to make influencers ...
Go deeper with Google Headlines on:
Human-like AI
Go deeper with Bing News on:
Human-like AI artificial intelligence
- Artificial Intelligence reveals shape of every protein known to scienceon August 1, 2022 at 1:33 am
Google's AI has predicted the shape of all 200 million proteins known to science, including that of plants, animals and microorganisms.
- RAKEZ welcomes American artificial intelligence company Falcons.AIon August 1, 2022 at 12:31 am
RAKEZ is a powerhouse business and industrial hub established by the Government of Ras Al Khaimah in the United Arab Emirates. It currently hosts over 15,000 companies coming from over 100+ countries ...
- 'Alternative physics' discovered by artificial intelligenceon July 31, 2022 at 2:55 am
An artificial intelligence program has studied various physical phenomena and identified its own variables for describing them.
- Rather than threaten jobs, artificial intelligence should collaborate with human writerson July 29, 2022 at 7:30 am
The Guardian published an opinion piece written by a program. The artificial intelligence, called GPT-3, is a large language model developed by OpenAI, and it posed a bold question in the headline of ...
- The hype around artificial intelligenceon July 29, 2022 at 1:32 am
Gabriella Kereszturi, Senior Lecturer in Marketing at University of Law Business School, walks us through the hype of artificial intelligence ...