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
- DeepMind is Google's AI research hub. Here's what it does, where it's located, and how it differs from OpenAI.on May 10, 2024 at 4:45 pm
Google DeepMind develops AI with the goal of making an artificial general intelligence. Here's what DeepMind does and how it differs from OpenAI.
- AI’s Next Big Step: Detecting Human Emotion and Expressionon May 10, 2024 at 3:00 pm
Emotionally intelligent bots may soon understand how you feel when you talk to them and reply with empathy. Is this the future? The post AI’s Next Big Step: Detecting Human Emotion and Expression ...
- The Rise of Deceptive AI: Manipulation to Achieve Goalson May 10, 2024 at 1:06 pm
Researchers found that AI systems like Meta's CICERO, developed for games like Diplomacy, often adopt deception as a strategy to excel, despite training intentions.
- AI systems are already skilled at deceiving and manipulating humanson May 10, 2024 at 9:25 am
Many artificial intelligence (AI) systems have already learned how to deceive humans, even systems that have been trained to be helpful and honest. Researchers describe the risks of deception by AI ...
- Grammy nominee Bas said AI still can't make music that evokes feeling: 'AI never been to the club.'on May 10, 2024 at 7:42 am
At the "Leading with AI" conference at Harvard, Grammy-nominated rapper Bas said AI won't replace human musicians anytime soon.
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
- Promises and pitfalls of artificial intelligence in healthcareon May 9, 2024 at 4:59 pm
This brings us to artificial intelligence (AI), which is defined as “…the simulation of human intelligence by a system or a machine… [with the goal of AI to] … develop a machine that can think like ...
- Artificial Intelligence- A crucial testament of Human Destructionon May 9, 2024 at 4:25 pm
Dr Sunish Sharma The debate over Artificial Intelligence (AI) and all possible damage it can do has accelerated in last few months. From ChatGPT to deepfakes to AI generated music, pictures and art ...
- Human-sounding AI can plan, help book your travel. But can you trust it?on May 9, 2024 at 6:54 am
Artificial intelligence-driven tools like Layla can now turn back the clock on that experience, engaging with users almost like humans to customize travel plans with lightning speed plus all the ...
- In an Era of Artificial Intelligence and Big Data, Human Touch Is Neededon May 8, 2024 at 6:19 am
While AI can assist with some decisions, it’s feasible that, at some level, overreliance on these technological capabilities ...
- Artificial Intelligence And Human Expertise In Graphic Designon May 8, 2024 at 4:15 am
Technology has long been a key part of graphic design, but modern AI-powered tools are going beyond traditional tools by leaps and bounds.
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”]