Toggle light / dark theme

Researchers at the Electronics and Telecommunications Research Institute (ETRI) in Korea have recently developed a deep learning-based model that could help to produce engaging nonverbal social behaviors, such as hugging or shaking someone’s hand, in robots. Their model, presented in a paper pre-published on arXiv, can actively learn new context-appropriate social behaviors by observing interactions among humans.

“Deep learning techniques have produced interesting results in areas such as computer vision and ,” Woo-Ri Ko, one of the researchers who carried out the study, told TechXplore. “We set out to apply to , specifically by allowing robots to learn from human-human interactions on their own. Our method requires no prior knowledge of human behavior models, which are usually costly and time-consuming to implement.”

The (ANN)-based architecture developed by Ko and his colleagues combines the Seq2Seq (sequence-to-sequence) model introduced by Google researchers in 2014 with generative adversarial networks (GANs). The new architecture was trained on the AIR-Act2Act dataset, a collection of 5,000 human-human interactions occurring in 10 different scenarios.

Check out the on-demand sessions from the Low-Code/No-Code Summit to learn how to successfully innovate and achieve efficiency by upskilling and scaling citizen developers. Watch now.

When it comes to artificial intelligence (AI), the past year has been aspirational, but ultimately unsuccessful, says Athina Kanioura, who was named PepsiCo’s first chief strategy and transformation officer in September 2020. But she is optimistic about 2023.

“Think of how we started with the metaverse and the use of AI, suddenly it crumbled into pieces,” she told VentureBeat. “In AI, we tend to see what doesn’t work the first time, then we lose hope — but I think 2023 should be a year of hope and focus for AI.”

To be a sheep is to blindly follow the crowd. But is a sheep’s sheepiness really enough to make an entire flock walk around in a circle non-stop for days on end?

That’s a mystery the internet has pondered for about a week now and solving it has proved more difficult than you’d expect.

On 17 November, a news outlet run by the Chinese state, called People’s Daily, shared an eerie video on Twitter of dozens of sheep in China’s Inner Mongolia Autonomous Region a strolling around in tight, almost perfect concentric circles.

Researchers have developed an energy-efficient soft robot that can swim more than four times faster than previous swimming soft robots by taking inspiration from the biomechanics of the manta ray. Developed at North Carolina State University.

Founded in 1,887 and part of the University of North Carolina system, North Carolina State University (also referred to as NCSU, NC State, or just State) is a public land-grant research university in Raleigh, North Carolina. It forms one of the corners of the Research Triangle together with Duke University in Durham and The University of North Carolina at Chapel Hill.

It’s time to go to bed for artificial neurons.

According to a recent study by the University of California, San Diego, neural networks can imitate the sleep patterns of the human brain in order to tackle catastrophic forgetting.

“The brain is very busy when we sleep, repeating what we have learned during the day,” said Maxim Bazhenov, Ph.D., professor of medicine and a sleep researcher at the University of California San Diego School of Medicine in the press release. “Sleep helps reorganize memories and presents them in the most efficient way.”

Sleep strengthens rational memory, the capacity to recall arbitrary or illogical associations between objects, people, or events, and guards against forgetting previous memories, according to research by Bazhenov and colleagues.

They were created to imitate neural networks within the human brain.

Artificial neural networks (ANNs) mimic biological neural networks in the human brain. ANN consists of an input layer, a hidden layer, and an output layer.

Also called neural nets, ANNs are used daily in healthcare, social media when suggesting people you might know, and in marketing when recommending products to consumers.

Artificial neural networks (ANNs), also known as neural nets, are computing systems that are inspired by the way biological neural networks work in the human, or other animals, brain.


DKosig/iStock.

What is an artificial neural network?