Colin G. Johnson, an associate professor at the University of Nottingham, recently developed a deep-learning technique that can learn a so-called "fitness function" from a set of sample solutions to a problem. This technique, presented in a paper published in...
Machine learning & AI
Researchers examine how multilingual BERT models encode grammatical features
Over the past few decades, researchers have developed deep neural network-based models that can complete a broad range of tasks. Some of these techniques are specifically designed to process and generate coherent texts in multiple languages, translate texts, answer...
A robot that allows users to virtually navigate remote environments
Two students who graduated from VR Siddartha Engineering College in Kanuru, India, have created a virtual telepresence robot that allows users to see what is happening in a remote location as if they were actually there. Their project, supervised by Professor V.N....
A system that automatically generates comic books from movies and other videos
Over the past few years, computer scientists have created numerous computational techniques that can automatically generate texts, images and other types of data. These models are highly advantageous, particularly for creating data or creative works that are demanding...
HuggieBot 2.0: A soft and human-size robot that hugs users on request
Researchers at the Max Planck Institute for Intelligent Systems (MPI-IS) and ETH Zürich have recently created HuggieBot 2.0, a robot that can hug users at their request. This robot, set to be presented at the ACM/IEEE International Conference on Human-Robot...
A machine learning framework that exploits memristor variability to implement Markov chain Monte Carlo sampling
Memristors, or resistive memory devices (RRAM) are nanometer-sized electronic components that can serve as memories for portable computers and other devices. When they are organized in a cross-bar structure, these tiny memories can be used to perform matrix...
Deep learning-based assessment of student engagement could aid classroom research
Past research has identified student engagement, or the extent to which students participate and are involved in classroom activities, as a crucial factor determining both the quality of education programs and the academic performance of individual students. As a...
Using AUVs to control the outbreak of crown-of-thorns starfish in Australia’s Great Barrier Reef
Over the past few decades, people around the world have been dealing with a vast variety of environmental threats. In Australia, these include risks associated with the deterioration and destruction of aquatic plants, animals and other organisms that inhabit...
A technique to estimate emotional valence and arousal by analyzing images of human faces
In recent years, countless computer scientists worldwide have been developing deep neural network-based models that can predict people's emotions based on their facial expressions. Most of the models developed so far, however, merely detect primary emotional states...
Tiny bio-inspired swarm robots for targeted medical interventions
Micro-sized robots could bring a new wave of innovation in the medical field by allowing doctors to access specific regions inside the human body without the need for highly invasive procedures. Among other things, these tiny robots could be used to carry drugs, genes...