A team of researchers at The University of Cambridge has recently introduced a unique experimental testbed that could be used for experiments in cooperative driving. This testbed, presented in a paper pre-published on arXiv, consists of 16 miniature Ackermann-steering...
TECHXPLORE
An approach for securing audio classification against adversarial attacks
Adversarial audio attacks are small perturbations that are not perceivable by humans and are intentionally added to audio signals to impair the performance of machine learning (ML) models. These attacks raise serious concerns about the security of ML models, as they...
Evolving neural networks with a linear growth in their behavior complexity
Evolutionary algorithms (EAs) are designed to replicate the behavior and evolution of biological organisms while solving computing problems. In recent years, many researchers have developed EAs and used them to tackle a variety of optimization tasks.
A new approach for unsupervised paraphrasing without translation
In recent years, researchers have been trying to develop methods for automatic paraphrasing, which essentially entails the automated abstraction of semantic content from text. So far, approaches that rely on machine translation (MT) techniques have proved particularly...
Investigating the self-attention mechanism behind BERT-based architectures
BERT, a transformer-based model characterized by a unique self-attention mechanism, has so far proved to be a valid alternative to recurrent neural networks (RNNs) in tackling natural language processing (NLP) tasks. Despite their advantages, so far, very few...
Investigating robot illusions and simulations of reality
To evaluate the performance of robotics algorithms and controllers, researchers typically use software simulations or real physical robots. While these may appear as two distinct evaluation strategies, there is a whole other range of possibilities that combine...
A new approach to enhance robot navigation in indoor environments
To effectively navigate their surroundings, robots typically plan paths based on pre-designed maps of the environment they are operating in and observations gathered by their sensors. While this type of navigation strategy can be useful in simple and static...
A bio-inspired flow-sensing cupula for submersible robotics
Nature can be a precious source of inspiration for researchers developing robots and artificial intelligence (AI) systems. Studies in submersible robotics, for instance, have often tried to replicate or incorporate mechanisms observed in aquatic life, such as fish...
A deep learning approach to coordinate defensive escort teams
Advancements in robotics and artificial intelligence (AI) are enabling the development of artificial agents designed to assist humans in a variety of everyday settings. One of the many possible uses for these systems could be to escort humans or valuable goods that...
An approach to enhance question answering (QA) models
Identifying the correct answer to a question often entails gathering large amounts of information and understanding complex ideas. In a recent study, a team of researchers at New York University (NYU) and Facebook AI Research (FAIR) investigated the possibility of...









