Researchers have developed artificial intelligence tools that may help to identify health problems faster and more efficiently.
Machine learning & AI
Elon Musk’s new sci-fi project Neuralink hopes to connect the human brain with AI
Elon Musk, Tesla’s CEO, is backing a new startup that is seeking to develop smart devices to be implanted in the human brain, pursuing one of the most sci-fi inspired ideas the world has ever heard of.
Three convolutional neural network models for facial expression recognition in the wild
Two researchers at Shanghai University of Electric Power have recently developed and evaluated new neural network models for facial expression recognition (FER) in the wild. Their study, published in Elsevier's Neurocomputing journal, presents three models of...
Using imitation and reinforcement learning to tackle long-horizon robotic tasks
Reinforcement learning (RL) is a widely used machine-learning technique that entails training AI agents or robots using a system of reward and punishment. So far, researchers in the field of robotics have primarily applied RL techniques in tasks that are completed...
Using Spotify data to predict what songs will be hits
Two students and researchers at the University of San Francisco (USF) have recently tried to predict billboard hits using machine-learning models. In their study, pre-published on arXiv, they trained four models on song-related data extracted using the Spotify Web...
Researchers use computer vision to better understand optical illusions
Optical illusions, images that deceive the human eye, are a fascinating research topic, as studying them can provide valuable insight into human cognition and perception. Researchers at Flinders University, in Australia, have recently carried out a very interesting...
SentiArt: a sentiment analysis tool for profiling characters from world literature texts
Arthur Jacobs, a professor and researcher at Freie Universität Berlin, has recently developed SentiArt, a new machine learning technique to carry out sentiment analyses of literary texts, as well as both fictional and non-fictional figures. In his paper, set to be...
SPFCNN-Miner: A new classifier to tackle class-unbalanced data
Researchers at Chongqing University in China have recently developed a cost-sensitive meta-learning classifier that can be used when the training data available is high-dimensional or limited. Their classifier, called SPFCNN-Miner, was presented in a paper published...
Infusing machine learning models with inductive biases to capture human behavior
Human decision-making is often difficult to predict and delineate theoretically. Nonetheless, in recent decades, several researchers have developed theoretical models aimed at explaining decision-making, as well as machine learning (ML) models that try to predict...
Kaolin: The first comprehensive library for 3-D deep learning research
As most real-world environments are three-dimensional, deep learning models designed to analyze videos or complete tasks in real-world environments should ideally be trained on 3-D data. Technological tools such as robots, self-driving vehicles, smartphones, and other...