We use both statistical methods and machine learning to understand the relationship between the structure/geometry of porous materials and their mass transport properties, i.e. diffusive transport and fluid flow. In a recent project, we generated a large number of virtual materials structures and computed diffusivity and fluid permeability using lattice Boltzmann methods. The data set consists of 90,000 binary 3D arrays of size 192 3 and the corresponding computed properties, to our knowledge the largest dataset ever of this kind. We used both artificial neural networks (ANNs) and 3D convolutional neural networks (CNNs) to perform nonlinear regression and predict the mass transport properties with high accuracy. However, in many practical cases, only 2D data is available.
I know this topic has been discussed many times. But I recently gave some talks on interpretability (for SCAI and France Innovation) and thought it would be good to include some of my work in this article. The importance of explainability for the decision-making process in machine learning doesn't need to be proved any longer. Users are demanding more explanations, and although there are no uniform and strict definitions of interpretability and explainability, the number of scientific papers explaining artificial intelligence (or XAI) is growing exponentially. As you may know, there are two ways to design an interpretable machine learning process.
It is Monday afternoon at St John's Church of England primary school in Wigan and the children in year six are studying science. One pupil is learning about vitamins, another is looking at a diagram of muscles in the arm and a third is being tested on tabulation. All the students are on iPads, with a personalised programme of lessons created by artificial intelligence (AI). The machine analyses their work and then tailors the learning to each child, allowing them to move at their own pace. Next door, the year fives are doing spelling and grammar.
A Universidad Carlos III de Madrid (UC3M) spin-off, Inrobics Social Robotics, S.L.L., has developed a robotic device that provides an innovative motor and cognitive rehabilitation service that can be used at health centers as well as at home. Inrobics was created using research results from the University's Department of Computer Science and Engineering. The entrepreneurial team has developed a platform made up of four elements: a robot that interacts with the patient, an artificial intelligence system that uses a 3D sensor to control the robot, an application that can be used by health care staff to set up and track sessions, and a cloud-based storage system which contains information and analytics from all of the rehabilitation processes. "The 3D sensor allows us to know the patient's position at all times. For example, we know if they are raising their arm, but we also know if they turn their spine to compensate for difficulty when doing so. All of this information is compiled and entered into the clinical reports that are generated," says Fernando Fernández, professor at the UC3M's Department of Computer Science and Engineering and founding partner of Inrobics.
Britain's National Health Service (NHS) is famous for offering free medical treatment to all UK citizens. Despite this, uptake of some services remains low, particularly in certain ethnic demographics. The British government has spent many years trying to reduce these inequalities – and now they are investigating how artificial intelligence (AI) can help bridge the gap. NHSx – the NHS' AI lab and health foundation – has a mission "to ensure NHS patients are amongst the first in the world to benefit from leading AI," and "a responsibility to ensure those technologies don't exacerbate existing health inequalities." As part of these efforts, NHSx has recently identified four AI projects that will benefit from additional investment.
Scientists at the Human Brain Project (HBP) have outlined in a new research paper how advances in neuroscience require high-computing technology and will eventually need exascale computing power. The HBP is the largest brain science project in Europe, and it is one of the biggest research projects ever funded by the European Union. The project […]
GE Healthcare and Optellum today announced that they have signed a letter of intent to collaborate to advance precision diagnosis and treatment of lung cancer. GE Healthcare is a global leader in medical imaging solutions. Optellum is the leader in AI decision support for the early diagnosis and optimal treatment of lung cancer. This press release features multimedia. Together, the companies are seeking to address one of the largest challenges in the diagnosis of lung cancer, helping providers to determine the malignancy of a lung nodule: a suspicious lesion that may be benign or cancerous.
No news or research item is a personal recommendation to deal. All investments can fall as well as rise in value so you could get back less than you invest. Nvidia reported record third quarter revenue of $7.1bn, up 50% year-on-year, with particularly strong growth in data centres and professional visualization. Operating profits rose 91% to nearly $2.7bn, with only a modest increase in sales, general & administrative expense. The group plans to pay dividends of $0.04 cents per share in the final quarter.
Machine learning (ML), a branch of artificial intelligence (AI), was sometimes referred to as "cognitive computing" in the past, and certain academic circles still today. Machine learning applications have been used for decades to automate complex human tasks that require analytic thinking, but recently the technology has expanded to encompass more business functions. Advanced ML algorithms have automated the game of chess, speech recognition, and some military activities. In the recent years, this forward-thinking science has invaded the mainstream industry sectors such as health care, banking, education, and marketing. Machine learning can help organizations identify which activities are most important for them to focus on, while allowing the machine to handle the rest.