Collaborating Authors


New deep learning technique paves path to pizza-making robots


This article is part of our coverage of the latest in AI research. For humans, working with deformable objects is not significantly more difficult than handling rigid objects. We learn naturally to shape them, fold them, and manipulate them in different ways and still recognize them. But for robots and artificial intelligence systems, manipulating deformable objects present a huge challenge. Consider the series of steps that a robot must take to shape a ball of dough into pizza crusts.

Artificial Intelligence in Nephrology: How Can Artificial Intelligence Augment Nephrologists' Intelligence?


Background: Artificial intelligence (AI) now plays a critical role in almost every area of our daily lives and academic disciplines due to the growth of computing power, advances in methods and techniques, and the explosion of the amount of data; medicine is not an exception. Rather than replacing clinicians, AI is augmenting the intelligence of clinicians in diagnosis, prognosis, and treatment decisions. Summary: Kidney disease is a substantial medical and public health burden globally, with both acute kidney injury and chronic kidney disease bringing about high morbidity and mortality as well as a huge economic burden. Even though the existing research and applied works have made certain contributions to more accurate prediction and better understanding of histologic pathology, there is a lot more work to be done and problems to solve. Key Messages: AI applications of diagnostics and prognostics for high-prevalence and high-morbidity types of nephropathy in medical-resource-inadequate areas need special attention; high-volume and high-quality data need to be collected and prepared; a consensus on ethics and safety in the use of AI technologies needs to be built. Artificial intelligence (AI) now plays a critical role in almost every area of our daily lives and academic disciplines; medicine is not an exception.

Why we must rethink AI benchmarks


This article is part of our reviews of AI research papers, a series of posts that explore the latest findings in artificial intelligence. For decades, researchers have used benchmarks to measure progress in different areas of artificial intelligence such as vision and language. Especially in the past few years, with deep learning becoming very popular, benchmarks have become a narrow focus for many research labs and scientists. But while benchmarks can help compare the performance of AI systems on specific problems, they are often taken out of context, sometimes to harmful results. In a paper accepted at the NeurIPS 2021 conference, scientists at University of California, Berkeley, University of Washington, and Google outline the limits of popular AI benchmarks.


Communications of the ACM

We present SoundWatch, a smartwatch-based deep learning application to sense, classify, and provide feedback about sounds occurring in the environment.

Doctors Are Very Worried About Medical AI That Predicts Race


To conclude, our study showed that medical AI systems can easily learn to recognise self-reported racial identity from medical images, and that this capability is extremely difficult to isolate,

Deep Learning: Types and Applications in Healthcare


Deep learning (DL), also known as deep structured learning or hierarchical learning, is a subset of machine learning. It is loosely based on the way neurons connect to each other to process information in animal brains. To mimic these connections, DL uses a layered algorithmic architecture known as artificial neural networks (ANNs) to analyze the data. By analyzing how data is filtered through the layers of the ANN and how the layers interact with each other, a DL algorithm can'learn' to make correlations and connections in the data. These capabilities make DL algorithms an innovative tool with the potential to transform healthcare.

Deep Learning Tool Saves Time Selecting Embryos For IVF - AI Summary


Time-lapse images are taken to allow embryologists to track how well an embryo is developing, but manual analysis of these images is time-consuming. AI tools have been developed that analyse these images to classify embryos as good or poor quality, but these tools do not work well with the poor quality of many time-lapse images. Time-lapse imaging, whereby regular images are taken of the embryo, is used to improve assessment by providing the embryologist with more information, however analysing this information is time consuming and often involves analysing multiple images of an embryo taken at the same time. To tackle this challenge researchers at Kaunas University of Technology decided to automate the fusion of time-lapse images taken of embryos, in order to create a better-quality image for analysis by embryologists. The resulting fused images were clearer than the individual images and the two embryologists who took part in the study found they were up to three times faster analysing the fused images than the separate images.

La veille de la cybersécurité


April 28, 2022 – Researchers have developed a convolutional neural network (CNN) model, a type of deep learning model, for classifying epileptic seizures that is designed to provide maximum accuracy and minor computational complexity, according to a study published in Soft Computing. The researchers developed their algorithm by integrating CNN architecture with a hierarchical attention mechanism, which was expected to enhance the model's performance. The model comprises three parts: a feature extraction layer, a hierarchical attention layer, and a classification layer. The model, which also uses a support vector machine (SVM) algorithm, analyzes a feature map obtained from the raw EEG signal and determines whether the EEGs it was taken from are "healthy" or "seizure."

Using AI to diagnose mild cognitive impairment that progresses to Alzheimer's


Alzheimer's disease is the main cause of dementia worldwide. Although there is no cure, early detection is considered crucial for being able to develop effective treatments that act before its progress is irreversible. Mild cognitive impairment is a phase that precedes the disease, but not everyone who suffers from it ends up developing Alzheimer's. A study led by scientists at the Universitat Oberta de Catalunya (UOC) and published in the IEEE Journal of Biomedical and Health Informatics, has succeeded in precisely distinguishing between people whose deterioration is stable and those who will progress to having the disease. The new technique, which uses specific artificial intelligence methods to compare magnetic resonance images, is more effective than the other methods currently in use. Alzheimer's disease affects more than 50 million people worldwide, and the aging of the population means that there may be many more sufferers in the coming decades.

Deepmind's hunger for data: large AI models are far from being fed up


Are giant AI language models like GPT-3 or PaLM under-trained? A Deepmind study shows that we can expect further leaps in performance. Big language models like OpenAI's GPT-3, Deepmind's Gopher, or most recently Google's powerful PaLM rely on lots of data and gigantic neural networks with hundreds of billions of parameters. PaLM, with 540 billion parameters, is the largest language model to date. The trend toward more and more parameters stems from the previous finding that the capabilities of large AI models scale with their size.