The paper describes a method to decode natural images from retinal-like activities, using convolutional neural networks. The retinal-like activities are generated by a constructed lattice of linear-nonlinear-Poisson models (separately fitted to RGC responses to natural scenes in a macaque retina preparation) in response to natural static images. After a simple linear decoding of the images from the retinal-like activities, a convolutional neural network further improves on the reconstruction of the original natural images. The paper is clearly written and the results seem sound. A few comments to clarify the motivation, assumptions and impact of the work: -the method proposed is compared to a linear decoder and shown to perform substantially better. However, the performance of the decoding stage will most likely depend on the performance of the encoding stage.

Ancient rock carvings have been uncovered near the Amazon River amid drought conditions in Brazil. A set of ancient texts burned by the volcanic eruption on Mount Vesuvius in 79 A.D. have been deciphered thanks to a team of researchers using AI. The nearly 2,000-year-old texts were unreadable after being charred in a villa in Herculaneum, a Roman town near Pompeii. The texts were discovered in an ancient villa in the town of Herculaneum. Believed to have been owned by the father-in-law of Julius Caesar, the texts were carbonized by the heat of the volcanic debris.

Artificial intelligence has come to stay in the healthcare industry. The term refers to a constellation of computational tools that can comb through vast troves of data at rates far surpassing human ability, in a way that can streamline providers' jobs. Regardless of the specific type of AI, these tools are generally capable of making a massive, complex industry run more efficiently. But several studies show it can also propagate racial biases, leading to misdiagnosis of medical conditions among people of colour, insufficient treatment of pain, under-prescription of life-affirming medications, and more. Many patients don't even know they've been enrolled in healthcare algorithms that are influencing their care and outcomes.

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.

EARLY LAST year, researchers at the Massachusetts Institute of Technology (MIT) used a machine-learning algorithm to look for new antibiotics. After training the system on molecules with antimicrobial properties, they let it loose on huge databases of compounds and found one that worked. Because it operated in a different way, even bacteria that had developed a resistance to traditional antibiotics could not evade the new drug. Your browser does not support the audio element. Behind the success was a deeper truth: the algorithm was able to spot aspects of reality that humans had not contemplated, might not be able to detect and may never comprehend.

August 11, 2021 A team of researchers in Barcelona have gathered bioactivity information for a million molecules using deep machine-learning computational models and a database of experimental results. Both the experimental results and the machine learning tool are available to the community at bioactivitysignatures.org. The work originated with the Structural Bioinformatics and Network Biology laboratory at the Institute for Research in Biomedicine (IRB) in Barcelona, Spain. In May 2020, the team published in Nature Biotechnology an integration of the major chemogenomics and drug databases including ChEMBL and DrugBank (DOI: 10.1038/s41587-020-0502-7). The result is Chemical Checker (CC), a database that includes processed, harmonized, and integrated bioactivity data on more than 800,000 small molecules.

A little over a year ago, OpenAI, an artificial intelligence company based in San Francisco, stunned the world by showing a dramatic leap in what appeared to be the power of computers to form natural-language sentences, and even to solve questions, such as completing a sentence, and formulating long passages of text people found fairly human. The latest work from that team shows how OpenAI's thinking has matured in some respects. GPT-3, as the newest creation is called, emerged last week, with more bells and whistles, created by some of the same authors as the last version, including Alec Radford and Ilya Sutskever, along with several additional collaborators, including scientists from Johns Hopkins University. It is now a truly monster language model, as it's called, gobbling two orders of magnitude more text than its predecessor. But within that bigger-is-better stunt, the OpenAI team seem to be approaching some deeper truths, much the way Dr. David Bowman approached the limits of the known at the end of the movie 2001.

Imagine a collection of books--maybe millions or even billions of them--haphazardly tossed by publishers into a heaping pile in a field. Every day the pile grows exponentially. Those books are brimming with knowledge and answers. But how would a seeker find them? Lacking organization, the books are useless. This is the raw internet in all its unfiltered glory.

A big part of personalized medicine in cancer is knowing ahead of time if a drug is likely to be effective or not. That's usually done by identifying actionable genetic mutations. But a team of researchers recently developed a potentially quicker and more consistent tool based on omics data: a machine learning algorithm that ranks drugs based on their anti-proliferative efficacy in cancer cells. Known as Drug Ranking Using Machine Learning (DRUML), the method was developed at Queen Mary University in London and is based on machine learning analysis of protein omics data in cancer cells. DRUML was created based on training responses of cancer cells to 412 cancer drugs to predict the most appropriate one to treat a particular cancer.

IMAGE: A team of doctors led by UVA Health's James H. Harrison Jr., MD, PhD, has given us a glimpse of tomorrow in a new article on the current state and... view more Artificial intelligence can already scan images of the eye to assess patients for diabetic retinopathy, a leading cause of vision loss, and to find evidence of strokes on brain CT scans. But what does the future hold for this emerging technology? How will it change how doctors diagnose disease, and how will it improve the care patients receive? A team of doctors led by UVA Health's James H. Harrison Jr., MD, PhD, has given us a glimpse of tomorrow in a new article on the current state and future use of artificial intelligence (AI) in the field of pathology. Harrison and other members of the College of American Pathologists' Machine Learning Workgroup have spent the last two years evaluating the potential of AI and machine learning, assessing its current role in diagnostic testing and outlining what is needed to meet its potential in the not-too-distant future.