Known as OceanOneK, the robot allows its operators to feel like they're underwater explorers, too. OceanOneK resembles a human diver from the front, with arms and hands and eyes that have 3D vision, capturing the underwater world in full color. The back of the robot has computers and eight multidirectional thrusters that help it carefully maneuver the sites of fragile sunken ships. OceanOneK, here doing an experiment in a swimming pool at Stanford University, resembles a human diver. When an operator at the ocean's surface uses controls to direct OceanOneK, the robot's haptic (touch-based) feedback system causes the person to feel the water's resistance as well as the contours of artifacts.

In 1917, Marcel Duchamp submitted a sculpture to the Society of Independent Artists under a false name. Fountain was a urinal, bought from a toilet supplier, with the signature R. Mutt on its side in black paint. Duchamp wanted to see if the society would abide by its promise to accept submissions without censorship or favor. But Duchamp was also looking to broaden the notion of what art is, saying a ready-made object in the right context would qualify. Then, as before, the debate raged about if something mechanically produced – a urinal, or a soup can (albeit hand-painted by Warhol) – counted as art, and what that meant. Now, the debate has been turned upon its head, as machines can mass-produce unique pieces of art on their own.

Incorporating artificial intelligence has been a key goal for agencies across the executive branch for quite some time. But now, Congress is considering jumping on the bandwagon as well. Lawmakers on the House Select Committee on the Modernization of Congress are interested in exploring just what AI might be able to help them accomplish. Joe Mariani, a research manager for the Deloitte Center for Government Insights, told the committee during a July 28 hearing about... Incorporating artificial intelligence has been a key goal for agencies across the executive branch for quite some time. But now, Congress is considering jumping on the bandwagon as well.

Robust quantization improves the tolerance of networks for various implementations, allowing reliable output in different bit-widths or fragmented low-precision arithmetic. In this work, we perform extensive analyses to identify the sources of quantization error and present three insights to robustify a network against quantization: reduction of error propagation, range clamping for error minimization, and inherited robustness against quantization. Based on these insights, we propose two novel methods called symmetry regularization (SymReg) and saturating nonlinearity (SatNL). Applying the proposed methods during training can enhance the robustness of arbitrary neural networks against quantization on existing post-training quantization (PTQ) and quantization-aware training (QAT) algorithms and enables us to obtain a single weight flexible enough to maintain the output quality under various conditions. We conduct extensive studies on CIFAR and ImageNet datasets and validate the effectiveness of the proposed methods.

Artificial intelligence reaches new adoption levels each year. As its adoption becomes more ubiquitous, industries like supply chain management and logistics have begun to leverage AI in innovative ways - taking the front row in the AI show-time. A recent report by Research and Markets "Artificial Intelligence in Supply Chain Management Market" finds that AI in SCM solutions as a whole will reach $15.5B globally by 2026. The large volumes of data generated by these industry verticals, the number of devices employed and the challenges associated with the process require a more defined, elaborate structure to ensure transparency through digital automation. Events such as the unexpected blocking of the world's busiest trade route Suez Canal by a large shipping vessel demonstrate how supply-chain optimization and diversification have become an essential need of the hour.

Fox News Flash top headlines are here. Check out what's clicking on Foxnews.com. Facing a growing threat from China, the Navy envisions drone ships keeping an electronic eye on enemy forces across the vast Pacific Ocean, extending the reach of firepower, and keeping sailors out of harm's way. The Navy is speeding development of those robotic ships as an affordable way to keep pace with China's growing fleet while vowing not to repeat costly shipbuilding blunders from recent years. The four largest drone ships are being used together this summer during a multination naval exercise in the Pacific Ocean.

"The fact that newer drones, such as the Mohajer-6, are now being seen in places like the Horn of Africa shows that countries see them as a potential game-changer," he added, referring to an advanced Iranian drone claimed to have a range of about 125 miles and the ability to carry precision-guided munitions. "It's amazing warfare on the cheap," said Mr. Frantzman, adding that Iranian drones cost less than other models on the market but were growing in sophistication, and had proved their worth on battlefields across the Middle East. Tehran began drone development in the 1980s during the Iran-Iraq war. Despite crippling sanctions imposed on Iran over its nuclear and missile programs in recent years, it has managed to produce and field a vast array of military drones, used for both surveillance and attack, according to analysis by experts. That program has become a major concern for Israel and the United States in recent years.

Language is our lifeline to the world. But because high-quality translation tools don't exist for hundreds of languages, billions of people today can't access digital content or participate fully in conversations and communities online in their preferred or native languages. This is particularly an issue for hundreds of millions of people who speak the many languages of Africa and Asia. To help people connect better today and be part of the metaverse of tomorrow, our AI researchers created No Language Left Behind (NLLB), an effort to develop high-quality machine translation capabilities for most of the world's languages. Today, we're announcing an important breakthrough in NLLB: We've built a single AI model called NLLB-200, which translates 200 different languages with results far more accurate than what previous technology could accomplish.

Signal Processing Society Magazine Best Paper Award (ICASSPにて) A. Cichocki (Skoltech) L. De Lathauwer (KULeuven) 19 テンソル分解のパイオニアと重要な文献 Sidiropoulosらのレビュー論文 Tensor Decomposition for Signal Processing and Machine Learning Sidiropoulos, IEEE TSP, 2017 [pdf] Cichockiらの書籍 Tensor Networks for Dimensionality Reduction and Large-Scale Optimization: Part 1 [link], Part 2 [pdf] Cichocki, Foundations and Trends in Machine Learning, 2016 [link] N. Sidiropoulos (Univ. of Virginia) 20 宣伝 Book chapterを書きました Tensors for Data Processing, Elsevier, 2021 [link] 目次 1章 Tensor decompositions: Computations, applications, and challenges 2章 Transform-based tensor SVD in multidimensional image recovery 3章 Partensor 4章 A Riemannian approach to low-rank tensor learning 5章 Generalized thresholding for low-rank tensor recovery 6章 Tensor principal component analysis 7章 Tensors for deep learning theory 8章 Tensor network algorithms for image classification 9章 High-performance TD for compressing and accelerating DNN 10章 Coupled tensor decomposition for data fusion 11章 Tensor methods for low-level vision T. Yokota, CF.

Two major causes of death in the United States and worldwide are stroke and myocardial infarction. The underlying cause of both is thrombi released from ruptured or eroded unstable atherosclerotic plaques that occlude vessels in the heart (myocardial infarction) or the brain (stroke). Clinical studies show that plaque composition plays a more important role than lesion size in plaque rupture or erosion events. To determine the plaque composition, various cell types in 3D cardiovascular immunofluorescent images of plaque lesions are counted. However, counting these cells manually is expensive, time-consuming, and prone to human error. These challenges of manual counting motivate the need for an automated approach to localize and count the cells in images. The purpose of this study is to develop an automatic approach to accurately detect and count cells in 3D immunofluorescent images with minimal annotation effort. In this study, we used a weakly supervised learning approach to train the HoVer-Net segmentation model using point annotations to detect nuclei in fluorescent images. The advantage of using point annotations is that they require less effort as opposed to pixel-wise annotation. To train the HoVer-Net model using point annotations, we adopted a popularly used cluster labeling approach to transform point annotations into accurate binary masks of cell nuclei. Traditionally, these approaches have generated binary masks from point annotations, leaving a region around the object unlabeled (which is typically ignored during model training). However, these areas may contain important information that helps determine the boundary between cells. Therefore, we used the entropy minimization loss function in these areas to encourage the model to output more confident predictions on the unlabeled areas. Our comparison studies indicate that the HoVer-Net model trained using our weakly ...