There is an increasing demand for piloted autonomous underwater vehicles (AUVs) to operate in polar ice conditions. At present, AUVs are deployed from ships and directly human-piloted in these regions, entailing a high carbon cost and limiting the scope of operations. A key requirement for long-term autonomous missions is a long-range route planning capability that is aware of the changing ice conditions. In this paper we address the problem of automating long-range route-planning for AUVs operating in the Southern Ocean. We present the route-planning method and results showing that efficient, ice-avoiding, long-distance traverses can be planned.

I recently wrote the book that I wish existed when I was introduced to machine learning: Human-in-the-Loop Machine Learning: Active Learning and Annotation for Human-Centered AI. Most machine learning models are guided by human-annotated data, but most machine learning books and courses focus on algorithms. You can often get state-of-the-art results with good data and simple algorithms, but you rarely get state-of-the-art results from the best algorithm with bad data. So if you need to go deep in one area of machine learning first, you could argue that the data side is more important. In addition to the technical focus of the book, it features anecdotes from 11 machine learning experts. Each shared an anecdote about data-related problems they encountered building and evaluating machine learning models in real-world situations. Their stories tell us something important about machine learning leadership more broadly, with each anecdote tying into a lesson about running successful data science projects.

Hassan Tetteh has one of the coolest-sounding jobs in medicine. His official title is Warfighter Health Mission Chief for the Department of Defense Joint Artificial Intelligence Center. The Pentagon established the JAIC, or "Jake" as he pronounces it, in 2018 to ensure that America's combat operations don't fall behind rivals in using machine learning to enhance troop readiness, cybersecurity, joint maneuvers and "lethality." Dr. Tetteh, 49, heads the JAIC's health mission. A decorated Navy captain, he's also a cardiothoracic surgeon who has deployed in Afghanistan and on warships in the Persian Gulf as well as at Walter Reed hospital.

In recent years, low-resource Machine Reading Comprehension (MRC) has made significant progress, with models getting remarkable performance on various language datasets. However, none of these models have been customized for the Urdu language. This work explores the semi-automated creation of the Urdu Question Answering Dataset (UQuAD1.0) by combining machine-translated SQuAD with human-generated samples derived from Wikipedia articles and Urdu RC worksheets from Cambridge O-level books. UQuAD1.0 is a large-scale Urdu dataset intended for extractive machine reading comprehension tasks consisting of 49k question Answers pairs in question, passage, and answer format. In UQuAD1.0, 45000 pairs of QA were generated by machine translation of the original SQuAD1.0 and approximately 4000 pairs via crowdsourcing. In this study, we used two types of MRC models: rule-based baseline and advanced Transformer-based models. However, we have discovered that the latter outperforms the others; thus, we have decided to concentrate solely on Transformer-based architectures. Using XLMRoBERTa and multi-lingual BERT, we acquire an F1 score of 0.66 and 0.63, respectively.

We study anomaly detection for the case when the normal class consists of more than one object category. This is an obvious generalization of the standard one-class anomaly detection problem. However, we show that jointly using multiple one-class anomaly detectors to solve this problem yields poorer results as compared to training a single one-class anomaly detector on all normal object categories together. We further develop a new anomaly detector called DeepMAD that learns compact distinguishing features by exploiting the multiple normal objects categories. This algorithm achieves higher AUC values for different datasets compared to two top performing one-class algorithms that either are trained on each normal object category or jointly trained on all normal object categories combined. In addition to theoretical results we present empirical results using the CIFAR-10, fMNIST, CIFAR-100, and a new dataset we developed called RECYCLE.

Madagascar's critically endangered'singing' lemurs -- Indri indri -- have a natural ability to keep a beat, just like us humans do, a study has concluded. Researchers from the Max Planck Institute for Psycholinguistics and the University of Turin studied the songs of indri in the rainforests of the island country. They found that the lemurs' strange, wailing songs have the same kinds of universal, categorical rhythms found across human musical cultures. Outside of humans, having rhythm is a rare trait in mammals -- although it can be found elsewhere in the animal kingdom, perhaps most notably in songbirds. Madagascar's critically endangered'singing' lemurs -- Indri indri -- have a natural ability to keep a beat, just like us humans do, a study has concluded.

We introduce Ego4D, a massive-scale egocentric video dataset and benchmark suite. It offers 3,025 hours of daily-life activity video spanning hundreds of scenarios (household, outdoor, workplace, leisure, etc.) captured by 855 unique camera wearers from 74 worldwide locations and 9 different countries. The approach to collection is designed to uphold rigorous privacy and ethics standards with consenting participants and robust de-identification procedures where relevant. Ego4D dramatically expands the volume of diverse egocentric video footage publicly available to the research community. Portions of the video are accompanied by audio, 3D meshes of the environment, eye gaze, stereo, and/or synchronized videos from multiple egocentric cameras at the same event. Furthermore, we present a host of new benchmark challenges centered around understanding the first-person visual experience in the past (querying an episodic memory), present (analyzing hand-object manipulation, audio-visual conversation, and social interactions), and future (forecasting activities). By publicly sharing this massive annotated dataset and benchmark suite, we aim to push the frontier of first-person perception. Project page: https://ego4d-data.org/

OceanX, a team of marine biologists, media and filmmakers, embarked on a quest in 2020 to explore the depths of the Red Sea where they not only found a giant shipwreck, but a massive creature that appeared to be larger than a human. While investigating the'Pella,' which sank in November 2011, at a depth of 2,800 feet, the group spotted what they thought could be'The Giant Squid.' 'I will never forget what happened next for as long as I live,' said OceanX science program lead Mattie Rodrigue in a video taken of the discovery. 'All of a sudden, as we're looking at the bow of the shipwreck, this massive creature comes into view, takes a look at the ROV [remotely operated vehicle] and curls its entire body around the bow of the wreck.' It was not until September 2021 did the team learn that the mysterious creature was'the giant form' of the purpleback flying squid, which typically grow up to two feet long. The OceanX team traveled to the Red Sea aboard the OceanXplorer, a research vessel with a 40-ton crane to launch submersibles, towed sonar arrays and other heavy equipment down into the depths.

Behind Sahej, hanging on the wall, Nayana could see rows of colorful masks, which, she learned, Sahej had carved and painted himself. On the first day of the new term, the teacher had asked Sahej about the masks, and the new student shyly gave a show-and-tell, explaining how the masks combined Indian gods and spirits with the powers of superheroes. Now, in an invitation-only room on her ShareChat, some of Nayana's classmates were gossiping about Sahej. From the way his room was furnished to the fact that his surname was hidden from public view in school records, these girls were certain Sahej was among the "vulnerable group" that the government mandated make up at least 15% of their student body. At private schools across India, such children were practically guaranteed spots and their tuition, books, and uniforms were covered by scholarships.

Afghanistan War veteran Rep. Mike Waltz, R-Fla., and Rep. Michael McCaul, R-Texas, weigh the consequences of Biden's overseas withdrawal. A senior al Qaeda leader has been killed in a drone strike in Syria, U.S. defense officials confirmed to Fox News Thursday. Salim Abu-Ahmad was killed in a U.S. airstrike near Idlib, Syria on Sept. 20. He was responsible for planning, funding, and approving trans-regional al Qaeda attacks. A U.S. Air Force MQ-1B Predator unmanned aerial vehicle (UAV), carrying a Hellfire missile flies over an air base after flying a mission in the Persian Gulf region.