A United States drone strike killed Al Qaeda chief Ayman al-Zawahiri at a hideout in the Afghan capital, President Joe Biden said Monday, adding "justice had been delivered" to the families of the September 11, 2001 attacks. In a somber televised address, Biden said he gave the final go-ahead for the high-precision strike that successfully targeted Zawahiri in the Afghan capital over the weekend. "Justice has been delivered and this terrorist leader is no more," Biden said, adding that he hoped Zawahiri's death would bring "closure" to families of the 3,000 people killed in the United States on 9/11. A senior administration official said Zawahiri was on the balcony of a house in Kabul when he was targeted with two Hellfire missiles, an hour after sunrise on July 31, and that there had been no US boots on the ground in Afghanistan. "We are not aware of him ever leaving the safe house. We identified Zawahiri on multiple occasions for sustained periods of time on the balcony of where he was ultimately struck," the official said.

Coccidiosis, Salmonella, and Newcastle are the common poultry diseases that curtail poultry production if they are not detected early. In Tanzania, these diseases are not detected early due to limited access to agricultural support services by poultry farmers. Deep learning techniques have the potential for early diagnosis of these poultry diseases. In this study, a deep Convolutional Neural Network (CNN) model was developed to diagnose poultry diseases by classifying healthy and unhealthy fecal images. Unhealthy fecal images may be symptomatic of Coccidiosis, Salmonella, and Newcastle diseases. We collected 1,255 laboratory-labeled fecal images and fecal samples used in Polymerase Chain Reaction diagnostics to annotate the laboratory-labeled fecal images. We took 6,812 poultry fecal photos using an Open Data Kit. Agricultural support experts annotated the farm-labeled fecal images. Then we used a baseline CNN model, VGG16, InceptionV3, MobileNetV2, and Xception models. We trained models using farm and laboratory-labeled fecal images and then fine-tuned them. The test set used farm-labeled images. The test accuracies results without fine-tuning were 83.06% for the baseline CNN, 85.85% for VGG16, 94.79% for InceptionV3, 87.46% for MobileNetV2, and 88.27% for Xception. Finetuning while freezing the batch normalization layer improved model accuracies, resulting in 95.01% for VGG16, 95.45% for InceptionV3, 98.02% for MobileNetV2, and 98.24% for Xception, with F1 scores for all...

A U.S. drone strike in Afghanistan this weekend killed Ayman al-Zawahri, who helped Osama bin Laden plot the Sept. 11, 2001, attacks on the United States and ensured al-Qaida survived and spread in the years after. President Joe Biden on Monday announced the killing of al-Zawahri, delivering a significant counterterrorism win just 11 months after American troops left the country. A look at the al-Qaida leader, who evaded U.S. capture for 21 years after the suicide airliner attacks that in many ways changed America and its relations with the rest of the world. Americans who lived through the 9/11 attacks may not remember al-Zawahri's name, but many know his face more than two decades on: a man in glasses, slightly smiling, invariably shown in photos by the side of bin Laden as the two arranged the strike on the United States. An Egyptian, al-Zawahri was born June 19, 1951, to a comfortable family in a leafy, drowsy Cairo suburb.

In 2002, when I profiled Ayman al-Zawahiri for The New Yorker, he was called "the man behind bin Laden." But since bin Laden was killed by American special forces in 2011, Zawahiri has been Al Qaeda's leader. Zawahiri and bin Laden were very different men, not friends but allies, using each other for the skills and resources they could each provide. Al Qaeda would not have survived without the dynamic they created together. Zawahiri, reportedly killed in Afghanistan by a U.S. drone strike over the weekend, was a doctor--a highly-educated professional who chose to devote himself to violent revolution.

President Joe Biden announced Monday that the United States had killed Al-Qaeda chief Ayman al-Zawahiri, one of the world's most wanted terrorists and suspected mastermind of the September 11, 2001 attacks. In a televised address, Biden said the strike in Kabul, Afghanistan had been carried out on Saturday. "I gave the final approval to go get him," he said, adding that there had been no civilian casualties. "Justice has been delivered and this terrorist leader is no more," Biden said. A senior administration official said Zawahiri had been killed on the balcony of a house in Kabul in a drone strike, and that there had been no US boots on the ground in Afghanistan.

In the open book question answering (OBQA) task, selecting the relevant passages and sentences from distracting information is crucial to reason the answer to a question. HotpotQA dataset is designed to teach and evaluate systems to do both passage ranking and sentence selection. Many existing frameworks use separate models to select relevant passages and sentences respectively. Such systems not only have high complexity in terms of the parameters of models but also fail to take the advantage of training these two tasks together since one task can be beneficial for the other one. In this work, we present a simple yet effective framework to address these limitations by jointly ranking passages and selecting sentences. Furthermore, we propose consistency and similarity constraints to promote the correlation and interaction between passage ranking and sentence selection.The experiments demonstrate that our framework can achieve competitive results with previous systems and outperform the baseline by 28% in Figure 1: An example from the HotpotQA dataset, terms of exact matching of relevant sentences where the question should be answered by combining on the HotpotQA dataset.

With recent improvements in natural language generation (NLG) models for various applications, it has become imperative to have the means to identify and evaluate whether NLG output is only sharing verifiable information about the external world. In this work, we present a new evaluation framework entitled Attributable to Identified Sources (AIS) for assessing the output of natural language generation models, when such output pertains to the external world. We first define AIS and introduce a two-stage annotation pipeline for allowing annotators to appropriately evaluate model output according to AIS guidelines. We empirically validate this approach on generation datasets spanning three tasks (two conversational QA datasets, a summarization dataset, and a table-to-text dataset) via human evaluation studies that suggest that AIS could serve as a common framework for measuring whether model-generated statements are supported by underlying sources. We release guidelines for the human evaluation studies.

Link prediction is an important task that has wide applications in various domains. However, the majority of existing link prediction approaches assume the given graph follows homophily assumption, and designs similarity-based heuristics or representation learning approaches to predict links. However, many real-world graphs are heterophilic graphs, where the homophily assumption does not hold, which challenges existing link prediction methods. Generally, in heterophilic graphs, there are many latent factors causing the link formation, and two linked nodes tend to be similar in one or two factors but might be dissimilar in other factors, leading to low overall similarity. Thus, one way is to learn disentangled representation for each node with each vector capturing the latent representation of a node on one factor, which paves a way to model the link formation in heterophilic graphs, resulting in better node representation learning and link prediction performance. However, the work on this is rather limited. Therefore, in this paper, we study a novel problem of exploring disentangled representation learning for link prediction on heterophilic graphs. We propose a novel framework DisenLink which can learn disentangled representations by modeling the link formation and perform factor-aware message-passing to facilitate link prediction. Extensive experiments on 13 real-world datasets demonstrate the effectiveness of DisenLink for link prediction on both heterophilic and hemophiliac graphs. Our codes are available at https://github.com/sjz5202/DisenLink

Nonnegative Tucker decomposition (NTD), a tensor decomposition model, has received increased interest in the recent years because of its ability to blindly extract meaningful patterns, in particular in Music Information Retrieval. Nevertheless, existing algorithms to compute NTD are mostly designed for the Euclidean loss. This work proposes a multiplicative updates algorithm to compute NTD with the beta-divergence loss, often considered a better loss for audio processing. We notably show how to implement efficiently the multiplicative rules using tensor algebra. Finally, we show on a music structure analysis task that unsupervised NTD fitted with beta-divergence loss outperforms earlier results obtained with the Euclidean loss.

NEURODATA is a global technology company dedicated to creating and scaling AI solutions by leveraging deep expertise and a common machine learning platform. Through meaningful engagement and collaboration, we partner with companies to build and operationalize impactful end-to-end AI solutions across a wide variety of industries and use cases. Our experience in computer vision, NLP, and recommendation engines in real world scenarios enables us to deliver solutions that integrate seamlessly with customer processes to solve the most complex business challenges. Our team consists of expert data scientists, software engineers, and AI business leaders in Tunisia and Montreal, Canada. As the Center of Excellence for AI embedded, we place the highest priority on the ethical adoption, development, and delivery of AI technologies and solutions, with the goal of better business outcomes that usher in a more resilient and inclusive world.