Fox News chief Washington correspondent Mike Emanuel reports on an Iranian warship intercepting American drones only to return them the following morning on'Special Report.' Iran has armed 51 cities and towns with a civil defense system aimed to respond to any foreign attack as tensions with the U.S. have mounted in recent weeks. The defenses will enable Iran's arms forces to "identify and monitor threats by using round-the-clock software according to the type of the threat and risk," Deputy Defense Minister General Mehdi Farahi said Saturday, according to a Reuters report. "These days, depending on the strength of countries, the form of battles has become more complicated," he added. Farahi did not name any specific countries Tehran could be targeted by but noted that conventional warfare has largely been replaced by cyber, biological and radioactive attack tactics.

This paper compares two deep reinforcement learning approaches for cyber security in software defined networking. Neural Episodic Control to Deep Q-Network has been implemented and compared with that of Double Deep Q-Networks. The two algorithms are implemented in a format similar to that of a zero-sum game. A two-tailed T-test analysis is done on the two game results containing the amount of turns taken for the defender to win. Another comparison is done on the game scores of the agents in the respective games. The analysis is done to determine which algorithm is the best in game performer and whether there is a significant difference between them, demonstrating if one would have greater preference over the other. It was found that there is no significant statistical difference between the two approaches.

We introduce a vision-language foundation model called VL-BEiT, which is a bidirectional multimodal Transformer learned by generative pretraining. Our minimalist solution conducts masked prediction on both monomodal and multimodal data with a shared Transformer. Specifically, we perform masked vision-language modeling on image-text pairs, masked language modeling on texts, and masked image modeling on images. VL-BEiT is learned from scratch with one unified pretraining task, one shared backbone, and one-stage training. Our method is conceptually simple and empirically effective. Experimental results show that VL-BEiT obtains strong results on various vision-language benchmarks, such as visual question answering, visual reasoning, and image-text retrieval. Moreover, our method learns transferable visual features, achieving competitive performance on image classification, and semantic segmentation.

Deep learning research has generated widespread interest leading to emergence of a large variety of technological innovations and applications. As significant proportion of deep learning research focuses on vision based applications, there exists a potential for using some of these techniques to enable low-power portable health-care diagnostic support solutions. In this paper, we propose an embedded-hardware-based implementation of microscopy diagnostic support system for PoC case study on: (a) Malaria in thick blood smears, (b) Tuberculosis in sputum samples, and (c) Intestinal parasite infection in stool samples. We use a Squeeze-Net based model to reduce the network size and computation time. We also utilize the Trained Quantization technique to further reduce memory footprint of the learned models. This enables microscopy-based detection of pathogens that classifies with laboratory expert level accuracy as a standalone embedded hardware platform. The proposed implementation is 6x more power-efficient compared to conventional CPU-based implementation and has an inference time of $\sim$ 3 ms/sample.

We report the results of DialogSum Challenge, the shared task on summarizing real-life scenario dialogues at INLG 2022. Four teams participate in this shared task and three submit their system reports, exploring different methods to improve the performance of dialogue summarization. Although there is a great improvement over the baseline models regarding automatic evaluation metrics, such as Rouge scores, we find that there is a salient gap between model generated outputs and human annotated summaries by human evaluation from multiple aspects. These findings demonstrate the difficulty of dialogue summarization and suggest that more fine-grained evaluatuion metrics are in need.

AlphaZero, Leela Chess Zero and Stockfish NNUE revolutionized Computer Chess. This book gives a complete introduction into the technical inner workings of such engines. The book is split into four main chapters -- excluding chapter 1 (introduction) and chapter 6 (conclusion): Chapter 2 introduces neural networks and covers all the basic building blocks that are used to build deep networks such as those used by AlphaZero. Contents include the perceptron, back-propagation and gradient descent, classification, regression, multilayer perceptron, vectorization techniques, convolutional networks, squeeze and excitation networks, fully connected networks, batch normalization and rectified linear units, residual layers, overfitting and underfitting. Chapter 3 introduces classical search techniques used for chess engines as well as those used by AlphaZero. Contents include minimax, alpha-beta search, and Monte Carlo tree search. Chapter 4 shows how modern chess engines are designed. Aside from the ground-breaking AlphaGo, AlphaGo Zero and AlphaZero we cover Leela Chess Zero, Fat Fritz, Fat Fritz 2 and Efficiently Updatable Neural Networks (NNUE) as well as Maia. Chapter 5 is about implementing a miniaturized AlphaZero. Hexapawn, a minimalistic version of chess, is used as an example for that. Hexapawn is solved by minimax search and training positions for supervised learning are generated. Then as a comparison, an AlphaZero-like training loop is implemented where training is done via self-play combined with reinforcement learning. Finally, AlphaZero-like training and supervised training are compared.

In that case, the Navy said it spotted an Iranian Islamic Revolutionary Guard Corps naval support ship towing a Saildrone Explorer. The American seamen told the Iranians that the drone was U.S. government property and asked for it back. With a U.S. Fifth Fleet MH-60S Sea Hawk helicopter hovering above, the Iranians disconnected the towing line they had attached to that drone and eventually departed the area, according to a U.S. Navy release at the time. The Navy resumed operations "without incident," the release said. The United States and Iran often tangle in the Persian Gulf -- which the United States calls the Arabian Gulf -- and in the Red Sea and the Arabian Sea.

Iran's navy has released two American surface drones hours after seizing them in the Red Sea, accusing the unmanned vessels of jeopardising maritime safety, Iranian state television reports, in the second such incident this week. "The [Iranian navy] frigate Jamaran seized the two vessels on Thursday to prevent any possible accident after issuing warnings to the US fleet. After international shipping lanes were secured, the two vessels were released in a safe area," the state TV reported on Friday. Footage appeared to show more than a dozen Iranian navy personnel pushing two drones into the sea from the deck of their vessel – the latest maritime incident involving the United States Navy's new drone fleet in the Middle East as negotiations over Tehran's nuclear deal with the world powers hang in the balance. The state TV said an Iranian naval flotilla found "several unmanned spying vessels abandoned in the international maritime routes" and "after warning an American destroyer twice, seized the two drone vessels to prevent possible accidents".

In the next few sections I'll attempt to fit GPT into some established categories, hopefully to reveal something about the shape of the peg through contrast, beginning with the main antagonist of the alignment problem as written so far, the agent. Alignment theory has been largely pushed by considerations of agentic AGIs.

Minister of Communications and Digital Technologies Khumbudzo Ntshavheni said the AI Institute is being established in partnership with institutions of higher learning, in particular the Johannesburg Business School of the University of Johannesburg and the Tshwane University of Technology, which are co-founder institutions together with the Department of Communications and Digital Technologies. "It is essential that we invest significantly to provide our youth with access to modern training, skill sets and formal education. To achieve this, our Department of Basic Education has introduced robotics and coding as school subjects in primary and high schools. "At present, learners in over a 1,000 schools are designing and producing robots both for gaming and to complete tasks the learners find tedious for human completion. "Next year, learners in these and additional schools that will join this category will compete in a National Robotics Development Challenge," the Minister said on Thursday during the G20 Digital Economy Ministers Meeting in Bali, Indonesia.