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.

Robot design optimization, imitation learning and system identification share a common problem which requires optimization over robot or task parameters at the same time as optimizing the robot motion. To solve these problems, we can use differentiable optimal control for which the gradients of the robot's motion with respect to the parameters are required. We propose a method to efficiently compute these gradients analytically via the differential dynamic programming (DDP) algorithm using sensitivity analysis (SA). We show that we must include second-order dynamics terms when computing the gradients. However, we do not need to include them when computing the motion. We validate our approach on the pendulum and double pendulum systems. Furthermore, we compare against using the derivatives of the iterative linear quadratic regulator (iLQR), which ignores these second-order terms everywhere, on a co-design task for the Kinova arm, where we optimize the link lengths of the robot for a target reaching task. We show that optimizing using iLQR gradients diverges as ignoring the second-order dynamics affects the computation of the derivatives. Instead, optimizing using DDP gradients converges to the same optimum for a range of initial designs allowing our formulation to scale to complex systems.

Graph Neural Networks achieve state-of-the-art performance on a plethora of graph classification tasks, especially due to pooling operators, which aggregate learned node embeddings hierarchically into a final graph representation. However, they are not only questioned by recent work showing on par performance with random pooling, but also ignore completely higher-order connectivity patterns. To tackle this issue, we propose HoscPool, a clustering-based graph pooling operator that captures higher-order information hierarchically, leading to richer graph representations. In fact, we learn a probabilistic cluster assignment matrix end-to-end by minimising relaxed formulations of motif spectral clustering in our objective function, and we then extend it to a pooling operator. We evaluate HoscPool on graph classification tasks and its clustering component on graphs with ground-truth community structure, achieving best performance. Lastly, we provide a deep empirical analysis of pooling operators' inner functioning.

In this work, we explore recurrent neural network architectures for tuberculosis (TB) cough classification. In contrast to previous unsuccessful attempts to implement deep architectures in this domain, we show that a basic bidirectional long short-term memory network (BiLSTM) can achieve improved performance. In addition, we show that by performing greedy feature selection in conjunction with a newly-proposed attention-based architecture that learns patient invariant features, substantially better generalisation can be achieved compared to a baseline and other considered architectures. Furthermore, this attention mechanism allows an inspection of the temporal regions of the audio signal considered to be important for classification to be performed. Finally, we develop a neural style transfer technique to infer idealised inputs which can subsequently be analysed. We find distinct differences between the idealised power spectra of TB and non-TB coughs, which provide clues about the origin of the features in the audio signal.

An ensemble of classifiers combines several single classifiers to deliver a final prediction or classification decision. An increasingly provoking question is whether such systems can outperform the single best classifier. If so, what form of an ensemble of classifiers (also known as multiple classifier learning systems or multiple classifiers) yields the most significant benefits in the size or diversity of the ensemble itself? Given that the tests used to detect autism traits are time-consuming and costly, developing a system that will provide the best outcome and measurement of autism spectrum disorder (ASD) has never been critical. In this paper, several single and later multiple classifiers learning systems are evaluated in terms of their ability to predict and identify factors that influence or contribute to ASD for early screening purposes. A dataset of behavioural data and robot-enhanced therapy of 3,000 sessions and 300 hours, recorded from 61 children are utilised for this task. Simulation results show the superior predictive performance of multiple classifier learning systems (especially those with three classifiers per ensemble) compared to individual classifiers, with bagging and boosting achieving excellent results. It also appears that social communication gestures remain the critical contributing factor to the ASD problem among children.