In this research work, we have demonstrated the application of Mask-RCNN (Regional Convolutional Neural Network), a deep-learning algorithm for computer vision and specifically object detection, to semiconductor defect inspection domain. Stochastic defect detection and classification during semiconductor manufacturing has grown to be a challenging task as we continuously shrink circuit pattern dimensions (e.g., for pitches less than 32 nm). Defect inspection and analysis by state-of-the-art optical and e-beam inspection tools is generally driven by some rule-based techniques, which in turn often causes to misclassification and thereby necessitating human expert intervention. In this work, we have revisited and extended our previous deep learning-based defect classification and detection method towards improved defect instance segmentation in SEM images with precise extent of defect as well as generating a mask for each defect category/instance. This also enables to extract and calibrate each segmented mask and quantify the pixels that make up each mask, which in turn enables us to count each categorical defect instances as well as to calculate the surface area in terms of pixels. We are aiming at detecting and segmenting different types of inter-class stochastic defect patterns such as bridge, break, and line collapse as well as to differentiate accurately between intra-class multi-categorical defect bridge scenarios (as thin/single/multi-line/horizontal/non-horizontal) for aggressive pitches as well as thin resists (High NA applications). Our proposed approach demonstrates its effectiveness both quantitatively and qualitatively.

Joint entity and relation extraction has been a core task in the field of information extraction. Recent approaches usually consider the extraction of relational triples from a stereoscopic perspective, either learning a relation-specific tagger or separate classifiers for each relation type. However, they still suffer from error propagation, relation redundancy and lack of high-level connections between triples. To address these issues, we propose a novel query-based approach to construct instance-level representations for relational triples. By metric-based comparison between query embeddings and token embeddings, we can extract all types of triples in one step, thus eliminating the error propagation problem. In addition, we learn the instance-level representation of relational triples via contrastive learning. In this way, relational triples can not only enclose rich class-level semantics but also access to high-order global connections. Experimental results show that our proposed method achieves the state of the art on five widely used benchmarks.

Despite recent progress in open-domain dialogue evaluation, how to develop automatic metrics remains an open problem. We explore the potential of dialogue evaluation featuring dialog act information, which was hardly explicitly modeled in previous methods. However, defined at the utterance level in general, dialog act is of coarse granularity, as an utterance can contain multiple segments possessing different functions. Hence, we propose segment act, an extension of dialog act from utterance level to segment level, and crowdsource a large-scale dataset for it. To utilize segment act flows, sequences of segment acts, for evaluation, we develop the first consensus-based dialogue evaluation framework, FlowEval. This framework provides a reference-free approach for dialog evaluation by finding pseudo-references. Extensive experiments against strong baselines on three benchmark datasets demonstrate the effectiveness and other desirable characteristics of our FlowEval, pointing out a potential path for better dialogue evaluation.

Our engineering team is split into organisations which we call Fleets. Each Fleet focuses on a core customer journey (onboarding, security, payments, support, new business, growth, and marketing, etc.). Each of these fleets contains multiple smaller teams called Pods, each of which focuses on a specific aspect of the product. Pods will include a product owner, product designer, back-end engineers, Android, iOS, and Web developers, who each bring a unique perspective to the problem you are all contributing towards. Luno offers a "Remote but Reachable" working approach.

For the last several years, Google has been using artificial intelligence to develop a system that can predict floods. It has also been working on wildfire tracking tools. Ahead of the COP27 climate conference taking place next week, the company announced that it is expanding those tools. First, Google says it will offer flood forecasts for river basins in another 18 countries. Those are Brazil, Colombia, Sri Lanka, Burkina Faso, Cameroon, Chad, Democratic Republic of Congo, Ivory Coast, Ghana, Guinea, Malawi, Nigeria, Sierra Leone, Angola, South Sudan, Namibia, Liberia and South Africa. The company previously offered flood warnings to users in India and Bangaldesh with alerts on Android devices and phones that have the Google Search app installed.

Artificial intelligence has found disparities in the amount of airtime women and men were given on CNN, FOX News and MSNBC - females had a 10 percent less chance of speaking during political discussions because male speakers constantly interrupted them. The discovery was made by researchers at Rochester Institute of Technology who analyzed 625,409 dialogues hosted on the three news cable networks from January 2000 through July 2021. The technology revealed women received an average of 72.8 words per chance to speak compared to 81.4 for male speakers and women were interrupted 39.4 percent of the time during discussions - this is compared to the 35.9 percent of the time for men. The team believes their AI could be used during talk shows, interviews and political debates to identify a serial interrupter in real-time, but the study also reinforces previous research that found men interrupt women more to show their dominance. AI analyzed thousands of dialogues from news segments on the three networks and found woman are given a 10 percent less chance at speaking because men interrupt them.

Fox News national security correspondent Jennifer Griffin provides insight on responding to drone attacks in Ukraine on "America Reports." The Paris-based dissident organization National Council of Resistance of Iran (NCRI) accused the Iranian regime of furnishing Russian strongman Vladimir Putin's army with more than 3,500 drones for his scorched-earth war against Ukraine. According to reports from the social network of the People's Mojahedin Organization of Iran (PMOI/MEK) inside the Islamic Republic, "Iran's UAV [unmanned aerial vehicle] sale contract to Russia includes various offensive drones, including Shahed-129, Mohajer-6 and suicide drones Shahed-136 and Shahed-131." MEK is part of the National Council of Resistance of Iran umbrella organization. The NCRI dossier states, "Tehran has sold more than 3,500 UAVs to Russia. Most of these were made at the factories of the Ministry of Defense, with others produced by the factories of the Iranian Aviation and Space Industries Association (IASIA)."

Evaluation metrics that are not robust to dialect variation make it impossible to tell how well systems perform for many groups of users, and can even penalize systems for producing text in lower-resource dialects. However, currently, there exists no way to quantify how metrics respond to change in the dialect of a generated utterance. We thus formalize dialect robustness and dialect awareness as goals for NLG evaluation metrics. We introduce a suite of methods and corresponding statistical tests one can use to assess metrics in light of the two goals. Applying the suite to current state-of-the-art metrics, we demonstrate that they are not dialect-robust and that semantic perturbations frequently lead to smaller decreases in a metric than the introduction of dialect features. As a first step to overcome this limitation, we propose a training schema, NANO, which introduces regional and language information to the pretraining process of a metric. We demonstrate that NANO provides a size-efficient way for models to improve the dialect robustness while simultaneously improving their performance on the standard metric benchmark.

Image analysis and machine learning algorithms operating on multi-gigapixel whole-slide images (WSIs) often process a large number of tiles (sub-images) and require aggregating predictions from the tiles in order to predict WSI-level labels. In this paper, we present a review of existing literature on various types of aggregation methods with a view to help guide future research in the area of computational pathology (CPath). We propose a general CPath workflow with three pathways that consider multiple levels and types of data and the nature of computation to analyse WSIs for predictive modelling. We categorize aggregation methods according to the context and representation of the data, features of computational modules and CPath use cases. We compare and contrast different methods based on the principle of multiple instance learning, perhaps the most commonly used aggregation method, covering a wide range of CPath literature. To provide a fair comparison, we consider a specific WSI-level prediction task and compare various aggregation methods for that task. Finally, we conclude with a list of objectives and desirable attributes of aggregation methods in general, pros and cons of the various approaches, some recommendations and possible future directions.

Environmental perception obtained via object detectors have no predictable safety layer encoded into their model schema, which creates the question of trustworthiness about the system's prediction. As can be seen from recent adversarial attacks, most of the current object detection networks are vulnerable to input tampering, which in the real world could compromise the safety of autonomous vehicles. The problem would be amplified even more when uncertainty errors could not propagate into the submodules, if these are not a part of the end-to-end system design. To address these concerns, a parallel module which verifies the predictions of the object proposals coming out of Deep Neural Networks are required. This work aims to verify 3D object proposals from MonoRUn model by proposing a plausibility framework that leverages cross sensor streams to reduce false positives. The verification metric being proposed uses prior knowledge in the form of four different energy functions, each utilizing a certain prior to output an energy value leading to a plausibility justification for the hypothesis under consideration. We also employ a novel two-step schema to improve the optimization of the composite energy function representing the energy model.