Recent years have seen significant advances in end-to-end (E2E) spoken language understanding (SLU) systems, which directly predict intents and slots from spoken audio. While dialogue history has been exploited to improve conventional text-based natural language understanding systems, current E2E SLU approaches have not yet incorporated such critical contextual signals in multi-turn and task-oriented dialogues. In this work, we propose a contextual E2E SLU model architecture that uses a multi-head attention mechanism over encoded previous utterances and dialogue acts (actions taken by the voice assistant) of a multi-turn dialogue. We detail alternative methods to integrate these contexts into the state-ofthe-art recurrent and transformer-based models. When applied to a large de-identified dataset of utterances collected by a voice assistant, our method reduces average word and semantic error rates by 10.8% and 12.6%, respectively. We also present results on a publicly available dataset and show that our method significantly improves performance over a noncontextual baseline

When you're dealing with marketing problems like customer churn (when a customer stops using a company's product over a certain period of time) prediction, the raw dataset is often imbalanced, meaning that the classes are inherently not balanced. Basically, what this means is the percentage of your customers who churn might be a lot lower than those who don't. In this example, the binary classification problem might have an 80–20 split, with only 20% of customers discontinuing their engagement with the company and 80% continuing to make a purchase. The problem is, that 20% could be VERY important to the business's bottom line. Think about it -- a gifting company has 100,000 customers with an average value of $50 per person.

The training and test data for deep-neural-network-based classifiers are usually assumed to be sampled from the same distribution. When part of the test samples are drawn from a distribution that is sufficiently far away from that of the training samples (a.k.a. out-of-distribution (OOD) samples), the trained neural network has a tendency to make high confidence predictions for these OOD samples. Detection of the OOD samples is critical when training a neural network used for image classification, object detection, etc. It can enhance the classifier's robustness to irrelevant inputs, and improve the system resilience and security under different forms of attacks. Detection of OOD samples has three main challenges: (i) the proposed OOD detection method should be compatible with various architectures of classifiers (e.g., DenseNet, ResNet), without significantly increasing the model complexity and requirements on computational resources; (ii) the OOD samples may come from multiple distributions, whose class labels are commonly unavailable; (iii) a score function needs to be defined to effectively separate OOD samples from in-distribution (InD) samples. To overcome these challenges, we propose a Wasserstein-based out-of-distribution detection (WOOD) method. The basic idea is to define a Wasserstein-distance-based score that evaluates the dissimilarity between a test sample and the distribution of InD samples. An optimization problem is then formulated and solved based on the proposed score function. The statistical learning bound of the proposed method is investigated to guarantee that the loss value achieved by the empirical optimizer approximates the global optimum. The comparison study results demonstrate that the proposed WOOD consistently outperforms other existing OOD detection methods.

To combat ethical risk proactively without sacrificing model performance, we must first define'fairness'. A model is considered'fair' if it gives similar predictions to similar groups or individuals. In more detail, a model is'fair' if for both groups of the positive outcome, the predictor has equal true positive rates and equal false positive rates for the negative outcomes. Next, we can break up our bias detection and mitigation techniques into phases -- the same phases that govern the development of an AI model: Data understanding & preparation; model development & post-processing; and model evaluation & auditing.

Where you born, raised, and in what kind of background? Nitesh Chawla: I'm from New Delhi although I was born in Calcutta. I did my schooling from Delhi Public School. Then I did my engineering from Pune. Then I came to the United States in 1993 right after finishing my undergrad.

We introduce powerful ideas from Hyperdimensional Computing into the challenging field of Out-of-Distribution (OOD) detection. In contrast to most existing work that performs OOD detection based on only a single layer of a neural network, we use similarity-preserving semi-orthogonal projection matrices to project the feature maps from multiple layers into a common vector space. By repeatedly applying the bundling operation $\oplus$, we create expressive class-specific descriptor vectors for all in-distribution classes. At test time, a simple and efficient cosine similarity calculation between descriptor vectors consistently identifies OOD samples with better performance than the current state-of-the-art. We show that the hyperdimensional fusion of multiple network layers is critical to achieve best general performance.

Facebook has worked for years to revamp its handling of political ads -- but researchers who conducted a comprehensive audit of millions of ads say the social media company's efforts have had uneven results. The problems, they say, include overcounting political ads in the U.S. -- and undercounting them in other countries. And despite Facebook's ban on political ads around the time of last year's U.S. elections, the platform allowed more than 70,000 political ads to run anyway, according to the research team that is based at the NYU Cybersecurity for Democracy and at the Belgian university KU Leuven. Their research study was released early Thursday. They also plan to present their findings at a security conference next August.

For children with autism spectrum disorder (ASD), receiving an early diagnosis can make a huge difference in improving behavior, skills and language development. There is no lab test and no single identified genetic cause--instead, clinicians look at the child's behavior and conduct structured interviews with the child's caregivers based on questionnaires. But these questionnaires are extensive, complicated and not foolproof. "In trying to discern and stratify a complex condition such as autism spectrum disorder, knowing what questions to ask and in what order becomes challenging," said USC University Professor Shrikanth Narayanan, Niki and Max Nikias Chair in Engineering and professor of electrical and computer engineering, computer science, linguistics, psychology, pediatrics and otolaryngology. "As such, this system is difficult to administer and can produce false positives, or confound ASD as other comorbid conditions, such as attention deficit hyperactivity disorder (ADHD)."

Hyperparameter optimization (HPO) is a necessary step to ensure the best possible performance of Machine Learning (ML) algorithms. Several methods have been developed to perform HPO; most of these are focused on optimizing one performance measure (usually an error-based measure), and the literature on such single-objective HPO problems is vast. Recently, though, algorithms have appeared which focus on optimizing multiple conflicting objectives simultaneously. This article presents a systematic survey of the literature published between 2014 and 2020 on multi-objective HPO algorithms, distinguishing between metaheuristic-based algorithms, metamodel-based algorithms, and approaches using a mixture of both. We also discuss the quality metrics used to compare multi-objective HPO procedures and present future research directions.

The digital transformation faces tremendous security challenges. In particular, the growing number of cyber-attacks targeting Internet of Things (IoT) systems restates the need for a reliable detection of malicious network activity. This paper presents a comparative analysis of supervised, unsupervised and reinforcement learning techniques on nine malware captures of the IoT-23 dataset, considering both binary and multi-class classification scenarios. The developed models consisted of Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), Isolation Forest (iForest), Local Outlier Factor (LOF) and a Deep Reinforcement Learning (DRL) model based on a Double Deep Q-Network (DDQN), adapted to the intrusion detection context. The most reliable performance was achieved by LightGBM. Nonetheless, iForest displayed good anomaly detection results and the DRL model demonstrated the possible benefits of employing this methodology to continuously improve the detection. Overall, the obtained results indicate that the analyzed techniques are well suited for IoT intrusion detection.