This article develops a Bayesian optimization (BO) method which acts directly over raw strings, proposing the first uses of string kernels and genetic algorithms within BO loops. Recent applications of BO over strings have been hindered by the need to map inputs into a smooth and unconstrained latent space. Learning this projection is computationally and data-intensive. Our approach instead builds a powerful Gaussian process surrogate model based on string kernels, naturally supporting variable length inputs, and performs efficient acquisition function maximization for spaces with syntactical constraints. Experiments demonstrate considerably improved optimization over existing approaches across a broad range of constraints, including the popular setting where syntax is governed by a context-free grammar.

In a move to expand its business into the logistics and delivery segment, ride-hailing startup Via today announced that it acquired Fleetonomy for an undisclosed sum. Via, which says it plans to apply Fleetonomy's expertise in demand prediction and fleet utilization to support fully integrated, digitally powered logistics solutions, says the pandemic has highlighted the growing need for essential services and goods delivery. Tel Aviv-based Fleetonomy, which was founded in 2017 by CEO Israel Duanis and CTO Lior Gerenstein, taps AI to analyze data and deliver insights with the goal of maximizing inventory and promoting proactive maintenance. The company provides white label ride-sharing and on-demand car subscription services that can accommodate semiautonomous and autonomous fleets. With Fleetonomy's cloud-based suite of tools, managers can simulate services before deploying cars on the road, adjusting for factors such as fleet size, parking, charging locations, demand, and more.

Amazon wants to make it safer and easier to use your phone while you're in the car. The feature turns your phone into a "driver-friendly" display with large touch targets and easy-to-read visuals. Auto Mode keeps things simple with four screens: Home, Navigation, Communicate and Play. The home screen includes shortcuts to pause or play your media source, navigate to home or work and make a call. The Navigation screen lets you create shortcuts for favorite locations, or if you ask Alexa to find someplace new, Auto Mode will display a simplified results list with only the most relevant info.

Do you believe that artificial intelligence (AI) is powerful and smart enough to take over the majority of jobs in the future? Should people start rethinking their career choices and choose jobs that are the least likely to become obsolete thanks to automation? According to Sinovations Ventures' Dr. Kai-Fu Lee, predicting the future of tech in China, robots are likely to replace 50 percent of all jobs in the next 10 years. The influential technologist has 50 million followers on Chinese social networks. He recently told CNBC that AI is the wave of the future, calling it the "singular thing that will be larger than all of human tech revolutions added together, including electricity, [the] industrial revolution, internet, mobile internet -- because AI is pervasive."

The videos i this article will blow your mind... and they are already out of date. Soul Machines is on the cutting edge of building commercial AI avatars that can appear on a computer screen, and even in 3D, to simulate face-to-face engagement. The face in the main image of this article is one of their 3D avatars and they are already being deployed in banks and energy companies to inform and serve customers. With names such as Jamie (ANZ Bank), Will (Vector Energy), Ava (Autodesk), and Sarah (Daimler Mercedes Benz), they are connecting with customers, replicating human emotion, providing the right answers and asking insightful questions. Many call centre workers in affluent countries have been'off-shored' to lower cost countries, and now those roles are set to be outsourced to AI bots.

Cross-validation (CV) is a technique used to estimate generalization error for prediction models. For pipeline modeling algorithms (i.e. modeling procedures with multiple steps), it has been recommended the entire sequence of steps be carried out during each replicate of CV to mimic the application of the entire pipeline to an external testing set. While theoretically sound, following this recommendation can lead to high computational costs when a pipeline modeling algorithm includes computationally expensive operations, e.g. imputation of missing values. There is a general belief that unsupervised variable selection (i.e. ignoring the outcome) can be applied before conducting CV without incurring bias, but there is less consensus for unsupervised imputation of missing values. We empirically assessed whether conducting unsupervised imputation prior to CV would result in biased estimates of generalization error or result in poorly selected tuning parameters and thus degrade the external performance of downstream models. Results show that despite optimistic bias, the reduced variance of imputation before CV compared to imputation during each replicate of CV leads to a lower overall root mean squared error for estimation of the true external R-squared and the performance of models tuned using CV with imputation before versus during each replication is minimally different. In conclusion, unsupervised imputation before CV appears valid in certain settings and may be a helpful strategy that enables analysts to use more flexible imputation techniques without incurring high computational costs.

Background: Catastrophic forgetting is the notorious vulnerability of neural networks to the changes in the data distribution during learning. This phenomenon has long been considered a major obstacle for using learning agents in realistic continual learning settings. A large body of continual learning research assumes that task boundaries are known during training. However, only a few works consider scenarios in which task boundaries are unknown or not well defined -- task agnostic scenarios. The optimal Bayesian solution for this requires an intractable online Bayes update to the weights posterior. Contributions: We aim to approximate the online Bayes update as accurately as possible. To do so, we derive novel fixed-point equations for the online variational Bayes optimization problem, for multivariate Gaussian parametric distributions. By iterating the posterior through these fixed-point equations, we obtain an algorithm (FOO-VB) for continual learning which can handle non-stationary data distribution using a fixed architecture and without using external memory (i.e. without access to previous data). We demonstrate that our method (FOO-VB) outperforms existing methods in task agnostic scenarios. FOO-VB Pytorch implementation will be available online.

Recent years have seen important advances in the quality of state-of-the-art models, but this has come at the expense of models becoming less interpretable. This survey presents an overview of the current state of Explainable AI (XAI), considered within the domain of Natural Language Processing (NLP). We discuss the main categorization of explanations, as well as the various ways explanations can be arrived at and visualized. We detail the operations and explainability techniques currently available for generating explanations for NLP model predictions, to serve as a resource for model developers in the community. Finally, we point out the current gaps and encourage directions for future work in this important research area.

Textbook Question Answering is a complex task in the intersection of Machine Comprehension and Visual Question Answering that requires reasoning with multimodal information from text and diagrams. For the first time, this paper taps on the potential of transformer language models and bottom-up and top-down attention to tackle the language and visual understanding challenges this task entails. Rather than training a language-visual transformer from scratch we rely on pre-trained transformers, fine-tuning and ensembling. We add bottom-up and top-down attention to identify regions of interest corresponding to diagram constituents and their relationships, improving the selection of relevant visual information for each question and answer options. Our system ISAAQ reports unprecedented success in all TQA question types, with accuracies of 81.36%, 71.11% and 55.12% on true/false, text-only and diagram multiple choice questions. ISAAQ also demonstrates its broad applicability, obtaining state-of-the-art results in other demanding datasets.

White supremacists embrace a radical ideology that considers white people superior to people of other races. The critical influence of these groups is no longer limited to social media; they also have a significant effect on society in many ways by promoting racial hatred and violence. White supremacist hate speech is one of the most recently observed harmful content on social media.Traditional channels of reporting hate speech have proved inadequate due to the tremendous explosion of information, and therefore, it is necessary to find an automatic way to detect such speech in a timely manner. This research investigates the viability of automatically detecting white supremacist hate speech on Twitter by using deep learning and natural language processing techniques. Through our experiments, we used two approaches, the first approach is by using domain-specific embeddings which are extracted from white supremacist corpus in order to catch the meaning of this white supremacist slang with bidirectional Long Short-Term Memory (LSTM) deep learning model, this approach reached a 0.74890 F1-score. The second approach is by using the one of the most recent language model which is BERT, BERT model provides the state of the art of most NLP tasks. It reached to a 0.79605 F1-score. Both approaches are tested on a balanced dataset given that our experiments were based on textual data only. The dataset was combined from dataset created from Twitter and a Stormfront dataset compiled from that white supremacist forum.