We introduce the task of acoustic question answering (AQA) in the area of acoustic reasoning. In this task an agent learns to answer questions on the basis of acoustic context. In order to promote research in this area, we propose a data generation paradigm adapted from CLEVR (Johnson et al. 2017). We generate acoustic scenes by leveraging a bank elementary sounds. We also provide a number of functional programs that can be used to compose questions and answers that exploit the relationships between the attributes of the elementary sounds in each scene. We provide AQA datasets of various sizes as well as the data generation code. As a preliminary experiment to validate our data, we report the accuracy of current state of the art visual question answering models when they are applied to the AQA task without modifications. Although there is a plethora of question answering tasks based on text, image or video data, to our knowledge, we are the first to propose answering questions directly on audio streams. We hope this contribution will facilitate the development of research in the area.

Convolutional networks were initially developed for supervised learning. They are used in deep learning to classify two-dimensional spatial information such as hand writing samples and photographs [16]. In the one dimensional setting, they have been applied to temporal data such as audio recordings of speech and music, and writing encoded at either the character level or the word level. In the three dimensional setting, applications have included medical scans, object detection for self driving cars, and object recognition from RGB-D photos. Videos, with their two spatial dimensions and one time dimension can also be seen as 2 1 3 dimensional objects for purposes of applying convolutional networks [29]. The movement of 3D objects happens in 3 1 4 dimensional space-time, but 4D ConvNets are relatively unexplored.

Recommender systems are growing progressively more popular in online retail because of their ability to offer personalized experiences to unique users. Mean Average Precision at K (MAP@K) is typically the metric of choice for evaluating the performance of a recommender systems. However, the use of additional diagnostic metrics and visualizations can offer deeper and sometimes surprising insights into a model's performance. This article explores Mean Average Recall at K (MAR@K), Coverage, Personalization, and Intra-list Similarity, and uses these metrics to compare three simple recommender systems. If you would like to use any of the metrics or plots discussed in this article, I have made them all available in a python library recmetrics.

A robot shall not harm a human nor allow a human to become harmed through inaction. A robot shall obey a human so long as the orders do not interfere with the First Law. A robot shall protect itself so long as it does not interfere with the two previous laws. Those principles had a profound impact not just on science fiction but the world of artificial intelligence. A generation of scientists tried to instill his principles in their creations.

AP and ICIJ used the FDA's Manufacturer and User Facility Device Experience database, or MAUDE, to analyze device problems, going back more than three decades. They eliminated reports that stemmed from academic literature reviews or studies, and largely focused on reports from 2008 through 2017. For some devices, they also analyzed the most-recent data available for the first half of 2018. To analyze the MAUDE data, the partners standardized as much as possible the names of device manufacturers - correcting misspellings, fixing irregularities and tracing back subsidiaries to their parent companies. Cases were tracked by the date they were reported to the U.S. health agency.

With the right combination of resources and perspectives, there are few areas that artificial intelligence (AI) cannot enter, and even thrive within. The technology is behind the creation of sophisticated works of art, and even a pretty decent black metal album. Now, the stakes are even higher, with luxury carmaker Lexus unveiling a one-minute advertisement with a script created entirely by AI for the release of its ES executive sedan. And as a symbol of the growing influence of AI, Academy Award winner Kevin McDonald agreed to lend his directing talents to the project. In order to ensure that a completely original story was produced, the AI underwent a training period that involved car and luxury advertisements from a 15-year period, all of them past winners in the Cannes Lion International Festival of Creativity.

What happens when we begin to think of all information as data that can be explored to yield new insights into our world? What would it look like to take nearly a decade of CNN, Fox News, and MSNBC television broadcasts and two years of BBC News broadcasts and run them through sophisticated natural language processing algorithms to identify every mention of a location on earth in their coverage and then create a series of maps that visualize the places we hear about when we turn to the news? What would those maps look like and what might they tell us about what we see when we turn on our televisions each day? Half a decade ago I began working with the Internet Archive's incredible Television News Archive to explore how powerful computer algorithms could allow us to "see" the news in entirely new ways. From simple longitudinal keyword searches to mass emotion mining to geographic mapping to the most powerful deep learning algorithms watching political ads, television has an incredible amount to teach us as we explore it through the modalities and lenses of massive data mining.

Choose "Yes, I have!" or "Never heard of it.". You'd think that having a sense of taste and smell would be essential in creating the perfect beer, and therefore would be a job reserved for humans only. IntelligentX Brewing Co., is a London-based company which introduced the first beer brewed with the help of artificial intelligence. Their AI, in the form of a chatbot, takes feedback from customers. It asks questions about flavor preferences, often answered with a simple'yes' or'no' or with a 1-10 rating system.

From birds taking flight to sweeping waterfalls - these amazing drone images showcase spectacular scenery from perspectives that have never been seen before. The beguiling images appeared on photo-sharing site Dronestagram which is dedicated to drone photography.

Recent character and phoneme-based parametric TTS systems using deep learning have shown strong performance in natural speech generation. However, the choice between character or phoneme input can create serious limitations for practical deployment, as direct control of pronunciation is crucial in certain cases. We demonstrate a simple method for combining multiple types of linguistic information in a single encoder, named representation mixing, enabling flexible choice between character, phoneme, or mixed representations during inference. Experiments and user studies on a public audiobook corpus show the efficacy of our approach.