Sephus, applied science manager for Amazon Artificial Intelligence, focuses on fairness and the detection of biases in data and machine learning …

Artificial intelligence (AI) is one technological area specifically identified within the questions for public comment along with quantum computing, …

The big data about music history contains information about time and users' behavior. Researchers could predict the trend of popular songs accurately by analyzing this data. The traditional trend prediction models can better predict the short trend than the long trend. In this paper, we proposed the improved LSTM Rolling Prediction Algorithm (LSTM-RPA), which combines LSTM historical input with current prediction results as model input for next time prediction. Meanwhile, this algorithm converts the long trend prediction task into multiple short trend prediction tasks. The evaluation results show that the LSTM-RPA model increased F score by 13.03%, 16.74%, 11.91%, 18.52%, compared with LSTM, BiLSTM, GRU and RNN.

With the prevalence of deep learning based embedding approaches, recommender systems have become a proven and indispensable tool in various information filtering applications. However, many of them remain difficult to diagnose what aspects of the deep models' input drive the final ranking decision, thus, they cannot often be understood by human stakeholders. In this paper, we investigate the dilemma between recommendation and explainability, and show that by utilizing the contextual features (e.g., item reviews from users), we can design a series of explainable recommender systems without sacrificing their performance. In particular, we propose three types of explainable recommendation strategies with gradual change of model transparency: whitebox, graybox, and blackbox. Each strategy explains its ranking decisions via different mechanisms: attention weights, adversarial perturbations, and counterfactual perturbations. We apply these explainable models on five real-world data sets under the contextualized setting where users and items have explicit interactions. The empirical results show that our model achieves highly competitive ranking performance, and generates accurate and effective explanations in terms of numerous quantitative metrics and qualitative visualizations.

Computer Vision (CV) aims to create computational models that can mimic the human visual system. From an engineering point of view, CV aims to build autonomous systems which could perform some of the tasks that the human visual system is able to accomplish [1]. Urban scenarios reconstruction and understanding of it is an area of research with several applications nowadays: entertainment industry, computer gaming, movie making, digital mapping for mobile devices, digital mapping for car navigation, urban planning, driving. Understanding urban scenarios has become much more important with the evolution of Augmented Reality (AR). AR is successfully exploited in many domains nowadays, one of them being culture and tourism, an area in which the authors of this paper carried multiple research projects [2], [3], [4].

To steal the artifact, the three kill the lights to the ballroom and snatch the cross before it's sold at the auction. All goes according to plan -- until it doesn't. Trying to escape the guards, you scale red-tiled Italian roofs, a la "Assassins Creed." Amid all the scaling and jumping, Drake grabs a zipline back toward the ballroom, where Sully is ready with the getaway car. But the line breaks and Drake ends up swinging into an ornate glass window, barreling headfirst into a gunfight alongside Sam.

Your membership supports a team of global Quartz journalists reporting on the forces shaping our world. We make sense of accelerating change and help you get ahead of it with business news for the next era, not just the next hour. Goodbye paywall, hello access across platforms -- including on our iOS app -- to global business news that offers a fresh perspective on the financial forces changing the world. Get concise analysis, forecasts, profiles, and advice in your inbox throughout the week. Deep dives on the companies, people, and phenomena defining the global economy.

Adobe is one of those companies that I don't think we pay enough attention to -- it's been around since 1982, and the entire creative economy runs through its software. You don't just edit a photo, you Photoshop it. Premiere Pro and After Effects are industry-standard video production tools. Pro photographers all depend on Lightroom. We spend a lot of time on Decoder talking about the creator economy, but creators themselves spend all their time working in Adobe's tools. Adobe is in the middle of announcing new features for all those tools this week -- at its annual conference, Adobe Max. On this episode, I'm talking to Scott Belsky, chief product officer at Adobe, about the new features coming to Adobe's products, many of which focus on collaboration, and about creativity broadly -- who gets to be a creative, where they might work, and how they get paid. Scott is a big proponent of NFTs -- non-fungible tokens. You've probably heard about NFTs, but the quick version is that they allow people to buy and sell digital artwork and keep records of that ownership in a public blockchain. The idea is to create scarcity for digital goods, just like physical products -- to definitively say you own a digital piece of art, just like you own a physical piece of art. Of course, the internet is a giant copy machine, so it's a little more complicated than that -- but a lot of people, including Scott, think it's a revolution. In fact, Photoshop itself will be able to prepare an image to be an NFT very soon. I'm a little more skeptical -- so we got into it. Scott and I talk about all that. And we squeezed it into just about an hour. This transcript has been lightly edited for clarity. It's been a while since we've talked, I've always enjoyed our conversations. We have a lot to talk about. This episode of the podcast is coming out alongside Adobe Max, your big conference, and you're announcing a ton of new products there, including big features for Creative Cloud on the web. You're very bullish on NFTs, which I really want to talk to you about, and I have some big questions about the future of computing. I was looking at these topics and I was like, "Man, I need like two hours." But we're going to try to get it all in. Let's do it, a power hour. But I want to start with what I have come to think of as the Decoder questions; the basics of how Adobe as a company works. I think Adobe, as a company, we take for granted in the best way. The products are ubiquitous, they're famous, entire industries depend on them. But I feel like it's a company we don't know a lot about.

Technology is currently buzzing around the topic of artificial intelligence, and for a good reason. We have witnessed the transformation of several science fiction technologies in recent years. According to experts, AI can introduce new sources of growth by transforming the way people do their work across industries. An Accenture report states that artificial intelligence could boost labor productivity by 40% or more by 2035. Achieving this would double the economic growth in 12 developed nations that continue to attract professional talent. And ML, a subset of AI, is also pacing at the same level in terms of technology trends.

This paper aimed to explore the efficacy of machine learning (ML) approaches in predicting under-five undernutrition in Ethiopian administrative …