In sparse recommender settings, users' context and item attributes play a crucial role in deciding which items to recommend next. Despite that, recent works in sequential and time-aware recommendations usually either ignore both aspects or only consider one of them, limiting their predictive performance. In this paper, we address these limitations by proposing a context and attribute-aware recommender model (CARCA) that can capture the dynamic nature of the user profiles in terms of contextual features and item attributes via dedicated multi-head self-attention blocks that extract profile-level features and predicting item scores. Also, unlike many of the current state-of-the-art sequential item recommendation approaches that use a simple dot-product between the most recent item's latent features and the target items embeddings for scoring, CARCA uses cross-attention between all profile items and the target items to predict their final scores. This cross-attention allows CARCA to harness the correlation between old and recent items in the user profile and their influence on deciding which item to recommend next. Experiments on four real-world recommender system datasets show that the proposed model significantly outperforms all state-of-the-art models in the task of item recommendation and achieving improvements of up to 53% in Normalized Discounted Cumulative Gain (NDCG) and Hit-Ratio. Results also show that CARCA outperformed several state-of-the-art dedicated image-based recommender systems by merely utilizing image attributes extracted from a pre-trained ResNet50 in a black-box fashion.

The ideal smart home seamlessly anticipates your needs and instantly responds to commands. You shouldn't have to open a specific app for each appliance or remember the precise voice command and voice assistant combination that starts the latest episode of your favorite podcast on the nearest speaker. Competing smart home standards make operating your devices needlessly complicated. Tech giants try to straddle standards by offering their voice assistants as a controlling layer on top, but Alexa can't talk to Google Assistant or Siri or control Google or Apple devices, and vice versa. And so far, no single ecosystem has created all the best devices.

A new wave of change in how consumers interact with services is on the horizon, driven by the growing demand for rapid responses from customers. According to Okwechime, AI-powered Chatbots leverage Natural Language Processing to understand conversations and their contexts to such an advanced level that appropriate responses can be generated. He explained that recent advances have gone beyond text-based chats, with companies like Apple (Siri), Google, and Amazon (Alexa), introducing voice-controlled virtual assistants, able to answer an infinite number of questions proficiently in natural language dialogue. "In a market like Africa where literacy rate falls heavily behind the world's average, voice-controlled products and services will revolutionise how a consumer interacts with technology platforms, reducing entry barriers and improving technology adoption," he said.

The last time I had a clear sense of the date it was still February. Time flies, the world warms, and the deals keep coming. This is a great time of year to stock up on outdoor gear and get your spring cleaning done. We found discounts on plenty of tech to help you out with both, plus some fun savings for those of you still whiling away the hours at home. Special offer for Gear readers: Get a 1-year subscription to WIRED for $5 ($25 off).

So, you're suddenly single, or single by a series of humiliating and bewildering degrees, and you find yourself in the prime, final ten to fifteen per cent of your life alone. Also, you are allergic to cats. Or somehow cats are not enough. You've tried them all: Tinder, Grindr (not a hotter Tinder, it turns out), FurryFriends (not at all what you thought), PamperedGals, MidnightCowboys, ReasonableBrides, Unpicky, and DamagedGoods. And yet you have not secured a perfect mate to hold your hand when it happens.

Consumers have invited AI into their lives with voice-activated personal assistants like Siri and Alexa, but how do they feel about computer vision technologies that can provide visual coaching and feedback in their homes? Sanjay Nichani, vice president of artificial intelligence and computer vision at Peloton Interactive, describes one compelling use case in the at-home fitness space. Sanjay Nichani is vice president of artificial intelligence and computer vision at Peloton Interactive. In that role, he leads an AI/computer vision team focused on human pose estimation, activity recognition, and movement-tracking technologies for the fitness domain. He also leads the ongoing development of Peloton Guide, a new camera-based interactive strength-training product. Previously, Nichani was vice president of the computer vision and machine learning team at Acuant, working on document forensics technologies for detecting fraud. Before that, he was vice president of the Mitek Labs R&D group, where he led the development of a deep learning-based image-processing pipeline for identity verification. He also founded 3D sensor technology company Merakona and cofounded Pelfunc, developer of a photo-sharing app/service. He has advanced degrees in business from Babson College and computer science from the University of South Florida.

You won't have to camp in front of a screen the next time you want to take advantage of an imminent Amazon sale. The company has updated Alexa with a Prime-only feature that alerts you to the availability of an Amazon deal up to 24 hours in advance as long as the relevant item is in your cart, saved for later or on your wish list. You can also remind Alexa to notify you when the deal is live, or even have the assistant buy the item when the deal takes effect. You can enable the feature by leaving products in the relevant lists. If there's a deal, you'll see Alexa's familiar yellow light or pop-up notification.

You might not know that Amazon makes wireless earbuds. The second-gen Echo Buds (8/10, WIRED Recommends) are some of our favorites. They sound great and work well with Alexa, and right now they're only $50. They frequently dip to $85, but this is the lowest price we've ever tracked. Even at their typical full price of $120, these wireless earbuds fall into the budget range, so at less than half that they're quite a steal. If you buy something using links in our stories, we may earn a commission.

ANJA KASPERSEN: Today I am very pleased to be joined by Pascale Fung. Pascale is a;rofessor in the Department of Electronic and Computer Engineering and Department of Computer Science and Engineering at The Hong Kong University of Science and Technology. She is known globally for her pioneering work on conversational artificial intelligence (AI), computational linguistics, and was one of the earliest proponents of statistical and machine-learning approaches for natural language processing (NLP). She is now leading groundbreaking research on how to build intelligent systems that can understand and empathize with humans. I have really been looking forward to this conversation with you. Your professional accolades are many, most of which we will touch on during our conversation. However, for our listeners to get to know you a bit better, I would like us to go back to your upbringing during what I understand to be a very tenuous political period in China. I was born, spent my childhood, ...

When a person joins an online-dating app, and then starts texting some of the people they've met on that app, and then makes plans to hang out with some of those people in the hopes of making out, they have a reasonable, limited expectation of privacy. Hardly anyone expects what happened to the mythological figure of "West Elm Caleb," a bumbling villain of the New York dating scene and hapless victim of the internet. In January, after a couple of New York women with substantial TikTok followings discovered that they had been dating Caleb simultaneously, it quickly came out that he was guilty of other crimes--sending the same Spotify playlist to multiple people, for instance, and not returning text messages. One woman recalled how he had told her that he found it harder to go on dates in the winter, because of the cold. Pretty soon brands were getting in on the West Elm Caleb conversation, as finding any excuse to talk about this pretty average dater in New York City became engagement-metric gold.