When Tony Stark needs to travel to space in the original Iron Man movie, he asks his artificial intelligent (AI) assistant J.A.R.V.I.S. to make a suit that can survive harsh conditions. As AI specialist Kamal Choudhary explains: "The way I see it, what J.A.R.V.I.S. did is, it had a database of materials, scanned the database, found a suitable material, tested it, then synthesized an alloy that could survive space conditions. "That's what we want our system to do, and that's why we called it JARVIS." Choudhary, a researcher at the National Institute of Standards and Technology (NIST), is the founder and developer of JARVIS (Joint Automated Repository for Various Integrated Simulations)--an open dataset designed to automate materials discovery and optimization. Writing in npj Computational Materials in December 2021, Choudhary and Brian DeCost (NIST) described the latest enhancements to JARVIS that apply AI to speed discovery. Combining graph neural networks with chemical and structural knowledge about materials, their Atomistic Line Graph Neural Network (ALIGNN) outperforms previously reported models on atomistic prediction tasks with very high accuracy and better or comparable model training speed. "ALIGNN can predict characteristics in seconds instead of months," Choudhary said. Beyond the inspiration from Iron Man, there was the Materials Genome Initiative. Originated in 2011 under President Obama, the initiative is a multi-federal agency effort to discover, manufacture, and deploy advanced materials twice as fast and at a fraction of the cost of traditional methods. NIST's original contribution to the initiative was the creation of a database of materials and their characteristics, obtained rigorously, using standardized, cutting-edge computing methods. Several such databases have been established, but "what's particular about the JARVIS database is that it contains modules for various kinds of computational approaches," according to David Vanderbilt, professor of physics at Rutgers University, member of the National Academy of Sciences, and a contributor to the project. "There are many different theoretical levels on which you can approach the field.

Conversational agents (CAs) have the great potential in mitigating the clinicians' burden in screening for neurocognitive disorders among older adults. It is important, therefore, to develop CAs that can be engaging, to elicit conversational speech input from older adult participants for supporting assessment of cognitive abilities. As an initial step, this paper presents research in developing the backchanneling ability in CAs in the form of a verbal response to engage the speaker. We analyzed 246 conversations of cognitive assessments between older adults and human assessors, and derived the categories of reactive backchannels (e.g. "hmm") and proactive backchannels (e.g. "please keep going"). This is used in the development of TalkTive, a CA which can predict both timing and form of backchanneling during cognitive assessments. The study then invited 36 older adult participants to evaluate the backchanneling feature. Results show that proactive backchanneling is more appreciated by participants than reactive backchanneling.

Recurrent neural networks have proven effective in modeling sequential user feedbacks for recommender systems. However, they usually focus solely on item relevance and fail to effectively explore diverse items for users, therefore harming the system performance in the long run. To address this problem, we propose a new type of recurrent neural networks, dubbed recurrent exploration networks (REN), to jointly perform representation learning and effective exploration in the latent space. REN tries to balance relevance and exploration while taking into account the uncertainty in the representations. Our theoretical analysis shows that REN can preserve the rate-optimal sublinear regret even when there exists uncertainty in the learned representations. Our empirical study demonstrates that REN can achieve satisfactory long-term rewards on both synthetic and real-world recommendation datasets, outperforming state-of-the-art models.

Deep learning, big data, the cloud, and the rest of the pieces of the developing AI world are becoming familiar, being visualized by marketers who understand we need images and ideas that fit into our worldview. We already love our cars and our dogs, so falling in love with an AI personal assistant who actually talks, and listens to us, seems like an easy jump. They pay attention to us, care for us, are interested and responsive, and leave us in charge. They don't judge us or pressure us, but actually seem to like us: Robots and human proximity. The heart of AI and robotic development, real and fictional, has always been how the brain works.

Recently, graph collaborative filtering methods have been proposed as an effective recommendation approach, which can capture users' preference over items by modeling the user-item interaction graphs. In order to reduce the influence of data sparsity, contrastive learning is adopted in graph collaborative filtering for enhancing the performance. However, these methods typically construct the contrastive pairs by random sampling, which neglect the neighboring relations among users (or items) and fail to fully exploit the potential of contrastive learning for recommendation. To tackle the above issue, we propose a novel contrastive learning approach, named Neighborhood-enriched Contrastive Learning, named NCL, which explicitly incorporates the potential neighbors into contrastive pairs. Specifically, we introduce the neighbors of a user (or an item) from graph structure and semantic space respectively. For the structural neighbors on the interaction graph, we develop a novel structure-contrastive objective that regards users (or items) and their structural neighbors as positive contrastive pairs. In implementation, the representations of users (or items) and neighbors correspond to the outputs of different GNN layers. Furthermore, to excavate the potential neighbor relation in semantic space, we assume that users with similar representations are within the semantic neighborhood, and incorporate these semantic neighbors into the prototype-contrastive objective. The proposed NCL can be optimized with EM algorithm and generalized to apply to graph collaborative filtering methods. Extensive experiments on five public datasets demonstrate the effectiveness of the proposed NCL, notably with 26% and 17% performance gain over a competitive graph collaborative filtering base model on the Yelp and Amazon-book datasets respectively. Our code is available at: https://github.com/RUCAIBox/NCL.

In recent years, the Internet of Things (IoT), has seen more popularity in cyber markets. Statista projects the IoT industry worldwide. The Internet of Things (IoT), which is a collection of connected devices such as smart home and office gadgets and others, has seen more popularity in recent years. Statista predicts that the IoT market will exceed one trillion dollars worldwide by 2030. Businesses can now use IoT technology to increase their revenue.

The way we express ourselves, either orally or in writing, tells a lot about who we are and how we feel at that moment. The words, tone, pitch, everything adds up to create a piece of information that we want to convey to the other person and the same is very peculiar to us. In theory, human behaviour is predictable with the help of the information a human being conveys through verbal communication. An individual is capable of generating thousands of sentences, and each sentence has its own level of complexity attached to it. Now imagine the level of complexity in analysing the language used by crores of people.

What do I mean by "recommender systems", and why are they useful? Let's look at the top 3 websites on the Internet, according to Alexa: Google, YouTube, and Facebook. Recommender systems form the very foundation of these technologies. Google: Search results They are why Google is the most successful technology company today. YouTube: Video dashboard I'm sure I'm not the only one who's accidentally spent hours on YouTube when I had more important things to do! Just how do they convince you to do that?

A new British dating app is promising to eradicate Tinder Swindler-style romance fraud, which cost duped daters almost £100m last year, by ensuring that all members complete biometric ID verification before they digitally mingle. Fluttr, which claims to be the first UK online dating app to use such technology to improve user safety, is launching on Valentine's Day in the hope of getting a boost from singletons looking to change their relationship status. The issue of romance fraud, catfishing and fake profiles has been put into the spotlight following the release of Netflix documentary The Tinder Swindler, which tells the true story of a man who went to extraordinary lengths to scam women for millions after meeting them online. The pandemic, when online dating was the only mixing that was allowed, has driven a huge surge in scams costing those duped £92m in the UK last year. "We want to rid the world of Tinder Swindlers and create a safe space free from the fake profiles used to defraud, catfish and abuse online daters," said Rhonda Alexander, the chief executive and co-founder of Fluttr.

E-commerce platforms generate vast amounts of customer behavior data, such as clicks and purchases, from millions of unique users every day. However, effectively using this data for behavior understanding tasks is challenging because there are usually not enough labels to learn from all users in a supervised manner. This paper extends the BERT model to e-commerce user data for pre-training representations in a self-supervised manner. By viewing user actions in sequences as analogous to words in sentences, we extend the existing BERT model to user behavior data. Further, our model adopts a unified structure to simultaneously learn from long-term and short-term user behavior, as well as user attributes. We propose methods for the tokenization of different types of user behavior sequences, the generation of input representation vectors, and a novel pretext task to enable the pre-trained model to learn from its own input, eliminating the need for labeled training data. Extensive experiments demonstrate that the learned representations result in significant improvements when transferred to three different real-world tasks, particularly compared to task-specific modeling and multi-task representation learning