Modeling the world can benefit robot learning by providing a rich training signal for shaping an agent's latent state space. However, learning world models in unconstrained environments over high-dimensional observation spaces such as images is challenging. One source of difficulty is the presence of irrelevant but hard-to-model background distractions, and unimportant visual details of task-relevant entities. We address this issue by learning a recurrent latent dynamics model which contrastively predicts the next observation. This simple model leads to surprisingly robust robotic control even with simultaneous camera, background, and color distractions. We outperform alternatives such as bisimulation methods which impose state-similarity measures derived from divergence in future reward or future optimal actions. We obtain state-of-the-art results on the Distracting Control Suite, a challenging benchmark for pixel-based robotic control.

The ubiquity of implicit feedback makes it indispensable for building recommender systems. However, it does not actually reflect the actual satisfaction of users. For example, in E-commerce, a large portion of clicks do not translate to purchases, and many purchases end up with negative reviews. As such, it is of importance to account for the inevitable noises in implicit feedback. However, little work on recommendation has taken the noisy nature of implicit feedback into consideration. In this work, we explore the central theme of denoising implicit feedback for recommender learning, including training and inference. By observing the process of normal recommender training, we find that noisy feedback typically has large loss values in the early stages. Inspired by this observation, we propose a new training strategy named Adaptive Denoising Training (ADT), which adaptively prunes the noisy interactions by two paradigms (i.e., Truncated Loss and Reweighted Loss). Furthermore, we consider extra feedback (e.g., rating) as auxiliary signal and propose three strategies to incorporate extra feedback into ADT: finetuning, warm-up training, and colliding inference. We instantiate the two paradigms on the widely used binary cross-entropy loss and test them on three representative recommender models. Extensive experiments on three benchmarks demonstrate that ADT significantly improves the quality of recommendation over normal training without using extra feedback. Besides, the proposed three strategies for using extra feedback largely enhance the denoising ability of ADT.

The inversion of real images into StyleGAN's latent space is a well-studied problem. Nevertheless, applying existing approaches to real-world scenarios remains an open challenge, due to an inherent trade-off between reconstruction and editability: latent space regions which can accurately represent real images typically suffer from degraded semantic control. Recent work proposes to mitigate this trade-off by fine-tuning the generator to add the target image to well-behaved, editable regions of the latent space. While promising, this fine-tuning scheme is impractical for prevalent use as it requires a lengthy training phase for each new image. In this work, we introduce this approach into the realm of encoder-based inversion. We propose HyperStyle, a hypernetwork that learns to modulate StyleGAN's weights to faithfully express a given image in editable regions of the latent space.

Recommendation systems are algorithms with an objective to suggest the most relevant information to users, whether that be similar products on Amazon, similar TV shows on Netflix, or similar songs on Spotify. There are two main types of recommendation systems: collaborative filtering and content-based filtering. Recommendation systems are one of the most widely used and most practical data science applications. Not only that, but it also has one of the highest ROIs when it comes to data products. It's estimated that Amazon increased its sales by 29% in 2019, specifically due to its recommendation system. As well, Netflix claimed that its recommendation system was worth a staggering $1 billion in 2016! But what makes it so profitable? As I alluded to earlier, it's about one thing: relevancy. By providing users with more relevant products, shows, or songs, you're ultimately increasing their likelihood to purchase more and/or stay engaged longer.

In August, Savannah's entire monthly income was at stake. OnlyFans, the social media platform where she built her career, making an average of $2,000 a month from subscribers, had just announced it would be removing content like hers from the site. But there was little she could do about it. She remembers thinking: "OK, well, this is another Thursday, I might as well finish my Chick-Fil-A, and I'm just gonna chill here and wait for us to get some sort of response." Savannah, 24, is part of a vibrant, supportive community of online sex workers that underwrite OnlyFans's considerable financial success; it's now valued at over $1 billion. But in a move that may foreshadow changes to come, that community was shaken when OnlyFans announced it would be banning explicit content on the site. "The sky falls on OnlyFans, like, every three or four months," Savannah says, wryly.

Collaborative filtering (CF) based on the alternating least squares (ALS) technique is another algorithm used to generate recommendations. It produces automatic predictions (filtering) about the interests of a user by collecting preferences from many other users (collaborating). The underlying assumption of the CF approach is that if a person A has the same opinion as a person B on an issue, A is more likely to have B's opinion on a different issue than a randomly chosen person. This algorithm gained a lot of traction in the data science community after it was used by the team winner of the Netflix Prize. The CF algorithm has also been implemented in Spark MLlib with the aim of addressing fast execution on very large datasets.

The first Matrix movie introduced a generation of sci-fi fans to an ancient philosopher's saw: What if your entire reality were a deceit? Two decades on, the film's plot--free-thinking renegades attempt to expose the lies behind an oppressive system--is as timely as ever, but its conceptual premise feels almost quaint. The technologies that have emerged since then do indeed raise the question of what is real, but now they do it in ways that are stranger than even the movie predicted, if rarely quite as sinister. Your day-to-day reality is an increasingly synthetic experience: Computerized voices inhabit your smart speakers, deepfakes bring dead movie actors back to life, and AI-generated artworks go for eye-watering prices at auction. The simulacrum is extending into food too: Supermarket shelves already contain countless vegan substitutes for meat and other animal products, and before long "real" meat, grown in a lab, will join them.

The phrase "artificial intelligence" can conjure up images of machines that are able to think, and act, just like humans, independent of any oversight from actual, flesh and blood people. Movies versions of AI tend to feature super-intelligent machines attempting to overthrow humanity and conquer the world. The reality is more prosaic, and tends to describe software that can solve problems, find patterns and, to a certain extent, "learn". This is particularly useful when huge amounts of data need to be sorted and understood, and AI is already being used in a host of scenarios, particularly in the private sector. Examples include chatbots able to conduct online correspondence; online shopping sites which learn how to predict what you might want to buy; and AI journalists writing sports and business articles (this story was, I can assure you, written by a human).

Many believe that artificial intelligence is a futuristic concept that we only see in sci-fi movies with humanoid robots and holograms. However, it is becoming rooted in our reality, affecting various fields and groups, including persons with disabilities. Accessibility and inclusivity are genuinely revolutionized, thanks to artificial intelligence! People with disabilities can substantially enhance their daily life thanks to AI technology solutions. We've already shown how smartphones can be tools for people with vision impairments.

PRNewswire/ — Z Advanced Computing, Inc. (ZAC), the pioneer Cognitive Explainable-AI (Artificial Intelligence) (Cognitive XAI) software startup, …