Recent studies have shown that deep learning models such as RNNs and Transformers have brought significant performance gains for long-term forecasting of time series because they effectively utilize historical information. We found, however, that there is still great room for improvement in how to preserve historical information in neural networks while avoiding overfitting to noise present in the history. Addressing this allows better utilization of the capabilities of deep learning models. To this end, we design a Frequency improved Legendre Memory model, or FiLM: it applies Legendre polynomial projections to approximate historical information, uses Fourier projection to remove noise, and adds a low-rank approximation to speed up computation. Our empirical studies show that the proposed FiLM significantly improves the accuracy of state-of-the-art models in multivariate and univariate long-term forecasting by (19.2%, 22.6%), respectively. We also demonstrate that the representation module developed in this work can be used as a general plugin to improve the long-term prediction performance of other deep learning modules.

Federated learning allows distributed users to collaboratively train a model while keeping each user's data private. Recently, a growing body of work has demonstrated that an eavesdropping attacker can effectively recover image data from gradients transmitted during federated learning. However, little progress has been made in recovering text data. In this paper, we present a novel attack method FILM for federated learning of language models (LMs). For the first time, we show the feasibility of recovering text from large batch sizes of up to 128 sentences.

Video of a sidewalk delivery robot crossing yellow caution tape and rolling through a crime scene in Los Angeles went viral this week, amassing more than 650,000 views on Twitter and sparking debate about whether the technology is ready for prime time. It turns out the robot's error, at least in this case, was caused by humans. The video of the event was taken and posted on Twitter by William Gude, the owner of Film the Police LA, an LA-based police watchdog account. Gude was in the area of a suspected school shooting at Hollywood High School at around 10 a.m. when he captured on video the bot as it hovered on the street corner, looking confused, until someone lifted the tape, allowing the bot to continue on its way through the crime scene. A food delivery robot forces it's way across a police crime scene.

For decades science fiction film, television, and literature have addressed our human desire for connection with our dead loved ones. With the creation of artificial intelligence, our imagination for machine learning holograms and robots has turned into reality. More recent film and documentary programs have addressed this new technology and I will be examining numerous mediated stories throughout my research studies.

But authentic color filters do nothing to hide awkward, stilted animations and the lifeless storytelling of the main campaign. It's only when you ignore these faults, and even the main campaign, when you start to appreciate what "Ghost" offers. When I later found that the game's side quests are written much better, I realized that "Ghost" works better not as a long epic campaign, but as a world filled with some pretty good samurai short stories. Many even have twists that surprised me. If anything, the game would've worked better as a series of short stories.

Anyone who's watched "Bridget Jones's Diary" knows one of her New Year's resolutions is "Not go out every night but stay in and read books and listen to classical music." The reality, however, is substantially different. What people actually do in their leisure time often doesn't match with what they say they'll do. Economists have termed this phenomenon "hyperbolic discounting." In a famous study titled "Paying Not to Go to the Gym," a couple of economists found that, when people were offered the choice between a pay-per-visit contract and a monthly fee, they were more likely to choose the monthly fee and actually ended up paying more per visit.

Movie history is filled with computers that make us miserable. Unlike today's computers that make our lives dreadful, like the little ones in our pockets eager to sell out our privacy for a nickel, or crash when we need them most, yesterday's computers were their own character in each film. Everyone knows how rude HAL got at the end of 2001: A Space Odyssey (1968). In The Aries Computer (1972, a mysterious Vincent Price film that may have not been filmed or released, part of the Zodiac series) the reported plot was this: It's 2013 and a supercomputer named Aries has become a ruling force, and humans need to figure out how to take their power back. Later came films like Terminator (1984), with it's hive-mind Skynet keeping humans under its virtual thumb.

How artificial intelligence can be used creatively is an often asked, and perpetually unsolved, question. Of course, the term "AI" itself can be somewhat misleading; serving, as it does, as a catch-all phrase for anything involving machine learning and/or algorithms. What is possible, however, is to explore in general terms what levels of creativity we can currently see from the people and technology working in this space. Beginning with the most publicised stories, we have IBM's lighthouse project Watson, which created a movie trailer for the film "Morgan", (a film about an artificially intelligent robot child – spoiler alert: it doesn't go well), and Sony using a system of machine learning algorithms called "Flow Machines" to compose a pop song, ("Daddy's Car"). Further back, we also had Oscar Sharp and Ross Goodwin put a recurrent neural network to work writing a screenplay for a film called "Sunspring", which they subsequently shot in a single day, (it is a must-watch).

That's the question at the heart of the documentary AlphaGo, about an AI program designed to play the ancient Chinese board game Go. Fan and Lee are forced to answer this question as they're overwhelmed by AlphaGo's uncanny play style. If you don't remember how the matches went, I won't spoil the film for you, but suffice to say that humanity does land at least one blow on the machines, through Lee's so-called "divine move" -- Go terminology for a play that is both unexpected and entirely original. But while this works in the context of Lee's battle with DeepMind's AI, it feels a little limited with regards to the wider challenges posed by artificial intelligence.

The Digital Human League, for example, recently unveiled'Digital Mike' – an artificial likeness of producer Mike Seymour. The idea, Digital Mike explains in a promo video, is'to produce a virtual human, and not only a virtual human, but one rendered in real time – puppeteered or driven in real time, rendered in real time, and not only that, at 90 frames per second, in stereo, in VR.' In a new study, researchers from Oxford University's Future of Humanity Institute, Yale University, and AI Impacts surveyed 352 machine learning experts to forecast the progress of AI in the next few decades. The idea, Digital Mike explains in a promo video, is'to produce a virtual human, and not only a virtual human, but one rendered in real time – puppeteered or driven in real time, rendered in real time, and not only that, at 90 frames per second, in stereo, in VR' A study from Oxford University's Future of Humanity Institute, Yale University, and AI Impacts released this past spring concluded that in less than 50 years, AI will beat humans at everything from language translation and truck driving to writing high-school essays.