If we learned nothing else from the aughts, we learned that if we don't watch and enjoy the Homestar Runner Halloween cartoon every year, the terrorists win. Poofers Must Die: A Top-Notch 4½ Stars With Over 600 Reviews Quality Ghost Story." The structure of this year's toon means we only get brief glimpses of the main Homestar Runner cast until the costume roundup at the end, but they're just as eclectic and fun a collection of bizarre pop-culture references as ever. Homestar is Dirk the Daring, the hero of the 1983 Don Bluth-animated video game Dragon's Lair: Marzipan is J. Mascis, the singer and guitarist from Dinosaur Jr. Strong Sad is Tummi Gummi, a character from Disney's Adventures of the Gummi Bears, a cartoon that ran for six seasons between 1985 and 1991: Strong Mad is Kano, a character from 2000 AD who was originally supposed to be part of the Judge Dredd universe.

The iPhone XR looks to offer most of what made the iPhone XS a knockout for £250 less – but with a colourful body and a slightly larger screen is this the iPhone to buy? With the iPhone XS and XS Max starting at £999 and £1,099 respectively, Apple has room to shoehorn a slightly lower cost, but still expensive, model in underneath. The iPhone XR is that model, but with a slightly larger screen than the 5.8in iPhone XS that's also a little smaller than the 6.5in iPhone XS Max, it offers something subtly different too. The 6.1in LCD is colourful and relatively crisp with excellent viewing angles, but just not quite as brilliant as the OLED displays on the top iPhones or rivals of a similar price. The bezels are also noticeably larger than the other iPhones, making it look a little like an iPhone XS permanently in a case.

Now, an AI system developed by MIT students Ziv Epstein and Matt Groh adds spooky figures to your photos, no reality TV show required. Called AI Spirits, it's a website that lets you upload empty landscapes, to be haunted with humanoid shadows. "In the world all around us, many people have lived full lives and passed on. Yet they are still with us emotionally, spiritually, and intellectually," says Epstein. "In the business of daily life, we can forget them and only see the empty scenes all around us. AI Spirits is a visualization of saudade: the presence of absence."

Learning to rank is an important problem in machine learning and recommender systems. In a recommender system, a user is typically recommended a list of items. Since the user is unlikely to examine the entire recommended list, partial feedback arises naturally. At the same time, diverse recommendations are important because it is challenging to model all tastes of the user in practice. In this paper, we propose the first algorithm for online learning to rank diverse items from partial-click feedback. We assume that the user examines the list of recommended items until the user is attracted by an item, which is clicked, and does not examine the rest of the items. This model of user behavior is known as the cascade model. We propose an online learning algorithm, cascadelsb, for solving our problem. The algorithm actively explores the tastes of the user with the objective of learning to recommend the optimal diverse list. We analyze the algorithm and prove a gap-free upper bound on its n-step regret. We evaluate cascadelsb on both synthetic and real-world datasets, compare it to various baselines, and show that it learns even when our modeling assumptions do not hold exactly.

We consider the problem of classification in a comparison-based setting: given a set of objects, we only have access to triplet comparisons of the form "object $x_i$ is closer to object $x_j$ than to object $x_k$.'' In this paper we introduce TripletBoost, a new method that can learn a classifier just from such triplet comparisons. The main idea is to aggregate the triplets information into weak classifiers, which can subsequently be boosted to a strong classifier. Our method has two main advantages: (i) it is applicable to data from any metric space, and (ii) it can deal with large scale problems using only passively obtained and noisy triplets. We derive theoretical generalization guarantees and a lower bound on the number of necessary triplets, and we empirically show that our method is both competitive with state of the art approaches and resistant to noise.

Many knowledge graph embedding methods operate on triples and are therefore implicitly limited by a very local view of the entire knowledge graph. We present a new framework MOHONE to effectively model higher order network effects in knowledge-graphs, thus enabling one to capture varying degrees of network connectivity (from the local to the global). Our framework is generic, explicitly models the network scale, and captures two different aspects of similarity in networks: (a) shared local neighborhood and (b) structural role-based similarity. First, we introduce methods that learn network representations of entities in the knowledge graph capturing these varied aspects of similarity. We then propose a fast, efficient method to incorporate the information captured by these network representations into existing knowledge graph embeddings. We show that our method consistently and significantly improves the performance on link prediction of several different knowledge-graph embedding methods including TRANSE, TRANSD, DISTMULT, and COMPLEX(by at least 4 points or 17% in some cases).

Automatic melody generation has been a long-time aspiration for both AI researchers and musicians. However, learning to generate euphonious melodies has turned out to be highly challenging. This paper introduces 1) a new variant of variational autoencoder (VAE), where the model structure is designed in a modularized manner in order to model polyphonic and dynamic music with domain knowledge, and 2) a hierarchical encoding/decoding strategy, which explicitly models the dependency between melodic features. The proposed framework is capable of generating distinct melodies that sounds natural, and the experiments for evaluating generated music clips show that the proposed model outperforms the baselines in human evaluation.

Nicole (Niki) Black is an attorney in Rochester, New York and the legal technology evangelist at MyCase.com, a law.

The Allen Institute for Artificial Intelligence (AI2) welcomes applications to the 2017 Key Scientific Challenges program.