The goal of a recommender system is to show its users items that they will like. In forming its prediction, the recommender system tries to answer: "what would the rating be if we 'forced' the user to watch the movie?" This is a question about an intervention in the world, a causal question, and so traditional recommender systems are doing causal inference from observational data. This paper develops a causal inference approach to recommendation. Traditional recommenders are likely biased by unobserved confounders, variables that affect both the "treatment assignments" (which movies the users watch) and the "outcomes" (how they rate them). We develop the deconfounded recommender, a strategy to leverage classical recommendation models for causal predictions. The deconfounded recommender uses Poisson factorization on which movies users watched to infer latent confounders in the data; it then augments common recommendation models to correct for potential confounding bias. The deconfounded recommender improves recommendation and it enjoys stable performance against interventions on test sets.

Nefarious actors on social media and other platforms often spread rumors and falsehoods through images whose metadata (e.g., captions) have been modified to provide visual substantiation of the rumor/falsehood. This type of modification is referred to as image repurposing, in which often an unmanipulated image is published along with incorrect or manipulated metadata to serve the actor's ulterior motives. We present the Multimodal Entity Image Repurposing (MEIR) dataset, a substantially challenging dataset over that which has been previously available to support research into image repurposing detection. The new dataset includes location, person, and organization manipulations on real-world data sourced from Flickr. We also present a novel, end-to-end, deep multimodal learning model for assessing the integrity of an image by combining information extracted from the image with related information from a knowledge base. The proposed method is compared against state-of-the-art techniques on existing datasets as well as MEIR, where it outperforms existing methods across the board, with AUC improvement up to 0.23.

Reinforcement learning methods have been used for learning dialogue policies from the experience of conversations. However, learning an effective dialogue policy frequently requires prohibitively many conversations. This is partly because of the sparse rewards in dialogues, and the relatively small number of successful dialogues in early learning phase. Hindsight experience replay (HER) enables an agent to learn from failure, but the vanilla HER is inapplicable to dialogue domains due to dialogue goals being implicit (c.f., explicit goals in manipulation tasks). In this work, we develop two complex HER methods providing different trade-offs between complexity and performance. Experiments were conducted using a realistic user simulator. Results suggest that our HER methods perform better than standard and prioritized experience replay methods (as applied to deep Q-networks) in learning rate, and that our two complex HER methods can be combined to produce the best performance.

Machine intelligence--also known as artificial intelligence--is the ability of machines to perform tasks that would normally require human intelligence. These new machine capabilities both inspire and unnerve: trucks that drive themselves, computer programs that develop drug therapies, software that writes news articles and composes music. But before you can imagine the possibilities, you need to know the basics. This Machine Intelligence Primer will give you a foundational understanding of complex concepts. In it, we discuss where MI came from, how it got to where it is today, and where it's likely going. We are honored to accompany you in your effort to understand and harness MI.

Machine learning aims to create artificial intelligence systems that make decisions with little intervention from people.

Carnegie Mellon University's School of Computer Science announced that a new artificial intelligence (AI) major will be launched this year, the first …

It's been a week of risk in the tech world, and I don't just mean Elon Musk's recent Twitter-on-acid experiment. Best Buy is wagering $800 million on a company that teaches your grandparents how gadgets work, Saint Louis University is peppering its dorms with Echos for some reason, and Reebok is hoping folks won't be too tempted to eat their vegetable-based sneakers. That's why Best Buy is shelling out nearly a billion dollars for GreatCall, makers of the senior-friendly JitterBug phones and purveyors of an emergency tech support service. But what will the yutes do with all that extra time now that we're not explaining to our parents how IG works? In an upcoming sequel to the forthcoming film, 1st Born, Kaye plans to hire (or at least build) a robotic actor capable of starring in a feature length film next to A-List talent like Val Kilmer and Tom Berenger.

Alphabet is broken out into its core Google business and a number of other subsidiaries, which it deems "Other Bets." The majority of Google's business comes from advertising revenues, which the company generates through its search engine as well as a number of other Google-affiliated and partnership websites. Outside of search and advertising, Google generates revenue from products including cloud and enterprise, consumer hardware, mapping, and YouTube. In addition to Google, Alphabet encompasses a host of other subsidiaries called "Other Bets." These companies are more experimental in nature, and as a result are not material to Alphabet's bottom line.

We develop a reinforcement learning based search assistant which can assist users through a set of actions and sequence of interactions to enable them realize their intent. Our approach caters to subjective search where the user is seeking digital assets such as images which is fundamentally different from the tasks which have objective and limited search modalities. Labeled conversational data is generally not available in such search tasks and training the agent through human interactions can be time consuming. We propose a stochastic virtual user which impersonates a real user and can be used to sample user behavior efficiently to train the agent which accelerates the bootstrapping of the agent. We develop A3C algorithm based context preserving architecture which enables the agent to provide contextual assistance to the user. We compare the A3C agent with Q-learning and evaluate its performance on average rewards and state values it obtains with the virtual user in validation episodes. Our experiments show that the agent learns to achieve higher rewards and better states.