Search


Google found to shatter the illusion of Santa for 1.1 million children every year

Daily Mail - Science & tech

It's a question most of us have asked at one point in our lives -is Santa real? Today's children aren't looking to their parents for an answer, but are turning to Google and the search engine is shattering the shattering the illusion. A report found that 1.1 million children learn online that Saint Nick is a fictitious character, as the first article in the search says'as adults we know Santa Claus isn't real.' When searching'Is Santa real' the first article that is displayed comes from Quartz, which provides parents with advice on how to answer the question . And the introductory sentence of the article reads: 'As adults we know Santa Claus isn't real.'


Google taps AI to improve news results in Search

#artificialintelligence

Google says it's implementing AI and machine learning techniques to improve story suggestions in Google Search. In a blog post this morning, the tech giant announced that users in the U.S. in English (with more languages and locations to come in the next few months) who search for a news topic will now see an article carousel at the top of the results page. When there are multiple stories related to a search, each will be organized by relevance and quality in a way that accounts for a diversity of perspectives. "People come to Search for all types of information to help them form a better understanding of the world and the topics they care about most," wrote Google Search product manager Duncan Osborn. "We've continued to bring new improvements to Search to help people better orient themselves around a topic and easily explore related ideas, so they can more quickly go from having a question in mind to developing deeper understanding … Our research has shown that clustering results into clearly-defined stories is critical in helping people easily navigate the results and identify the best content for their needs."


Predictions Series: Top 10 Trends in Digital Advertising in 2020

#artificialintelligence

As we approach the "visionary" year of 2020, we took a look at what the New Year has in store for the Digital Advertising industry. Here are key things to watch out for as you plan ahead and finalize your Marketing budgets. Brands have begun to understand the power of advertising on Amazon and the unique opportunity it offers to capture people at the beginning of their purchasing journey. The Opportunity: Brands have flocked to Amazon for its revenue-generating ad capabilities. We expect this trend to continue in 2020 as Amazon refines its offering and advertiser use becomes more sophisticated.


Attractive Innovation Project Awards 2019 - UU Innovation - Uppsala University, Sweden

#artificialintelligence

Common to all projects is support från Uppsala University Innovation and success in securing external funding to further enhance development opportunities. Proteins are the workers of the cell, and many proteins interact with each other. In order to understand the importance of these interactions, there is a need to measure both free and interacting proteins. Ola Söderberg, professor at the Department of Pharmaceutical Biosciences, has developed a method to label each protein with its own unique colour, making it possible to measure the proteins individually. At the same time, the proportion of proteins that bind to each other are labelled with a combination of the colours.


Theoretical Analysis of Heuristic Search Methods for Online POMDPs

Neural Information Processing Systems

Planning in partially observable environments remains a challenging problem, despite significant recent advances in offline approximation techniques. A few online methods have also been proposed recently, and proven to be remarkably scalable, but without the theoretical guarantees of their offline counterparts. Thus it seems natural to try to unify offline and online techniques, preserving the theoretical properties of the former, and exploiting the scalability of the latter. In this paper, we provide theoretical guarantees on an anytime algorithm for POMDPs which aims to reduce the error made by approximate offline value iteration algorithms through the use of an efficient online searching procedure. The algorithm uses search heuristics based on an error analysis of lookahead search, to guide the online search towards reachable beliefs with the most potential to reduce error.


Human memory search as a random walk in a semantic network

Neural Information Processing Systems

The human mind has a remarkable ability to store a vast amount of information in memory, and an even more remarkable ability to retrieve these experiences when needed. Understanding the representations and algorithms that underlie human memory search could potentially be useful in other information retrieval settings, including internet search. Psychological studies have revealed clear regularities in how people search their memory, with clusters of semantically related items tending to be retrieved together. These findings have recently been taken as evidence that human memory search is similar to animals foraging for food in patchy environments, with people making a rational decision to switch away from a cluster of related information as it becomes depleted. We demonstrate that the results that were taken as evidence for this account also emerge from a random walk on a semantic network, much like the random web surfer model used in internet search engines.


Link Prediction in Graphs with Autoregressive Features

Neural Information Processing Systems

In the paper, we consider the problem of link prediction in time-evolving graphs. We assume that certain graph features, such as the node degree, follow a vector autoregressive (VAR) model and we propose to use this information to improve the accuracy of prediction. Our strategy involves a joint optimization procedure over the space of adjacency matrices and VAR matrices which takes into account both sparsity and low rank properties of the matrices. Oracle inequalities are derived and illustrate the trade-offs in the choice of smoothing parameters when modeling the joint effect of sparsity and low rank property. The estimate is computed efficiently using proximal methods through a generalized forward-backward agorithm.


Predicting response time and error rates in visual search

Neural Information Processing Systems

A model of human visual search is proposed. It predicts both response time (RT) and error rates (RT) as a function of image parameters such as target contrast and clutter. The model is an ideal observer, in that it optimizes the Bayes ratio of tar- get present vs target absent. The ratio is computed on the firing pattern of V1/V2 neurons, modeled by Poisson distributions. The optimal mechanism for integrat- ing information over time is shown to be a'soft max' of diffusions, computed over the visual field by'hypercolumns' of neurons that share the same receptive field and have different response properties to image features.


Evaluating Search Engines by Modeling the Relationship Between Relevance and Clicks

Neural Information Processing Systems

We propose a model that leverages the millions of clicks received by web search engines, to predict document relevance. This allows the comparison of ranking functions when clicks are available but complete relevance judgments are not. After an initial training phase using a set of relevance judgments paired with click data, we show that our model can predict the relevance score of documents that have not been judged. These predictions can be used to evaluate the performance of a search engine, using our novel formalization of the confidence of the standard evaluation metric discounted cumulative gain (DCG), so comparisons can be made across time and datasets. This contrasts with previous methods which can provide only pair-wise relevance judgements between results shown for the same query.


Dirichlet-Bernoulli Alignment: A Generative Model for Multi-Class Multi-Label Multi-Instance Corpora

Neural Information Processing Systems

We propose Dirichlet-Bernoulli Alignment (DBA), a generative model for corpora in which each pattern (e.g., a document) contains a set of instances (e.g., paragraphs in the document) and belongs to multiple classes. By casting predefined classes as latent Dirichlet variables (i.e., instance level labels), and modeling the multi-label of each pattern as Bernoulli variables conditioned on the weighted empirical average of topic assignments, DBA automatically aligns the latent topics discovered from data to human-defined classes. DBA is useful for both pattern classification and instance disambiguation, which are tested on text classification and named entity disambiguation for web search queries respectively. Papers published at the Neural Information Processing Systems Conference.