Microsoft Technology Licensing, LLC

Other

Microsoft Corporation

Ralf Herbrich

Thore Graepel

Thore K H Graepel

David Stern

Michael E Tipping

Mark Andrew Hatton

Jurgen Anne Francois Marie Van Gael

Andrew Blake

Tauhid Rashed Zaman

Gilad Lotan

Thomas Ivan Borchert

David Shaw

Yoram Bachrach

Joaquin Quinonero Candela

Weizhu Chen

Hugo Zaragoza

Ulrich Paquet

Thomas Minka

Thore Kurt Hartwig Graepel

Anton Schwaighofer

Oleg Isakov

Jeffrey Scott Dunn

Gjergji Kasneci

Thore Kraepel

Philipp Hennig

Horst Cornelius Samulowitz

Jurgen Anne Francios Marie Van Gael

Joaquin Quiñonero Candela

Kurt Hartwig Graepel

Julian Gold

Taha Bekir Eren

Shyansundar Rajaram

A real-time stereo video signal of a captured scene with a physical foreground object and a physical background is received. In real-time, a foreground/background separation algorithm is used on the real-time stereo video signal to identify pixels from the stereo video signal that represent the physical foreground object. A video sequence may be produced by rendering a 3D virtual reality based on the identified pixels of the physical foreground object.

Stereo video for gaming

Online recommendations are tracked through a forwarding service. The forwarding service can provide such statistics to an ad service, which can provide incentives to the recommending user and a consuming user. Example incentives may include an accumulation of points by the recommending user, a discount to the consuming user if a purchase is made in response to the recommendation, etc. To determine how much of an incentive each participant in the recommendation flow receives, a graph is created to model the recommendation flow and incentives are allocated using a cooperative game description based on this graph that associates each participant with a power index that represents that participants share of the incentive.

Pricing in social advertising

One or more techniques and/or systems are disclosed for predicting propagation of a message on a social network. A predictive model is trained to determine a probability of propagation of information on the social network using both positive and negative information propagation feedback, which may be collected while monitoring the social network over a desired period of time for information propagation. A particular message can be input to the predictive model, which can determine a probability of propagation of the message on the social network, such as how many connections may receive at least a portion of the message and/or a likelihood of at least a portion of the message reaching respective connections in the social network.

Information propagation probability for a social network

Methods, systems, and media are provided for a dynamic batch strategy utilized in parallelization of online learning algorithms. The dynamic batch strategy provides a merge function on the basis of a threshold level difference between the original model state and an updated model state, rather than according to a constant or pre-determined batch size. The merging includes reading a batch of incoming streaming data, retrieving any missing model beliefs from partner processors, and training on the batch of incoming streaming data. The steps of reading, retrieving, and training are repeated until the measured difference in states exceeds a set threshold level. The measured differences which exceed the threshold level are merged for each of the plurality of processors according to attributes. The merged differences which exceed the threshold level are combined with the original partial model states to obtain an updated global model state.

Parallelization of online learning algorithms

A recommender system may be used to predict a user behavior that a user will give in relation to an item. In an embodiment such predictions are used to enable items to be recommended to users. For example, products may be recommended to customers, potential friends may be recommended to users of a social networking tool, organizations may be recommended to automated users or other items may be recommended to users. In an embodiment a memory stores a data structure specifying a bi-linear collaborative filtering model of user behaviors. In the embodiment an automated inference process may be applied to the data structure in order to predict a user behavior given information about a user and information about an item. For example, the user information comprises user features as well as a unique user identifier.

Recommending items to users utilizing a bi-linear collaborative filtering model

Knowledge corroboration is described. In an embodiment many judges provide answers to many questions so that at least one answer is provided to each question and at least some of the questions have answers from more than one judge. In an example a probabilistic learning system takes features describing the judges or the questions or both and uses those features to learn an expertise of each judge. For example, the probabilistic learning system has a graphical assessment component which aggregates the answers in a manner which takes into account the learnt expertise in order to determine enhanced answers. In an example the enhanced answers are used for knowledge base clean-up or web-page classification and the learnt expertise is used to select judges for future questions. In an example the probabilistic learning system has a logical component that propagates answers according to logical relations between the questions.

Knowledge corroboration

Matchmaking processes at online game services often result in players having to wait unacceptably long times to receive a match or immediately receiving a poorly matched session. By using a matchmaking process which dynamically adapts a good balance is achieved between the quality of proposed matches (for example, in terms of how balanced, interesting and fun those matches are likely to be) and the waiting time for potential matches. A matchmaking threshold is specified. When a player seeks a match a waiting time is observed, for example, as to how long that player waits until starting a game or dropping out. Information about such waiting times is used to dynamically update the matchmaking threshold. The update is made on the basis of a relationship between information about the observed waiting time and a target waiting time. Further control may be achieved by using separate matchmaking thresholds and target waiting times for different game categories.

Adaptive matchmaking for games

Machine learning techniques may be used to train computing devices to understand a variety of documents (e.g., text files, web pages, articles, spreadsheets, etc.). Machine learning techniques may be used to address the issue that computing devices may lack the human intellect used to understand such documents, such as their semantic meaning. Accordingly, a topic model may be trained by sequentially processing documents and/or their features (e.g., document author, geographical location of author, creation date, social network information of author, and/or document metadata). Additionally, as provided herein, the topic model may be used to predict probabilities that words, features, documents, and/or document corpora, for example, are indicative of particular topics.

Topic models

Many computing scenarios involve the classification of content items within one or more categories. The content item set may be too large for humans to classify, but an automated classifier (e.g., an artificial neural network) may not be able to classify all content items with acceptable accuracy. Instead, the automated classifier may calculate a classification confidence while classifying respective content items. Content items having a low classification confidence may be sent to a human classifier, and may be added, along with the categories identified by the human classifier, to a training set. The automated classifier may then be retrained using the training set, thereby incrementally improving the classification confidence of the automated classifier while conserving the involvement of human classifiers. Additionally, human classifiers may be rewarded for classifying the content items, and the costs of such rewards may be considered while selecting content items for the training set.

Human-assisted training of automated classifiers

Skill scores represent a ranking or other indication of the skill of the player based on the outcome of the game in a gaming environment. Skills scores can be used in matching compatible players on the same team and matching opposing players or teams to obtain an evenly-matched competition. An initial skill score of a player in a new gaming environment may be based in whole or in part on the skill score of that player in another game environment. The influence that the skill scores for these other game environments may have in the skill score seeding for the new game environment may be weighted based on a defined compatibility factor with the new game environment. The compatibility factor can be determined based on a game-to-game basis, compatible categories or features, game developer defined parameters, or any combination of considerations.

Seeding in a skill scoring framework

Data structures for collaborative filtering systems are described. In an embodiment sketches which extremely concisely represent a list of items that a user has rated are created and stored for use by a collaborative filtering system to recommend items. For example, the sketches are created by using several versions of a cryptographic hash function to permute the item list and store a minimal value from each permutation in the sketch together with a user rating. In examples the sketches are used to compute estimates of similarity measures between pairs of users such as rank correlations including Spearman's Rho and Kendall's Tau. For example, the similarity measures are used by a collaborative filtering system to accurately and efficiently recommend items to users. For example the sketches are so concise that massive amounts of data can be taken into account in order to give high quality recommendations in a practical manner.

Data structures for collaborative filtering systems

There is a desire to provide a way to determine relative skills of players of games such as computer games, chess, tennis and any other suitable type of game. Our earlier Bayesian Scoring system is implemented in Xbox Live (trade mark) and is currently commercially available under the trade name TrueSkill (trade mark). Here we build on our earlier work and use a new method of computation to enable processing times to be significantly reduced. Message passing techniques are adapted to enable computation of updated skill beliefs to be obtained quickly even in the case of multiple teams of multiple players.

Growing community of inventors

Cambridge, United Kingdom

Ralf Herbrich