Abstract: A method of training an image classification neural network comprises: presenting a first plurality of images to an observer as a visual stimulus, while collecting neurophysiological signals from a brain of the observer; processing the neurophysiological signals to identify a neurophysiological event indicative of a detection of a target by the observer in at least one image of the first plurality of images; training the image classification neural network to identify the target in the image, based on the identification of the neurophysiological event; and storing the trained image classification neural network in a computer-readable storage medium.

Abstract: A method of training an image classification neural network comprises: presenting a first plurality of images to an observer as a visual stimulus, while collecting neurophysiological signals from a brain of the observer; processing the neurophysiological signals to identify a neurophysiological event indicative of a detection of a target by the observer in at least one image of the first plurality of images; training the image classification neural network to identify the target in the image, based on the identification of the neurophysiological event; and storing the trained image classification neural network in a computer-readable storage medium.

Abstract: A method of classifying an image is disclosed. The method comprises: applying a computer vision procedure to the image to detect therein candidate image regions suspected as being occupied by a target; presenting to an observer each candidate image region as a visual stimulus, while collecting neurophysiological signals from a brain of the observer; processing the neurophysiological signals to identify a neurophysiological event indicative of a detection of the target by the observer; and determining an existence of the target in the image is based, at least in part, on the identification of the neurophysiological event.

Abstract: Systems and method for classifying EEG signals of a human subject generated responsive to a series of images containing target images and non-target images. The EEG signals are in a spatio-temporal representation. The time points are classified independently, using a linear discriminant classifier, to compute spatio-temporal discriminating weights that are used to amplify the spatio-temporal representation, to create a spatially-weighted representation. Principal Component Analysis is used on a temporal domain for dimensionality reduction, separately for each spatial channel of the signals, to create a projection, which is applied to the spatially-weighted representation onto a first plurality of principal components, to create a temporally approximated spatially weighted representation.

Abstract: A method of training an image classification neural network comprises: presenting a first plurality of images to an observer as a visual stimulus, while collecting neurophysiological signals from a brain of the observer; processing the neurophysiological signals to identify a neurophysiological event indicative of a detection of a target by the observer in at least one image of the first plurality of images; training the image classification neural network to identify the target in the image, based on the identification of the neurophysiological event; and storing the trained image classification neural network in a computer-readable storage medium.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for selecting textual representations for entity attribute values. One of the methods includes receiving, for presentation to a user, data identifying a relevant entity and a respective presentation attribute value for each of a plurality of presentation attributes associated with the relevant entity; obtaining user profile data for the user; selecting a respective textual representation for each of the presentation attribute values, wherein selecting the textual representations comprises selecting a first alternative textual representation for a first presentation attribute value based on the user profile data; and providing data identifying the entity and the textual representations for presentation to the user.

Abstract: Systems and methods are disclosed for enriching a knowledge base for search queries. According to certain embodiments, images are assigned annotations that identify entities contained in the images. An object entity is selected among the entities based on the annotations and at least one attribute entity is determined using annotated images containing the object entity. A relationship between the object entity and the at least one attribute entity is inferred and stored in the knowledge base. In some embodiments, confidence may be calculated for the entities. The confidence scores may be aggregated across a plurality of images to identify an object entity.

Abstract: Systems and methods are disclosed for providing an explanation of an estimate for information missing from a data graph. An example method may include receiving a query that requests information for a first entity and receiving an estimate for the information, the estimate being based on a plurality of features of a joint distribution model. The method may include determining respective contribution scores for the plurality of features, selecting a quantity of the features with highest contribution scores, generating, using the selected quantity of features, an explanation for the estimate; and providing the explanation and the estimate as part of a search result for the query.

Abstract: A method of classifying an image is disclosed. The method comprises: applying a computer vision procedure to the image to detect therein candidate image regions suspected as being occupied by a target; presenting to an observer each candidate image region as a visual stimulus, while collecting neurophysiological signals from a brain of the observer; processing the neurophysiological signals to identify a neurophysiological event indicative of a detection of the target by the observer; and determining an existence of the target in the image is based, at least in part, on the identification of the neurophysiological event.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for selecting textual representations for entity attribute values. One of the methods includes receiving, for presentation to a user, data identifying a relevant entity and a respective presentation attribute value for each of a plurality of presentation attributes associated with the relevant entity; obtaining user profile data for the user; selecting a respective textual representation for each of the presentation attribute values, wherein selecting the textual representations comprises selecting a first alternative textual representation for a first presentation attribute value based on the user profile data; and providing data identifying the entity and the textual representations for presentation to the user.

Abstract: Systems and methods are disclosed for providing an explanation of an estimate for information missing from a data graph. An example method may include receiving a query that requests information for a first entity and receiving an estimate for the information, the estimate being based on a plurality of features of a joint distribution model. The method may include determining respective contribution scores for the plurality of features, selecting a quantity of the features with highest contribution scores, generating, using the selected quantity of features, an explanation for the estimate; and providing the explanation and the estimate as part of a search result for the query.

Abstract: Systems and method for classifying EEG signals of a human subject generated responsive to a series of images containing target images and non-target images. The EEG signals are in a spatio-temporal representation. The time points are classified independently, using a linear discriminant classifier, to compute spatio-temporal discriminating weights that are used to amplify the spatio-temporal representation, to create a spatially-weighted representation. Principal Component Analysis is used on a temporal domain for dimensionality reduction, separately for each spatial channel of the signals, to create a projection, which is applied to the spatially-weighted representation onto a first plurality of principal components, to create a temporally approximated spatially weighted representation.