Abstract: An approach is provided in which a knowledge manager selects an extraction layer from a convolutional neural network that was trained on an initial set of images. The knowledge manager processes subsequent images obtained from crawling a computer network that includes extracting image feature sets of the subsequent images from the selected extraction layer and generating tags from metadata associated with the subsequent images. In turn, the knowledge manager receives a new image, extracts a new image feature set from the selected extraction layer, and assigns one or more of the tags to the new image based upon evaluating the new image feature set to the image features sets of the subsequent images.

Abstract: An approach is provided in which a knowledge manager locates centroids in a high-dimensional vector space that are closest to a new image feature set and performs nearest neighbor searches on feature sets included in clusters corresponding to the located centroids. The knowledge manager then selects feature sets closest to the new image feature set based on the nearest neighbor searches and in turn, marks images corresponding to the selected closest features sets as similar images to a new image corresponding to the new image feature set.

Abstract: An approach is provided in which a knowledge manager selects an extraction layer from a convolutional neural network that was trained on an initial set of images. The knowledge manager processes subsequent images obtained from crawling a computer network that includes extracting image feature sets of the subsequent images from the selected extraction layer and generating tags from metadata associated with the subsequent images. In turn, the knowledge manager receives a new image, extracts a new image feature set from the selected extraction layer, and assigns one or more of the tags to the new image based upon evaluating the new image feature set to the image features sets of the subsequent images.

Abstract: An approach is provided in which a knowledge manager locates centroids in a high-dimensional vector space that are closest to a new image feature set and performs nearest neighbor searches on feature sets included in clusters corresponding to the located centroids. The knowledge manager then selects feature sets closest to the new image feature set based on the nearest neighbor searches and in turn, marks images corresponding to the selected closest features sets as similar images to a new image corresponding to the new image feature set. identifies a set of closest centroids to a new image in a high-dimensional vector space and performs a nearest neighbors search between the new image and each of the images included in a set of clusters that correspond to the set of closest centroids. In turn, the knowledge manager selects similar images based upon the nearest neighbors search and provides the similar images to a user interface.

Abstract: An approach is provided in which a knowledge manager trains a custom taxonomy classifier based upon a set of training samples that results in the custom taxonomy classifier understanding relationships between a set of pre-leaned terms. The knowledge manager then uses the custom taxonomy classifier to analyze input data and determine that the input data corresponds to one or more of the pre-learned terms. In turn, the custom taxonomy classifier matches the corresponding pre-learned terms to user-defined categories and assigns the input data to the matched user-defined categories.

Abstract: An approach is provided in which a knowledge manager selects an extraction layer from a convolutional neural network that was trained on an initial set of images. The knowledge manager processes subsequent images obtained from crawling a computer network that includes extracting image feature sets of the subsequent images from the selected extraction layer and generating tags from metadata associated with the subsequent images. In turn, the knowledge manager receives a new image, extracts a new image feature set from the selected extraction layer, and assigns one or more of the tags to the new image based upon evaluating the new image feature set to the image features sets of the subsequent images.

Abstract: An approach is provided in which a knowledge manager selects an extraction layer from a convolutional neural network that was trained on an initial set of images. The knowledge manager processes subsequent images obtained from crawling a computer network that includes extracting image feature sets of the subsequent images from the selected extraction layer and generating tags from metadata associated with the subsequent images. In turn, the knowledge manager receives a new image, extracts a new image feature set from the selected extraction layer, and assigns one or more of the tags to the new image based upon evaluating the new image feature set to the image features sets of the subsequent images.

Abstract: An approach is provided in which a knowledge manager computes a set of unreasonable answer probabilities based upon a corresponding set of answers. Each of the set of unreasonable answer probabilities indicate a likelihood that its corresponding answer is an unreasonable answer to a question received by the knowledge manager. The knowledge manager determines that one or more unreasonable answers are included in the set of answers based upon determining that their corresponding unreasonable answer probabilities are above a threshold. In turn, the knowledge manager removes the one or more unreasonable answers from the set of answers and provides a modified set of answers to a user.