Abstract: Hierarchical branching deep convolutional neural networks (HD-CNNs) improve existing convolutional neural network (CNN) technology. In a HD-CNN, classes that can be easily distinguished are classified in a higher layer coarse category CNN, while the most difficult classifications are done on lower layer fine category CNNs. Multinomial logistic loss and a novel temporal sparsity penalty may be used in HD-CNN training. The use of multinomial logistic loss and a temporal sparsity penalty causes each branching component to deal with distinct subsets of categories.

Abstract: Hierarchical branching deep convolutional neural networks (HD-CNNs) improve existing convolutional neural network (CNN) technology. In a HD-CNN, classes that can be easily distinguished are classified in a higher layer coarse category CNN, while the most difficult classifications are done on lower layer fine category CNNs. Multinomial logistic loss and a novel temporal sparsity penalty may be used in HD-CNN training. The use of multinomial logistic loss and a temporal sparsity penalty causes each branching component to deal with distinct subsets of categories.

Abstract: Systems and methods for behavioral modeling to optimize shopping cart conversion are discussed. For example, a method can include identifying a user interacting with a networked system, accessing user profile data associated with the user, tracking user activity associated with the user, accessing a behavioral model, applying the behavioral model, and determining a shopping cart optimization. The behavioral model can be generated from historical data detailing interactions with the networked system. The behavioral model can be applied to the user profiled data and the user activity data to assist in selection of a shopping cart optimization.

Abstract: Support vector machines (SVMs), though accurate, are not preferred in applications requiring great classification speed, due to the number of support vectors being large. To overcome this problem a primal system and method with the following properties has been devised: (1) it decouples the idea of basis functions from the concept of support vectors; (2) it greedily finds a set of kernel basis functions of a specified maximum size (dmax) to approximate the SVM primal cost function well; (3) it is efficient and roughly scales as O(ndmax2) where n is the number of training examples; and, (4) the number of basis functions it requires to achieve an accuracy close to the SVM accuracy is usually far less than the number of SVM support vectors.

Abstract: The present invention provides a system and method for building fast and efficient support vector classifiers for large data classification problems which is useful for classifying pages from the World Wide Web and other problems with sparse matrices and large numbers of documents. The method takes advantage of the least squares nature of such problems, employs exact line search in its iterative process and makes use of a conjugate gradient method appropriate to the problem.

Abstract: A method for providing search results to a user is disclosed. The method includes receiving a first set of information associated with a plurality of web pages. A second set of information associated with a user preference, determining a commercial score for each web page is also received. A subset of the first set of information is determined based on the second set of information. A visual indicator for the subset of the first set of information is generated in accordance with a commercial score, and the subset and the visual indicator are displayed on a display.