Versions of the invention are directed to computer-based methods, apparatus and software (programs) for fast, dynamic programming and recursive partitioning techniques to segment data, especially real-world data, into data structures for display as nodal trees. These techniques and displayed data in segmented form have numerous applications, especially for the analysis and understanding of real-world data. Some particular applications are in the area of computational high throughput screening of...

A special purpose processor (SPP) can use a Field Programmable Gate Array (FPGA) or similar programmable device to model a large number of neural elements. The FPGAs can have multiple cores doing presynaptic, postsynaptic, and plasticity calculations in parallel. Each core can implement multiple neural elements of the neural model.

The present invention provides techniques for transmitting at least one signal through an element of a classification system. One or more input signals are received at the element. One or more functional components are extracted from the one or more input signals, and one or more membership components are extracted from the one or more input signals. An output signal is generated from the element comprising a functional component and a membership component that correspond to one or more function...

Media and gesture recognition apparatus and methods are disclosed. A computerized system views a first printed media using an electronic visual sensor. The system retrieves information corresponding to the viewed printed media from a database. Using the electronic visual sensor, the system views at least a first user gesture relative to at least a portion of the first printed media. The system interprets the gesture as a command, and based at least in part on the first gesture and the retrieved ...

Provided are systems, methods and techniques for classifying items. According to one preferred embodiment, initial feature sets are obtained for a current batch of items, and classification predictions are generated for the items based on their initial feature sets, using a set of existing classifiers. The classification predictions are then appended as additional features to the respective feature sets of the items, thereby obtaining enhanced feature sets, and a first classifier is trained, usi...

A system for learning an attention model for an image based on user navigation actions while viewing the image is provided. An attention model learning system generates an initial attention model based on static features derived from the image. The learning system logs the actions of users as they view the image. The learning system identifies from the actions of the users those areas of the image that may be of user interest: After the learning system identifies areas that may be of user intere...

Disclosed are a system and method of multi-modality sensor data classification and fusion comprising partitioning data stored in a read only memory unit on a sensor node using a low query complexity boundary-decision classifier, applying an iterative two-dimensional nearest neighbor classifier to the partitioned data, forming a low query complexity classifier from a combination of the low query complexity boundary-decision classifier and the iterative two-dimensional nearest neighbor classifier,...

A method and system for document analysis and retrieval. A remote host in a first computing system transmits a first portion and at least one additional portion of a document to a web service host in a second computing system. The web service host reconstructs the entire document from the received first portion and at the least one additional portion. After reconstructing the entire document, the web service host implements at least one of extracting, generating, and determining steps. The extra...

A neural network system includes a random access memory (RAM); and an index-based weightless neural network with a columnar topography; wherein patterns of binary connections and values of output nodes' activities are stored in the RAM. Information is processed by pattern recognition using the neural network by storing a plurality of output patterns to be recognized in a pattern index; accepting an input pattern and dividing the input pattern into a plurality of components; and processing each c...

Systems and methods for clustering-based text classification are described. In one aspect text is clustered as a function of labeled data to generate cluster(s). The text includes the labeled data and unlabeled data. Expanded labeled data is then generated as a function of the cluster(s). The expanded label data includes the labeled data and at least a portion of unlabeled data. Discriminative classifier(s) are then trained based on the expanded labeled data and remaining ones of the unlabeled d...