Abstract: Described herein is a machine learning mechanism implemented by one or more computers, the mechanism having access to a base neural network and being configured to determine a simplified neural network by iteratively performing the following set of steps: forming sample data by sampling the architecture of a current candidate neural network; selecting, in dependence on the sample data, an architecture for a second candidate neural network; forming a trained candidate neural network by training the second candidate neural network, wherein the training of the second candidate neural network comprises applying feedback to the second candidate neural network in dependence on a comparison of the behaviours of the second candidate neural network and the base neural network; and adopting the trained candidate neural network as the current candidate neural network for a subsequent iteration of the set of steps.

Abstract: A method of solving an energy minimization problem, the method comprising: a. constructing a graph representative comprising a set of nodes; two terminals; a set of N-links each connecting a pair of the nodes; and a set of T-links each connecting one of the terminals with one of the nodes; b. assigning a capacity to each of the N-links; c. assigning a capacity to each of the T-links; d. determining a first minimum cut/maximum flow solution which partitions the nodes into subsets, each subset containing one of the terminals; e. changing the capacity assigned to at least one of the N-links and at least one of the T-links in response to a change in the problem; and f. dynamically updating the first minimum cut/maximum flow solution determined in step d. to take into account the changed capacities.

Abstract: Systems and methods for object or pattern detection that use a nonlinear support vector (SV) machine are described. In the illustrated and described embodiment, objects or patterns comprising faces are detected. The decision surface is approximated in terms of a reduced set of expansion vectors. In order to determine the presence of a face, the kernelized inner product of the expansion vectors with the input pattern are sequentially evaluated and summed, such that if at any point the pattern can be rejected as not comprising a face, no more expansion vectors are used. The sequential application of the expansion vectors produces a substantial saving in computational time.

Abstract: Systems and methods for object or pattern detection that use a nonlinear support vector (SV) machine are described. In the illustrated and described embodiment, objects or patterns comprising faces are detected. The decision surface is approximated in terms of a reduced set of expansion vectors. In order to determine the presence of a face, the kernelized inner product of the expansion vectors with the input pattern are sequentially evaluated and summed, such that if at any point the pattern can be rejected as not comprising a face, no more expansion vectors are used. The sequential application of the expansion vectors produces a substantial saving in computational time.

Abstract: A multi-layer graph for dense stereo dynamic progranmmiing can improve synthesis of cyclopean virtual images by distinguishing between stereo disparities causes by occlusion and disparities caused by non-fronto-parallel surfaces. In addition, cyclopean virtual image processing may be combined with simulation of three-dimensional translation of a virtual camera to assist in aligning the user's gaze with the virtual camera. Such translation may include without limitation one or more of the following: horizontal (e.g., left and right) translation of the virtual camera, vertical translation (e.g., up and down) of the virtual camera, and axial translation (e.g., toward the subject and away from the subject) of the virtual camera.

Abstract: A multi-layer graph for dense stereo dynamic programming can improve synthesis of cyclopean virtual images by distinguishing between stereo disparities caused by occlusion and disparities caused by non-fronto-parallel surfaces. This distinction can be leveraged to reduce image artifacts, such as “halos”. Distinguishing at least between these two types of disparities allows improved matching of left and right pixel data, which increases the amount of correct pixel information used in constructing the cyclopean virtual image and minimizes occlusion artifacts.