Techniques are provided for increasing the accuracy of automated classifications produced by a machine learning engine. Specifically, the classification produced by a machine learning engine for one photo-realistic image is adjusted based on the classifications produced by the machine learning engine for other photo-realistic images that correspond to the same portion of a 3D model that has been generated based on the photo-realistic images. Techniques are also provided for using the classifications of the photo-realistic images that were used to create a 3D model to automatically classify portions of the 3D model. The classifications assigned to the various portions of the 3D model in this manner may also be used as a factor for automatically segmenting the 3D model.

A mechanism is provided in a data processing system comprising a processor and a memory, the memory comprising instructions executed by the processor to specifically configure the processor to implement a statistical model tool for providing insight into decision making. The statistical model tool applies the statistical model to an input image to generate an original classification probability. An image modification component executing within the statistical model tool iterative modifies each portion of the input image to generate a modified image. The statistical model tool applies the statistical model to the modified image to generate a new classification probability for each portion of the input image. A compare component executing in the statistical model tool compares each new classification probability to the original classification probability to generate a respective probability distance. A distance map generator executing within the statistical model tool generates a distance map data structure based on the probability distances. The distance map data structure represents an impact each portion of the input image has on determining classification probability by the statistical model.

A mechanism is provided in a data processing system comprising a processor and a memory, the memory comprising instructions executed by the processor to specifically configure the processor to implement a statistical model tool for providing insight into decision making. The statistical model tool applies the statistical model to an input image to generate an original classification probability. An image modification component executing within the statistical model tool iterative modifies each portion of the input image to generate a modified image. The statistical model tool applies the statistical model to the modified image to generate a new classification probability for each portion of the input image. A compare component executing in the statistical model tool compares each new classification probability to the original classification probability to generate a respective probability distance. A distance map generator executing within the statistical model tool generates a distance map data structure based on the probability distances. The distance map data structure represents an impact each portion of the input image has on determining classification probability by the statistical model.

The user is to be informed of the reliability of the machine-learned model based on the current input relative to the training data used to train the model or the model itself. In a medical situation, the data for a current patient is compared to the training data used to train a prediction model and/or to a decision function of the prediction model. The comparison indicates the training content relative to the current patient, so provides a user with information on the reliability of the prediction for the current situation. The indication deals with the variation of the data of the current patient from the training data or relative to the prediction model, allowing the user to see how well trained the predication model is relative to the current patient. This indication is in addition to any global confidence output through application of the prediction model to the data of the current patient.

An apparatus for calibrating output from an image classifier. The apparatus has an image classifier trained to compute, from an image, confidence values for each of a plurality of skin conditions potentially depicted in the image. The apparatus has a processor to compute a probability score for at least one skin condition by adjusting an associated confidence value using information from an incidence corrected data set which is a plurality of images resampled according to data about an incidence of the skin condition in a population from which the image was captured.

A method may include receiving a number of images to train a first neural network, masking a portion of each of the images and inputting the masked images to the first neural network. The method may also include generating, by the first neural network, probable pixel values for pixels located in the masked portion of each of the plurality of images, forwarding the images including the probable pixel values to a second neural network and determining, by the second neural network, whether each of the probable pixel values is contextually suitable. The method may further include identifying pixels in each of the plurality of images that are not contextually suitable.

A method to balance computation accuracy and energy consumption, including: programming thresholds voltages of first memory cells to store first weight matrices representative of a first artificial neural network; programming thresholds voltages of second memory cells to store second weight matrices representative of a second artificial neural network smaller than the first artificial neural network, where both the first artificial neural network and the second artificial neural network are operable to provide at least one common functionality in processing each of the inputs; selecting configurations of using the first memory cells, or the second memory cells, or both in processing a sequence of inputs; and performing, according to the configurations, operations of multiplication and accumulation using the first memory cells, and the second memory cells in computations of the first artificial neural network and the second artificial neural network in processing the sequence of the inputs.

The disclosed technology is generally directed to identifying media documents embedded within other media documents. In one example of the technology, source fingerprints are generated from input images using a source machine-learning model. The input images are derived from the media documents. Target fingerprints are generated from the input images using a target machine-learning model. The source machine-learning model includes a first neural network. The target machine-learning model includes a second neural network that is different from the first neural network. The source machine-learning model was trained in parallel with the target machine-learning model. Candidate media-document pairs from the media documents are determined based on the source fingerprints and the target fingerprints. Each candidate media-document pair includes a media document that is a candidate for being embedded in another media document.

To provide a robust information processing system against attacks by Adversarial Example. A neural network model 608, a latent space database 609 for storing position information in a latent space in which first output vectors, which are output vectors of a predetermined hidden layer included in the neural network model, are embedded concerning input data used for learning of the neural network model, and an inference control unit 606 for making an inference using the neural network model and the latent space database are provided. The inference control unit infers the input data based on the positional relationship between the second output vector, which is an output vector of the predetermined hidden layer concerning input data to be inferred, and the first output vectors in said latent space.

The pose and shape of a human body may be recovered based on joint location information associated with the human body. The joint location information may be derived based on an image of the human body or from an output of a human motion capture system. The recovery of the pose and shape of the human body may be performed by a computer-implemented artificial neural network (ANN) trained to perform the recovery task using training datasets that include paired joint location information and human model parameters. The training of the ANN may be conducted in accordance with multiple constraints designed to improve the accuracy of the recovery and by artificially manipulating the training data so that the ANN can learn to recover the pose and shape of the human body even with partially observed joint locations.