Abstract: Some embodiments provide a non-transitory machine-readable medium that stores a program. The program retrieves a data object associated with a defined category. The program further determines a subcategory of the defined category associated with the data object. The program also determines a set of machine learning models based on the subcategory of the defined category associated with the data object. The program further uses the set of machine learning models to determine a first set of data values. Based on the set of data values, the program also derives a second set of data values associated with the data object.

Abstract: Embodiments of the present disclosure pertain to character recognition using neural networks. In one embodiment, the present disclosure includes a computer implemented method comprising processing a plurality of characters using a first recurrent machine learning algorithm. The first recurrent machine learning algorithm sequentially produces a first plurality of internal arrays of values. The first plurality of internal arrays of values are stored to form a stored plurality of arrays of values. The stored plurality of arrays of values are multiplied by a plurality of attention weights to produce a plurality of selection values. An attention array of values is generated from the stored arrays based on the selection values. The attention array of values is processed using a second recurrent machine learning algorithm, the second recurrent machine learning algorithm produces a recognized character sequence.

Abstract: A system and method for modeling information security risk to an enterprise are disclosed. The method includes providing multiple input media, each of which forms a vector of risk severity in a dimension characterizing the information security risk. Each vector is of a dimension distinct from that of each other vector. The input media are user interactive for providing input to a computer in a network environment. The input includes data corresponding to the magnitude and dimension of each of the vectors. Upon receiving the input, the vectors are processed to output a model of the information security risk. Each risk can be modeled from the perspective of at least two dimensions, one related to a technical exploitation aspect of the risk, and the other related to a risk aspect associated with business impact. The input media can be a web based application.