Threat modeling systems include one or more computing device(s) coupled with one or more data store(s), the computing device(s) including a first software application. The data store(s) associate threats with threat model components. One or more mapping files may couple with the data store(s) to correlate the threat model components with visual diagram components of a second software application (“second software diagram components”). A machine learning (ML) algorithm may alternatively or additionally be configured to select, for each second software diagram component, a corresponding threat model component. An import interface initiates reading of a data file generated by the second software application, the data file including a subset of the second software diagram components and defining relationships therebetween. The systems determine, using the ML algorithm and/or the mapping file(s), which threat model components correspond with the subset, and display the corresponding threat model components on one or more user interfaces.

Threat modeling systems include one or more computing device(s) coupled with one or more data store(s), the computing device(s) including a first software application. The data store(s) associate threats with threat model components. One or more mapping files may couple with the data store(s) to correlate the threat model components with visual diagram components of a second software application (“second software diagram components”). A machine learning (ML) algorithm may alternatively or additionally be configured to select, for each second software diagram component, a corresponding threat model component. An import interface initiates reading of a data file generated by the second software application, the data file including a subset of the second software diagram components and defining relationships therebetween. The systems determine, using the ML algorithm and/or the mapping file(s), which threat model components correspond with the subset, and display the corresponding threat model components on one or more user interfaces.

The present disclosure describes devices and methods monitoring a technology environment. In particular, a computing device including a processor with computer readable instructions to access a plurality of indicators (e.g., variables) that have corresponding stored historical information. The indicators are then used to calculate a summed weights table of relative risk for each time period in the past. The summed weights table is then correlated to a target variable (e.g., a variable that documents major issues, incidents, or disruptions that occurred in the technology environment in the past). The correlation coefficient between the summed weights table and the target variable is then used to implement a machine learning algorithm in order to better determine current risk levels (e.g., relative values that predict issues, incidents, or disruption).

Techniques for a machine learning model including the steps of summing values of a set of non-binary input feature values with bias values of a first set of bias values to generate first summed values; binarizing the first summed values; receiving a set of binary weights; performing a convolution operation on the binarized summed values and the set of binary weights to generate convolved output feature values; summing feature values of the convolved output feature values with bias values of a second set of bias values and applying a scale value of a first set of scale values to generate a first set of normalized feature values; summing the first set of normalized feature values with the non-binary input feature values to generate second summed values; and outputting a set of output feature values based on the second summed normalized feature values and non-binary input feature values.

Techniques for a machine learning model including the steps of summing values of a set of non-binary input feature values with bias values of a first set of bias values to generate first summed values; binarizing the first summed values; receiving a set of binary weights; performing a convolution operation on the binarized summed values and the set of binary weights to generate convolved output feature values; summing feature values of the convolved output feature values with bias values of a second set of bias values and applying a scale value of a first set of scale values to generate a first set of normalized feature values; summing the first set of normalized feature values with the non-binary input feature values to generate second summed values; and outputting a set of output feature values based on the second summed normalized feature values and non-binary input feature values.

In various embodiments, a relevance application quantifies how a trained neural network operates. In operation, the relevance application generates a set of input distributions based on a set of input points associated with the trained neural network. Each input distribution is characterized by a mean and a variance associated with a different neuron included in the trained neural network. The relevance application propagates the set of input distributions through a probabilistic neural network to generate at least a first output distribution. The probabilistic neural network is derived from at least a portion of the trained neural network. Based on the first output distribution, the relevance application computes a contribution of a first input point included in the set of input points to a difference between a first output point associated with a first output of the trained neural network and an estimated mean prediction associated with the first output.

In various embodiments, a relevance application quantifies how a trained neural network operates. In operation, the relevance application generates a set of input distributions based on a set of input points associated with the trained neural network. Each input distribution is characterized by a mean and a variance associated with a different neuron included in the trained neural network. The relevance application propagates the set of input distributions through a probabilistic neural network to generate at least a first output distribution. The probabilistic neural network is derived from at least a portion of the trained neural network. Based on the first output distribution, the relevance application computes a contribution of a first input point included in the set of input points to a difference between a first output point associated with a first output of the trained neural network and an estimated mean prediction associated with the first output.

Techniques are presented for accelerating in-memory matrix multiplication operations for a convolution neural network (CNN) inference in which the weights of a filter are stored in the memory of a storage class memory device, such as a ReRAM or phase change memory based device. To improve performance for inference operations when filters exhibit sparsity, a zero column index and a zero row index are introduced to account for columns and rows having all zero weight values. These indices can be saved in a register on the memory device and when performing a column/row oriented matrix multiplication, if the zero row/column index indicates that the column/row contains all zero weights, the access of the corresponding bit/word line is skipped as the result will be zero regardless of the input.

Techniques are presented for accelerating in-memory matrix multiplication operations for a convolution neural network (CNN) inference in which the weights of a filter are stored in the memory of a storage class memory device, such as a ReRAM or phase change memory based device. To improve performance for inference operations when filters exhibit sparsity, a zero column index and a zero row index are introduced to account for columns and rows having all zero weight values. These indices can be saved in a register on the memory device and when performing a column/row oriented matrix multiplication, if the zero row/column index indicates that the column/row contains all zero weights, the access of the corresponding bit/word line is skipped as the result will be zero regardless of the input.

Techniques are described for cognitive defined network management (CDNM) that seek to perform real-time collection and analysis of raw network data from across a disaggregated wireless network and to dynamically orchestrate network management functions substantially in real time, accordingly. For example, a multi-modal artificial intelligence (AI) engine is trained to normalize the heterogeneous raw network data into homogeneous so-called “golden record data.” A repository of historical golden records can be maintained for generating data models for use in training AI network management applications. An orchestrator can operate to directing execution of pre-developed network management workflows based on results obtained from querying the trained AI network management applications with newly received (real-time) golden records.