Computer-implemented machines, systems and methods for providing insights about a machine learning model, the machine learning model trained, during a training phase, to learn patterns to correctly classify input data associated with risk analysis. Analyzing one or more features of the machine learning model, the one or more features being defined based on one or more constraints associated with one or more values and relationships and whether said one or more values and relationships satisfy at least one of the one or more constraints. Displaying one or more visual indicators based on an analysis of the one or more features and training data used to train the machine learning model, the one or more visual indicators providing a summary of the machine learning model's performance or efficacy.

Techniques are provided for extracting anomaly related rules from organizational data. One method comprises obtaining anomaly analysis data integrated from multiple data sources of an organization, wherein the multiple data sources comprise at least one set of labeled anomaly data related to anomalous transactions; extracting features from the integrated anomaly analysis data that correlate with an indication of an anomaly; training multiple machine learning models using the extracted features, where the machine learning models are trained using different combinations of the extracted features; evaluating a performance of the trained machine learning models; and extracting rules from the trained machine learning models based on the performance, wherein the extracted rules are used to classify transactions as anomalous. The trained machine learning models comprise a decision tree comprising paths to an anomaly classification. The extracted rules are optionally in a human-readable format.

Methods, apparatus, systems and articles of manufacture to defend against adversarial machine learning are disclosed. An example apparatus includes a model trainer to train a classification model based on files with expected classifications; and a model modifier to select a convolution layer of the trained classification model based on an analysis of the convolution layers of the trained classification model; and replace the convolution layer with a tree-based structure to generate a modified classification model.

Approaches for private and interpretable machine learning systems include a system for processing a query. The system includes one or more teacher modules for receiving a query and generating a respective output, one or more privacy sanitization modules for privacy sanitizing the respective output of each of the one or more teacher modules, and a student module for receiving a query and the privacy sanitized respective output of each of the one or more teacher modules and generating a result. Each of the one or more teacher modules is trained using a respective private data set. The student module is trained using a public data set. In some embodiments, human understandable interpretations of an output from the student module is provided to a model user.

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 facilitating causal reasoning for explanation of model predictions are provided. A system can generate one or more explanations of a machine learning model prediction. The one or more explanations can be based on causal relationships determined between feature data of a set of feature data and based on dataset point samples around a trace associated with the causal relationships.

Explaining the decisions of AI modules to a user is difficult.

The invention relates to methods for providing an explanation dataset (2) for an AI module (31), the methods comprising: receiving a user dataset (20) which specifies at least one input dataset (21) of an AI module (31), wherein the AI module (31) is adapted to compute an output dataset (3) for the input dataset (21), wherein the user dataset (20) comprises at least one target specification (25) which specifies a value of a data item (26) in an output dataset (3) of the AI module (31); loading at least one optimization task (16) which specifies a specific metric (14) and/or a similarity metric (15); computing at least one solution of the at least one optimization task (16) as an explanation dataset (2) taking the user dataset (20) and the AI module (31) into consideration and applying at least one optimization method (17), wherein the AI module (31) is adapted to compute for the explanation dataset (2) an output dataset (3) which comprises the data item (26) specified by the target specification (25); providing the explanation dataset (2) for the AI module (31).

A computer-implemented method comprising, automatically: analyzing a machine learning dataset which comprises multiple datapoints, to deduce constraints on features of the datapoints; generating a first set of CSP (Constraint Satisfaction Problem) rules expressing the constraints; based on a machine learning model which was trained on the dataset, generating a second set of CSP rules that define one or more perturbation candidates among the features of one of the datapoints; formulating a CSP based on the first and second sets of CSP rules; solving the formulated CSP using a solver; and using the solution of the CSP as a counterfactual explanation of a prediction made by the machine learning model with respect to the one datapoint.

A post-processing method, system, and computer program product for post-hoc improvement of instance-level and group-level prediction metrics, including training a bias detector on a payload data that learns to detect a sample in a customer model that has an individual bias greater than a predetermined individual bias threshold value with constraints on a group bias, suggesting, in the run-time, a de-biased prediction based on the selected biased sample by a de-biasing procedure, and an arbiter decides based on user feedback whether to use the de-biased prediction or an original prediction made prior to the de-biasing procedure from the customer model which is then used as an output.

The current document is directed to methods and systems that automatically instantiate complex distributed applications by deploying distributed-application instances across the computational resources of one or more distributed computer systems and that automatically manage instantiated distributed applications. Automatic deployment of multiple instances of a distributed application across computational resources, such as distribution of microservices of a microservice-based application across one or more distributed computer systems, and scaling of instantiated distributed applications are computationally difficult optimization problems that are not amenable to traditional centralized approaches. The current document discloses decentralized, distributed automated methods and systems that instantiate and manage distributed applications. Reinforcement-learning-based agents are installed within the computational resources of one or more distributed computer systems. Distributed-application instances are initially distributed to one or more agents. The agents then exchange distributed-application instances among themselves in order to locally optimize the set of distributed-application instances that they each manage.