Various aspects of the disclosure relate to monitoring a physical location to determine and/or predict anomalous activities. One or more machine learning algorithms may be used to analyze inputs from one or more sensors, cameras, audio recording equipment, and/or any other types of sensors to detect anomalous measurements/patterns. Notifications may be sent one or more devices in a network based on the detection.

In an approach for explaining a theorem proving model, a processor predicts a truth value of a query through a pre-trained theorem proving model, based on the query and one or more facts and rules in a knowledge base. A processor ranks the one or more facts and rules according to contribution, calculated in a pre-defined scoring method, made to the predicted truth value of the query. A processor generates a proof of the predicted truth value, wherein the proof is one or more logical steps that demonstrate the predicted truth value in a natural language. A processor outputs the proof.

A neural network classifies an input signal. For example, an accelerometer signal may be classified to detect human activity. In a first convolutional layer, two-valued weights are applied to the input signal. In a first two-valued function layer coupled at input to an output of the first convolutional layer, a two-valued function is applied. In a second convolutional layer coupled at input to an output of the first two-valued functional layer, weights of the second convolutional layer are applied. In a fully-connected layer coupled at input to an output of the second convolutional layer, two-valued weights of the fully connected layer are applied. In a second two-valued function layer coupled at input to an output of the fully connected layer, a two-valued function of the second two-valued function layer is applied. A classifier classifies the input signal based on an output signal of second two-valued function layer.

An information processing apparatus according to an aspect of the present invention includes an information processing circuit configured to generate a finite state machine based on a predetermined matching condition with respect to sequence data of an event that is input to the information processing apparatus; to process the sequence data so as to substantially remove data that does not match the matching condition from the sequence data; and to output the processed sequence data.

An information processing apparatus according to an aspect of the present invention includes an information processing circuit configured to generate a finite state machine based on a predetermined matching condition with respect to sequence data of an event that is input to the information processing apparatus; to process the sequence data so as to substantially remove data that does not match the matching condition from the sequence data; and to output the processed sequence data.

Calls received by a data center that are associated with a request are monitored. Features are subsequently extracted from the monitored calls so that a machine learning model may use such features to determine that the request will cause the data center to malfunction. The machine learning model can be trained using data derived from a transaction log for the data center. At least one correction action to prevent the data center from malfunctioning can then be initiated in response to such determination. Related apparatus, systems, techniques and articles are also described.

In one approach, a method includes: receiving a login event input from a user, the login event input being associated with a session of the user logging into an account; accessing a machine learning model; and authenticating, with the machine learning model, the user for the account, based at least in part on the login event input. In examples, the login event input comprises one or more items of biometric data associated with the user, an item of the one or more items of biometric data associated being generated by interaction of the user with an input device for logging into the account, and the interaction communicating a login credential of the user. In examples, an item of the one or more items of biometric data associated with the user is keyboard event-related biometric data, or mouse event-related biometric data.

A method of generating an uncertainty score for an output of a Gradient Boosted Decision Tree (GBDT) model is disclosed. The output is a prediction of the GBDT model for an in-use dataset. The method comprises acquiring the GBDT model including a sequence of trees beginning with an initial tree and ending with a last tree, a given one of the sequence of trees having been stochastically built during a current training iteration of the GBDT model, and defining a plurality of sub-sequences of trees in the sequence of trees as sub-models of the GBDT model. During a given in-use iteration of the GBDT model executable for the in-use dataset, the method comprises generating a plurality of sub-outputs using the respective sub-models and generating the uncertainty score using the plurality of sub-outputs, the uncertainty score being indicative of how different sub-outputs from the plurality of sub-outputs are amongst each other.

Various embodiments include methods and devices for training and implementing a tree-based behavior prediction model for use in autonomous vehicle control systems. Some embodiments may include labeling real-world autonomous vehicle run data to indicate an insight of the data, selecting an insight decision tree of the tree-based behavior prediction model for training using the labeled data, training the insight decision tree using the labeled data to classify a probability of an insight associated with the insight decision tree, and updating the tree-based behavior prediction model based on training the insight decision tree. Some embodiments may include selecting an insight decision tree of a tree-based behavior prediction model configured for classifying a probability of an insight associated with the insight decision tree, executing the insight decision tree, and outputting a probability of an insight determined from executing the insight decision tree using the data.

A method checks a plug connection, in which a first plug part is connected to a second plug part. The method determines a force-time curve of a force applied by an assembler during an assembly process of a plug connection. In addition, the method determines characteristic values of a plurality of characteristics of the force-time curve. The method also classifies the plug connection by use of a machine-learned classifier on the basis of the characteristic values of the plurality of characteristics.