The present disclosure provides systems and methods for the management and/or evaluation of machine-learned models based on locally logged data. In one example, a user computing device can obtain a machine-learned model (e.g., from a server computing device) and can evaluate at least one performance metric for the machine-learned model. In particular, the at least one performance metric for the machine-learned model can be evaluated relative to data that is stored locally at the user computing device. The user computing device and/or the server computing device can determine whether to activate the machine-learned model on the user computing device based at least in part on the at least one performance metric. In another example, the user computing device can evaluate a plurality of machine-learned models against locally stored data. At least one of the models can be selected based on the evaluated performance metrics.

Robotic visualization systems and methods include running and analyzing perception algorithms and models for robotic visualization systems on multiple computing platforms to obtain a successful complete an object processing request.

A device may obtain, for a set of transactions, a set of transaction values associated with a particular industry. The device may determine one or more sample statistical distributions for a probabilistic transaction model by using one or more machine learning techniques. The one or more sample statistical distributions may be similar to one or more actual statistical distributions that are associated with the set of transaction values. The device may generate simulated transaction information using the probabilistic transaction model. The device may perform one or more actions after generating the simulated transaction information.

A device may obtain, for a set of transactions, a set of transaction values associated with a particular industry. The device may determine one or more sample statistical distributions for a probabilistic transaction model by using one or more machine learning techniques. The one or more sample statistical distributions may be similar to one or more actual statistical distributions that are associated with the set of transaction values. The device may generate simulated transaction information using the probabilistic transaction model. The device may perform one or more actions after generating the simulated transaction information.

A method includes receiving a plurality of drilling parameters from a drilling operation, wherein the plurality of drilling parameters. The drilling parameters include a cuttings bed height and a friction factor between a drill string and a wellbore. The method further includes applying the plurality of drilling parameters to a friction model. The friction model utilizes a function of the cuttings bed height to determine a comprehensive friction factor. The comprehensive friction factor is applied to the plurality of drilling parameters to determine a required torque or hook load of the drill string. The method further includes providing an indication of a stuck pipe event.

An example apparatus includes a matrix processor in circuit with a probability generator to determine a first matrix representative of element-wise multiplication between a constraint matrix and a first transpose matrix of the estimated demographic impression distribution, the constraint matrix based on the reference demographic impression distribution and determine a second matrix by multiplying the first matrix with a second transpose matrix of the constraint matrix. The apparatus further includes an error determiner in circuit with the matrix processor, the error determiner to determine an error indicator value based on the second matrix, the error indicator value indicative of an error associated with the estimated demographic impression distribution, and a probability generator to generate, in response to the error indicator value satisfying a threshold, an accuracy-improved demographic impression distribution.

A method for determining a torsional moment of a wheel set shaft of a rail vehicle during the operation of the rail vehicle is used for a wheel set shaft having two wheels secured to ends of the shaft for rolling on two rails. A model is used to calculate a torsional moment which acts on the wheel set shaft, and the model is based on a torsional vibration of the wheel set shaft at a specified slip action point. The torsional moment acting on the wheel set shaft is ascertained based on the energy of the torsional vibration of the wheel set shaft at the slip action point and based on a damping energy which acts on the torsional vibration of the wheel set shaft.

A method for generating a category clustering data via a code division multiple access (CDMA) structure comprises the steps of: dividing a dataset to generate dataset categories; and generating the category clustering data via the CDMA structure processing the dataset categories according to the dataset categories; wherein the dataset includes a plurality of variable sequences; wherein dividing the dataset includes the step of: using a variable slope of each of the variable sequences to perform a segment division on a corresponding variable sequence to generate a plurality of segments; and using a distance, an angle and a slope to perform an affinity group on the variable sequences to generate a plurality of groups. The method for generating the category clustering data via the CDMA structure can make the category clustering data to have a very high similarity.

A method for generating a category clustering data via a code division multiple access (CDMA) structure comprises the steps of: dividing a dataset to generate dataset categories; and generating the category clustering data via the CDMA structure processing the dataset categories according to the dataset categories; wherein the dataset includes a plurality of variable sequences; wherein dividing the dataset includes the step of: using a variable slope of each of the variable sequences to perform a segment division on a corresponding variable sequence to generate a plurality of segments; and using a distance, an angle and a slope to perform an affinity group on the variable sequences to generate a plurality of groups. The method for generating the category clustering data via the CDMA structure can make the category clustering data to have a very high similarity.

Systems and methods are provided for automatically scoring a constructed response. The constructed response is processed to generate a plurality of numerical vectors that is representative of the constructed response. A model is applied to the plurality of numerical vectors. The model includes an input layer configured to receive the plurality of numerical vectors, the input layer being connected to a following layer of the model via a first plurality of connections. Each of the connections has a first weight. An intermediate layer of nodes is configured to receive inputs from an immediately-preceding layer of the model via a second plurality of connections, each of the connections having a second weight. An output layer is connected to the intermediate layer via a third plurality of connections, each of the connections having a third weight. The output layer is configured to generate a score for the constructed response.