Methods, apparatus, systems and articles of manufacture for distributed use of a machine learning model are disclosed. An example edge device includes a model partitioner to partition a machine learning model received from an aggregator into private layers and public layers. A public model data store is implemented outside of a trusted execution environment of the edge device. The model partitioner is to store the public layers in the public model data store. A private model data store is implemented within the trusted execution environment. The model partitioner is to store the private layers in the private model data store.

A method of recognizing gestures of a person from at least one image from a monocular camera, e.g. a vehicle camera, includes comp the steps: a) detecting key points of the person in the at least one image, b) connecting the key points to form a skeleton-like representation of body parts of the person, wherein the skeleton-like representation represents a relative position and a relative orientation of the respective body parts of the person, c) recognizing a gesture of the person from the skeleton-like representation of the person, and d) outputting a signal indicating the gesture.

The present disclosure relates to systems, methods, and non-transitory computer readable media for selecting hyper-parameter sets by utilizing a modified Bayesian optimization approach based on a combination of accuracy and training efficiency metrics of a machine learning model. For example, the disclosed systems can fit accuracy regression and efficiency regression models to observed metrics associated with hyper-parameter sets of a machine learning model. The disclosed systems can also implement a trade-off acquisition function that implements an accuracy-training efficiency balance metric to explore the hyper-parameter feature space and select hyper-parameters for training the machine learning model considering a balance between accuracy and training efficiency.

A device may receive a classification model generated based on a set of spectroscopic measurements performed by a first spectrometer. The device may store the classification model in a data structure. The device may receive a spectroscopic measurement of an unknown sample from a second spectrometer. The device may obtain the classification model from the data structure. The device may classify the unknown sample into a Kosher or non-Kosher group or a Halal or non-Halal group based on the spectroscopic measurement and the classification model. The device may provide information identifying the unknown sample based on the classifying of the unknown sample.

Techniques are provided for selection of machine learning algorithms based on performance predictions by trained algorithm-specific regressors. In an embodiment, a computer derives meta-feature values from an inference dataset by, for each meta-feature, deriving a respective meta-feature value from the inference dataset. For each trainable algorithm and each regression meta-model that is respectively associated with the algorithm, a respective score is calculated by invoking the meta-model based on at least one of: a respective subset of meta-feature values, and/or hyperparameter values of a respective subset of hyperparameters of the algorithm. The algorithm(s) are selected based on the respective scores. Based on the inference dataset, the selected algorithm(s) may be invoked to obtain a result. In an embodiment, the trained regressors are distinctly configured artificial neural networks. In an embodiment, the trained regressors are contained within algorithm-specific ensembles. Techniques are also provided for optimal training of regressors and/or ensembles.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for clustering data are disclosed. In one aspect, a method includes the actions of receiving feature vectors. The actions further include, for a subset of the feature vectors, accessing a first label. The actions further include generating a classifier that is configured to associate a given feature vector with a feature vector of the subset of the feature vectors. The actions further include applying the feature vectors that are not included in the subset of the feature vectors to the classifier. The actions further include generating a dissimilarity matrix. The actions further include, based on the dissimilarity matrix, generating a graph. The actions further include, for each node of the graph, determining a second label. The actions further include, based on the second labels and the first labels, determining a training label for each feature vector.

Machine learning adversarial campaign mitigation on a computing device. The method may include deploying an original machine learning model in a model environment associated with a client device; deploying a classification monitor in the model environment to monitor classification decision outputs in the machine learning model; detecting, by the classification monitor, a campaign of adversarial classification decision outputs in the machine learning model; applying a transformation function to the machine learning model in the model environment to transform the adversarial classification decision outputs to thwart the campaign of adversarial classification decision outputs; determining a malicious attack on the client device based in part on detecting the campaign of adversarial classification decision outputs; and implementing a security action to protect the computing device against the malicious attack.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for machine learning. One of the methods includes receiving a document having a plurality of first text strings; extracting the plurality of first text strings from the document; providing the extracted plurality of first text strings to a first machine learning model, wherein the first machine learning model is trained to output a numerical vector representation for each input first text string; providing the output vector representations from the first machine learning model to a second machine learning model, wherein the second machine learning model is trained to output a second text string for each input vector representation; and processing the second text strings to generate an output.

A method and a device for operating a robot are provided. According to an example of the method, information of a first gesture is acquired from a group of gestures of an operator, each gesture from the group of gestures corresponding to an operation instruction from a group of operation instructions. A first operation instruction from the group of operation instructions is obtained based on the acquired information of the first gesture, the first operation corresponding to the first gesture. The first operation instruction is executed.

Differential expression of long non-coding RNAs (lncRNAs) and enhancer RNAs (eRNAs) are used to diagnose diseases including neurological diseases, inflammatory diseases, rheumatic diseases, and autoimmune diseases. Machine learning systems are used to identify lncRNAs or eRNAs having differential expression correlated with certain disease states.