Abstract: A provider network implements a machine learning deployment service for generating and deploying packages to implement machine learning at connected devices. The service may receive from a client an indication of an inference application, a machine learning framework to be used by the inference application, a machine learning model to be used by the inference application, and an edge device to run the inference application. The service may then generate a package based on the inference application, the machine learning framework, the machine learning model, and a hardware platform of the edge device. To generate the package, the service may optimize the model based on the hardware platform of the edge device and/or the machine learning framework. The service may then deploy the package to the edge device. The edge device then installs the inference application and performs actions based on inference data generated by the machine learning model.

Abstract: Systems and methods for modelling prediction errors in path-learning of an autonomous learning agent are provided. The traditional systems and methods provide for machine learning techniques, wherein estimation of errors in prediction is reduced with an increase in the number of path-iterations of the autonomous learning agent. Embodiments of the present disclosure provide for a two-stage modelling technique to model the prediction errors in the path-learning of the autonomous learning agent, wherein the two-stage modelling technique comprises extracting a plurality of fitted error values corresponding to a plurality of predicted actions and actual actions by implementing an Autoregressive moving average (ARMA) technique on a set of prediction error values; and estimating, by implementing a linear regression technique on the plurality of fitted error values, a probable deviation of the autonomous learning agent from each of an actual action amongst a plurality of predicted and actual actions.

Abstract: A method of training a model comprising a generative network mapping a latent vector to a feature vector, wherein weights in the generative network are modelled as probabilistic distributions. The method comprises: a) obtaining one or more observed data points, each comprising an incomplete observation of the features in the feature vector; b) training the model based on the observed data points to learn values of the weights of the generative network which map the latent vector to the feature vector; c) from amongst a plurality of potential next features to observe, searching for a target feature of the feature vector which maximizes a measure of expected reduction in uncertainty in a distribution of said weights of the generative network given the observed data points so far; and d) outputting a request to collect a target data point comprising at least the target feature.

Abstract: Matrix completion and recommendation provision with deep learning is described. A matrix manager system imputes unknown values of incomplete input matrices using deep learning. Unlike conventional techniques, the matrix manager system completes incomplete input matrices using deep learning regardless of whether an input matrix represents numerical, categorical, or a combination of numerical and categorical attributes. To enable a machine-learning model (e.g., an autoencoder) to complete a matrix, the matrix manager system initially encodes the matrix. This involves normalizing known values of numerical attributes and categorically encoding known values of categorical attributes. The matrix manager system performs categorical encoding by replacing information of a given categorical attribute (e.g., an attribute column) with replacement information for each possible value of the attribute (e.g., new columns for each possible value).

Abstract: One embodiment facilitates generating synthetic data objects using a semi-supervised GAN. During operation, a generator module synthesizes a data object derived from a noise vector and an attribute label. The system passes, to an unsupervised discriminator module, the data object and a set of training objects which are obtained from a training data set. The unsupervised discriminator module calculates: a value indicating a probability that the data object is real; and a latent feature representation of the data object. The system passes the latent feature representation and the attribute label to a supervised discriminator module. The supervised discriminator module calculates a value indicating a probability that the attribute label given the data object is real. The system performs the aforementioned steps iteratively until the generator module produces data objects with a given attribute label which the unsupervised and supervised discriminator modules can no longer identify as fake.

Abstract: A method implemented by one or more computing systems includes accessing content viewing data associated with a first user account, wherein the first user account is associated with one or more client devices. The content viewing data includes temporal-based content viewing data. The method further includes determining, using one or more sequence models, a set of content viewing features based on the temporal-based content viewing data, and concatenating the content viewing features into a single computational array. The method further includes providing, through one or more dense layers of a deep-learning model, the single computational array to an output layer of the deep-learning model, and calculating, based on the output layer, one or more probabilities for one or more labels for the first user account. Each label includes a predicted attribute for the first user account.

Abstract: A machine learning module receives inputs comprising attributes of a storage controller, where the attributes affect performance parameters for performing stages and destages in the storage controller. In response to an event, the machine learning module generates, via forward propagation, an output value that indicates whether to fill holes in a track of a cache by staging data to the cache prior to destage of the track. A margin of error is calculated based on comparing the generated output value to an expected output value, where the expected output value is generated from an indication of whether it is correct to fill holes in a track of the cache by staging data to the cache prior to destage of the track. An adjustment is made of weights of links that interconnect nodes of the plurality of layers via back propagation to reduce the margin of error.

Abstract: An online system receives information describing events corresponding to actions associated with a third party system performed by an individual. The received information describes event types and times at which the events occurred. The online system generates nodes of a directed graph associated with the third party system, in which each node corresponds to an event type. For each event, a node count associated with a node corresponding to the event's type is incremented by the online system. Pairs of consecutively occurring events are identified based on times at which the events occurred and an edge describing each transition from one event to another is generated by the online system. The online system determines an edge count for each transition indicating a number of edges describing the transition as well as a sequential order of event types based on one or more node counts and one or more edge counts.

Abstract: A method of performing time series prediction by improper learning comprising calculating a plurality of filters based on a symmetric matrix and generating a mapping term based on a time series input and a function. The method may include comprising iteratively: transforming the function using the calculated plurality of filters; predicting an interim output using the transformed function and the mapping term; computing an error of the interim output based on a known output; and updating the mapping term based on the computed error. The method may include generating the mapping term through iterations over a predetermined interval and performing a time series prediction using the mapping term generated over the iterations.