Abstract: Systems, apparatuses, methods, and computer program products are disclosed for determining a value corresponding to a composite object. Paths are determined based on initial values of underlying items of the composite object and random numbers. A DNN is trained by determining a final value for each path based on a final set of items corresponding to the path at the final time, iterating the value backward in time using a non-linear generator function from the final value to an initial value, defining a set of initial values comprising the initial value determined for each path and determining a statistical measure based on the set of initial values, and modifying parameters of the DNN based on the statistical measure. Value information comprising the value for the composite object at one or more times is determined based on output of the DNN. The value information is provided such that a user computing device receives it.

Abstract: A system and method for automatically generating deep neural network architectures for time series prediction. The system includes a processor for: receiving a prediction context associated with a current use case; based on the associated prediction context, selecting a prediction model network configured for a current use case time series prediction task; replicating the selected prediction model network to create a plurality of candidate prediction model networks; inputting a time series data to each of the plurality of the candidate prediction model network; train, in parallel, each respective candidate prediction model network of the plurality with the input time series data; modifying each of the plurality of the candidate prediction model network by applying a respective different set of one or more model parameters while being trained in parallel; and determine a fittest modified prediction model network for solving the current use case time series prediction task.

Abstract: A method of pruning a pre-trained model comprises the steps of (a) constructing a stochastic super net and (b) training the stochastic super net to determine a particular candidate block selection that provides an optimal level of sparsity for each of the layers based upon a cost function. The stochastic super net generally represents a layer-wise search space with a fixed macro-architecture. A number of layers of the macro-architecture and input/output dimensions of each of the layers of the macro-architecture are essentially the same as the pre-trained model. Each layer comprises a plurality of candidate blocks. A sparsity of each of the candidate blocks in a respective layer is different. A training dataset used to train the pre-trained model is used to train the stochastic super net.

Abstract: A computer implemented method includes distributing a plurality of prediction models, where each of a plurality of clients initially includes at least one associated prediction model from the plurality of prediction models, among all of the plurality of clients to provide each of the plurality of clients with each of the plurality of prediction models. The plurality of prediction models is evaluated on at least a portion of a local dataset resident on each of the plurality of clients to output a quantification indicating how each of the prediction models fit at least the portion of the local dataset of each of the plurality of clients. An ensemble model is generated by applying weights to each of the plurality of prediction models based on a value, a gradient, and a Hessian matrix of a user-defined objective.

Abstract: Non-limiting examples of the present disclosure describe analysis of venue data and prediction of trendiness of venues based on analyzing the venue data. As an example, one or more new venues are determined. The one or more new venues are determined by identification of a venue that has venue data existing for a period of time less than or equal to a predetermined time threshold. The venue data associated with the one or more new venues is evaluated. A predicted popularity for the one or more new venues is generated based on evaluation of the venue data. The generated predicted popularity may be provided to a processing device. In some examples, a ranked list of the one or more new venues is generated. The ranked list may display the one or more venues in a ranked order according to the generated predicted popularity. Other examples are also described.

Abstract: Techniques for quantum entanglement forging for quantum simulations are presented. A decomposer component can decompose a weakly entangled variational state into respective local components of the weakly entangled variational state, wherein the respective local components describe respective tensor product states. A quantum computing simulator component can perform respective quantum simulations of the respective local components of the weakly entangled variational state, and can determine respective portions of variational energy contributed by the respective tensor product states associated with the respective local components based on the respective quantum simulations of the respective local components of the weakly entangled variational state. An energy determination component can determine a variational energy associated with the weakly entangled variational state based on the respective portions of the variational energy contributed by the respective tensor product states.

Abstract: A method, workflow and system for automated classification of rock cuttings based on two tasks: (i) pixel-wise labeling of rock cutting images based on a convolutional neural network-based edge detection scheme; and (ii) training a general purpose deep learning model for classification of heterogeneous rock cutting mixtures based on the underlying texture.

Abstract: Computer hardware and/or software that performs the following operations: (i) updating a machine learning model by synchronously applying, to the machine learning model, a first set of training results received from a set of trainers having respective training datasets; (ii) receiving, from one or more trainers of the set of trainers, a first set of metrics pertaining to at least some of the training results of the first set of training results; and (iii) based, at least in part, on the first set of metrics, determining to subsequently update the machine learning model via asynchronous application of subsequent training results received from respective trainers of the set of trainers.

Abstract: Using a training portion of a dataset, a set of component parameters comprising parameters of a component of an object detection model are trained. Using the trained set of component parameters, a set of backbone component weights comprising weights of component types in a backbone portion of the object detection model are trained. Using the trained set of component parameters, a set of backbone link weights comprising weights of links within the backbone portion are trained. Using the trained set of component parameters, a set of head component weights comprising weights of component types in a head portion of the object detection model are trained. Using the trained sets of component parameters, backbone component weights, backbone link weights, and head component weights, a trained object detection model is configured and trained to perform object detection.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for reinforcement learning in agent training. Agents may be trained using reinforcement learning. The methods, systems, and apparatus include actions of obtaining scene grammars, obtaining a reference video of a reference agent performing a task, generating environments from the scene grammars, determining that behavior of a sample agent shown in a particular environment of the environments matches behavior of the reference agent, storing an indication that the particular environment trains agents to perform the task, determining to train a new agent to perform the task, identifying the particular environment based on the indication, and training the new agent to perform the task in the particular environments identified.

Abstract: According to one embodiment, a method, computer system, and computer program product for training a cognitive model that involves one or more decision trees as base learners is provided. The present invention may include constructing, by a tree building algorithm, the one or more decision trees, wherein the constructing further comprises associating one or more training examples with one or more leaf nodes of the one or more decision trees and iteratively running a breadth-first search tree builder on one or more of the decision trees to perform one or more tree building operations; and training the cognitive model based on the one or more decision trees.

Abstract: The present disclosure relates to generating proposed digital actions in high-dimensional action spaces for client devices utilizing reinforcement learning models. For example, the disclosed systems can utilize a supervised machine learning model to train a latent representation decoder to determine proposed digital actions based on latent representations. Additionally, the disclosed systems can utilize a latent representation policy gradient model to train a state-based latent representation generation policy to generate latent representations based on the current state of client devices. Subsequently, the disclosed systems can identify the current state of a client device and a plurality of available actions, utilize the state-based latent representation generation policy to generate a latent representation based on the current state, and utilize the latent representation decoder to determine a proposed digital action from the plurality of available actions by analyzing the latent representation.