Abstract: A method and an apparatus to build a machine learning based network model are described. For example, processing circuitry of an information processing apparatus obtains a data processing procedure of a first network model and a reference dataset that is generated by the first network model in the data processing procedure. The data processing procedure includes a first data processing step. Further, the processing circuitry builds a first sub-network in a second network model of a neural network type. The second network model is the machine learning based network model to be built. The first sub-network performs the first data processing step. Then, the processing circuitry performs optimization training on the first sub-network by using the reference dataset.

Abstract: Methods, systems, and computer program products for multi-modal construction of deep learning networks are provided herein. A computer-implemented method includes extracting, from user-provided multi-modal inputs, one or more items related to generating a deep learning network; generating a deep learning network model, wherein the generating includes inferring multiple details attributed to the deep learning network model based on the one or more extracted items; creating an intermediate representation based on the deep learning network model, wherein the intermediate representation includes (i) one or more items of data pertaining to the deep learning network model and (ii) one or more design details attributed to the deep learning network model; automatically converting the intermediate representation into source code; and outputting the source code to at least one user.

Abstract: An example method for facilitating the generation of a control field for a quantum system is provided. The example method may include receiving quantum system experiment input parameters and generating a set of coefficients defining a plurality of controls. The plurality of controls may be provided as a weighted sum of basis functions that include discrete prolate spheroidal sequences. The example method may further include applying a gradient based optimization, synthesizing the plurality of controls, and configuring a waveform generator with the plurality of controls to enable the waveform generator to generate the control field.

Abstract: A computer-implemented method, computer program product, and computer processing system are provided for Hierarchical Reinforcement Learning (HRL) with a target task. The method includes obtaining, by a processor device, a sequence of tasks based on hierarchical relations between the tasks, the tasks constituting the target task. The method further includes learning, by a processor device, a sequence of constraints corresponding to the sequence of tasks by repeating, for each of the tasks in the sequence, reinforcement learning and supervised learning with a set of good samples and a set of bad samples and by applying an obtained constraint for a current task to a next task.

Abstract: A computer-implemented method is provided for machine prediction. The method includes forming, by a hardware processor, a Convolutional Dynamic Boltzmann Machine (C-DyBM) by extending a non-convolutional DyBM with a convolutional operation. The method further includes generating, by the hardware processor using the convolution operation of the C-DyBM, a prediction of a future event at time t from a past patch of time-series of observations. The method also includes performing, by the hardware processor, a physical action responsive to the prediction of the future event at time t.

Abstract: In one embodiment, a service receives machine learning-based generative models from a plurality of distributed sites. Each generative model is trained locally at a site using unlabeled data observed at that site to generate synthetic unlabeled data that mimics the unlabeled data used to train the generative model. The service receives, from each of the distributed sites, a subset of labeled data observed at that site. The service uses the generative models to generate synthetic unlabeled data. The service trains a global machine learning-based model using the received subsets of labeled data received from the distributed sites and the synthetic unlabeled data generated by the generative models.

Abstract: In various examples there is a computer-implemented method performed by a digital twin at a computing device in a communications network. The method comprises: receiving at least one stream of event data observed from the environment. Computing at least one schema from the stream of event data, the schema being a concise representation of the stream of event data. Participating in a distributed inference process by sending information about the schema or the received event stream to at least one other digital twin in the communications network and receiving information about schemas or received event streams from the other digital twin. Computing comparisons of the sent and received information. Aggregating the digital twin and the other digital twin, or defining a relationship between the digital twin and the other digital twin on the basis of the comparison.

Abstract: A computer-implemented method for outputting a data element to a user for an operation by the user to give a label to plural data elements, includes: selecting the data element by either one of a first strategy and a second strategy, the first strategy being a strategy for selecting a data element which has been predicted with a low confidence level, the second strategy being a strategy for selecting a data element which has been predicted with a high confidence level; outputting the selected data element so as for a user to give a label to the selected data element; and switching between the first strategy and the second strategy depending on a progress degree of labeling by the user.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a model using parameter server shards. One of the methods includes receiving, at a parameter server shard configured to maintain values of a disjoint partition of the parameters of the model, a succession of respective requests for parameter values from each of a plurality of replicas of the model; in response to each request, downloading a current value of each requested parameter to the replica from which the request was received; receiving a succession of uploads, each upload including respective delta values for each of the parameters in the partition maintained by the shard; and updating values of the parameters in the partition maintained by the parameter server shard repeatedly based on the uploads of delta values to generate current parameter values.

Abstract: Systems and methods are provided for operating to an initial optimized baseline solution to a multi-objective problem. As the initial optimized baseline solution is determined, some regions, such as local or global maxima, minima, and/or saddle points in the objective space may be mapped. The mapping may be performed by storing mesh chromosomes corresponding to some of the features (e.g., extrema, saddle points, etc.) in the objective space along with the location of those chromosomes within the objective space (e.g., objective values corresponding to each of the objectives). The mesh chromosome may be used in subsequent re-optimization problems, such as with reformulation. Although in a re-optimization the objectives, decision variables, and or objective/constraint models may change, the mesh chromosomes may still provide information and direction for more quickly and/or with reduced resources converge on a re-optimized solution.

Abstract: In an embodiment, a method for optimizing computer machine learning includes receiving an optimization goal. The optimization goal is used to search a database of base option candidates (BOC) to identify matching BOCs that at least in part matches the goal. A selection of a selected base option among the matching BOCs is received. Machine learning prediction model(s) are selected based at least in part on the goal to determine prediction values associated with alternative features for the selected base option, where the model(s) were trained using training data to at least identify weight values associated with the alternative features for models. Based on the prediction values, at least a portion of the alternative features is sorted to generate an ordered list. The ordered list is provided for use in manufacturing an alternative version of the selected base option with the alternative feature(s) in the ordered list.

Abstract: Described is a system for controlling a mobile platform. A neural network that runs on the mobile platform is trained based on a current state of the mobile platform. A Satisfiability Modulo Theories (SMT) solver capable of reasoning over non-linear activation functions is periodically queried to obtain examples of states satisfying specified constraints of the mobile platform. The neural network is then trained on the examples of states. Following training on the examples of states, the neural network selects an action to be performed by the mobile platform in its environment. Finally, the system causes the mobile platform to perform the selected action in its environment.

Abstract: A system and method for training a system for monitoring administration of medication. The method includes the steps of a method for training a medication administration monitoring apparatus, comprising the steps of defining one or more predetermined medications and then acquiring information from one or more data sources of a user administering medication. A first network is trained to recognize a first step of a medication administration sequence, and then a second network is trained to recognize a second step of a medication administration sequence based upon the training of the first network.

Abstract: A method for receiving training data for training a neural network (NN) to perform a machine learning (ML) task and for determining, using the training data, an optimized NN architecture for performing the ML task is described. Determining the optimized NN architecture includes: maintaining population data comprising, for each candidate architecture in a population of candidate architectures, (i) data defining the candidate architecture, and (ii) data specifying how recently a neural network having the candidate architecture has been trained while determining the optimized neural network architecture; and repeatedly performing multiple operations using each of a plurality of worker computing units to generate a new candidate architecture based on a selected candidate architecture having the best measure of fitness, adding the new candidate architecture to the population, and removing from the population the candidate architecture that was trained least recently.

Abstract: An example method includes receiving, by one or more processors, a representation of an utterance spoken at a computing device; identifying, by a first computational agent from a plurality of computational agents and based on the utterance, a multi-element task to be performed, wherein the plurality of computational agents includes one or more first party computational agents and a plurality of third-party computational agents; and performing, by the first computational agent, a first sub-set of elements of the multi-element task, wherein performing the first sub-set of elements comprises selecting a second computational agent from the plurality of computational agents to perform a second sub-set of elements of the multi-element task.

Abstract: According to embodiments, an encoder neural network receives a one-hot representation of a real text. The encoder neural network outputs a latent representation of the real text. A decoder neural network receives random noise data or artificial code generated by a generator neural network from random noise data. The decoder neural network outputs softmax representation of artificial text. The decoder neural network receives the latent representation of the real text. The decoder neural network outputs a reconstructed softmax representation of the real text. A hybrid discriminator neural network receives a first combination of the soft-text and the latent representation of the real text and a second combination of the softmax representation of artificial text and the artificial code. The hybrid discriminator neural network outputs a probability indicating whether the second combination is similar to the first combination. Additional embodiments for utilizing latent representation are also disclosed.

Abstract: Techniques are provided for evolutionary computer-based optimization and artificial intelligence systems, and include receiving first and second candidate executable code (with ploidy of at least two and one, respectively) each selected at least in part based on a fitness score. If the desired ploidy of the resultant executable code is one, then the first candidate executable code and the second candidate executable code are combined to produce haploid executable code. If the desired ploidy is two, then the first candidate executable code and the second candidate executable code are combined to produce diploid executable code. A fitness score is determined for the resultant executable code, and a determination is made whether the resultant executable code will be used as a future candidate executable code based at least in part on the third fitness score. If an exit condition is met, then the resultant executable code is used as evolved executable code.

Abstract: A method of controlling an operational system by a rules management system comprising a processor and a memory, and a computing apparatus comprising a processor and a memory are provided. The processor is programmed to execute rules from a rules repository stored on a memory in response to a request. The computing apparatus further comprises a high rules repository storing one or more high level rules, wherein each high level rule, when executed by the processor, modifies the effect of execution of one or more rules Rm in the rules repository; and a high rules conditions module that when executed by the processor identifies and executes the high level rules that apply to the request.

Abstract: Computer systems and associated methods are disclosed to detect a future change point in time series data used as input to a machine learning model. A forecast for the time series data is generated. In some embodiments, a fitting model is generated from the time series data, and residuals of the fitting model are obtained for respective portions of the data both before and after a potential change point in the future. The change point is determined based on a ratio of residual metrics for the two portions. In some embodiments, data features are extracted from individual segments in the time series data, and the segments are clustered based on their data features. A change point is determined based on a dissimilarity in cluster assignments for segments before and after the point. In some embodiments, when a change point is predicted, an update of the machine learning model is triggered.

Abstract: In general, the disclosure describes techniques for facilitating trust in neural networks using a trusted neural network system. For example, described herein are multi-headed, trusted neural network systems that can be trained to satisfy one or more constraints as part of the training process, where such constraints may take the form of one or more logical rules and cause the objective function of at least one the heads of the trusted neural network system to steer, during machine learning model training, the overall objective function for the system toward an optimal solution that satisfies the constraints. The constraints may be non-temporal, temporal, or a combination of non-temporal and temporal. The constraints may be directly compiled to a neural network or otherwise used to train the machine learning model.