Abstract: Systems and methods for artificial intelligence discovered codes are described herein. A method includes obtaining received samples from a receive decoder, obtaining decoded bits from the receive decoder based on the receiver samples, training an encoder neural network of a transmit encoder, the encoder neural network receiving parameters that comprise the information bits, the received samples, and the decoded bits. The encoder neural network is optimized using a loss function applied to the decoded bits and the information bits to calculate a forward error correcting code.

Abstract: A method and system for recommending articles including: receiving a customer request from the customer during the session; generating case data for a case, by an article recommender app; configuring a training set based on the subject and description data of the customer request; identifying, by an artificial intelligence (AI) app, a first pool of articles from a knowledge database; identifying by at least one query, a second pool of articles from a case article database to into a merged pool of articles; assigning, by the AI app, an implicit label to one of the first pool and the second pool of the articles; applying a model derived by the AI app based on customer behavior and a set of features related to the case to classify each article of the merged pool of articles based at least in part on the predicted relevance of the article.

Abstract: A technique is described herein for automatically logging journeys taken by a user, and then automatically classifying the purposes of the journeys. In one implementation, the technique obtains journey data from one or more movement-sensing devices as a user travels from a starting location to an ending location in a vehicle. The technique generates a set of features based on the journey data, and then uses a machine-trainable model (such as a neural network) to make its classification based on the features. The machine-trainable model accepts at least one feature that is based on statistical information regarding at least one aspect of prior journeys that the user has taken. Overall, the technique provides a resource-efficient solution that rapidly provides personalized results to individual respective users. In some implementations, the technique performs its personalization without sharing journey data with a remote server.

Abstract: Cooperative neural networks may be implemented by providing an input to a first neural network including a plurality of first parameters, and updating at least one first parameter based on an output from a recurrent neural network provided with the input, the recurrent neural network including a plurality of second parameters.

Abstract: A deep learning heterogeneous computing method based on layer-wide memory allocation, at least comprises steps of: traversing a neural network model so as to acquire a training operational sequence and a number of layers L thereof; calculating a memory room R1 required by data involved in operation at the ith layer of the neural network model under a double-buffer configuration, where 1?i?L; altering a layer structure of the ith layer and updating the training operational sequence; distributing all the data across a memory room of the CPU and the memory room of the GPU according to a data placement method; performing iterative computation at each said layer successively based on the training operational sequence so as to complete neural network training.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a neural network used to select actions performed by a reinforcement learning agent interacting with an environment. In one aspect, a method includes maintaining a replay memory, where the replay memory stores pieces of experience data generated as a result of the reinforcement learning agent interacting with the environment. Each piece of experience data is associated with a respective expected learning progress measure that is a measure of an expected amount of progress made in the training of the neural network if the neural network is trained on the piece of experience data. The method further includes selecting a piece of experience data from the replay memory by prioritizing for selection pieces of experience data having relatively higher expected learning progress measures and training the neural network on the selected piece of experience data.

Abstract: Estimating Remaining Useful Life (RUL) from multi-sensor time series data is difficult through manual inspection. Current machine learning and data analytics methods, for RUL estimation require large number of failed instances for training, which are rarely available in practice, and these methods cannot use information from currently operational censored instances since their failure time is unknown. Embodiments of the present disclosure provide systems and methods for estimating RUL using time series data by implementing an LSTM-RNN based ordinal regression technique, wherein during training RUL value of failed instance(s) is encoded into a vector which is given as a target to the model. Unlike a failed instance, the exact RUL for a censored instance is unknown. For using the censored instances, target vectors are generated and the objective function is modified for training wherein the trained LSTM-RNN based ordinal regression is applied on an input test time series for RUL estimation.

Abstract: A pooling operation method and a processing device for performing the same are provided. The pooling operation method may rearrange a dimension order of the input data before pooling is performed. The technical solutions provided by the present disclosure have the advantages of short operation time and low energy consumption.

Abstract: A transition control unit detects, when stochastically determining based on a temperature, energy changes, and a random number whether to accept any of a plurality of state transitions according to a relative relationship between the energy changes and thermal excitation energy, a minimum value among the energy changes. The transition control unit then subtracts, when the minimum value is positive, an offset obtained by multiplying the minimum value by a value M that is greater than 0 and less than or equal to 1 from each of the energy changes corresponding to the plurality of state transitions.

Abstract: This present disclosure relates to systems and methods for providing an Adaptive Analytical Behavioral and Health Assistant. These systems and methods may include collecting one or more of patient behavior information, clinical information, or personal information; learning one or more patterns that cause an event based on the collected information and one or more pattern recognition algorithms; identifying one or more interventions to prevent the event from occurring or to facilitate the event based on the learned patterns; preparing a plan based on the collected information and the identified interventions; and/or presenting the plan to a user or executing the plan.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for a projection neural network. In one aspect, a projection neural network is configured to receive a projection network input and to generate a projection network output from the projection network input. The projection neural network includes a sequence of one or more projection layers. Each projection layer has multiple projection layer parameters, and is configured to receive a layer input, apply multiple projection layer functions to the layer input, and generate a layer output by applying the projection layer parameters for the projection layer to the projection function outputs.

Abstract: According to one embodiment, when a predicted trajectory is received, a set of one or more features are extracted from at least some of the trajectory points of the predicted trajectory. The predicted trajectory is predicted using a prediction method or algorithm based on perception data perceiving an object within a driving environment surrounding an autonomous driving vehicle (ADV). The extracted features are fed into a predetermined DNN model to generate a similarity score. The similarity score represents a difference or similarity between the predicted trajectory and a prior actual trajectory that was used to train the DNN model. The similarity score can be utilized to evaluate the prediction method that predicted the predicted trajectory.

Abstract: An information processing device which performs semi-supervised learning is provided with: a dictionary input circuit for acquiring a dictionary, a parameter group used by an identification device; a boundary determination circuit which obtains an identification boundary for the dictionary on the basis of the dictionary, supervised data, and labelled unsupervised data; a labelling circuit which labels the unsupervised data in accordance with the identification boundary; a loss calculation circuit which calculates the sum total of supervised-data loss calculated in accordance with the labels assigned in advance and the labels based on the identification boundary, and unsupervised-data loss calculated such that further from the identification boundary the smaller the loss; a dictionary update circuit which updates the dictionary such that the sum-total loss is reduced; and a dictionary output circuit which outputs the updated dictionary.

Abstract: Some embodiments provide a method for training a machine-trained (MT) network. The method propagates multiple inputs through the MT network to generate an output for each of the inputs. each of the inputs is associated with an expected output, the MT network uses multiple network parameters to process the inputs, and each network parameter of a set of the network parameters is defined during training as a probability distribution across a discrete set of possible values for the network parameter. The method calculates a value of a loss function for the MT network that includes (i) a first term that measures network error based on the expected outputs compared to the generated outputs and (ii) a second term that penalizes divergence of the probability distribution for each network parameter in the set of network parameters from a predefined probability distribution for the network parameter.

Abstract: A method identifies and removes bias from a machine learning model. A user/computer inputs a plurality of input training data into a machine learning system to generate an output of labeled output data. The user/computer evaluates the labeled output data according to a consistency metric to associate the labeled output data with a corresponding consistency assessment. The user/computer selects each labeled output data having a consistency assessment indicating a consistency assessment that is greater than a predetermined threshold to form a labeled output data subset, and then creates additional labeling for the labeled output data subset. The user/computer utilizes the additional labeling to distinguish each labeled training data from labeled output data subset as being mislabeled and biased, and then adjusts the learning machine based on the labeled output data subset being mislabeled and biased.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for transforming patterns of operations on tensors in a computational graph to reduce the memory burden incurred when reshape operations are performed, in particular when deployed to hardware platforms that have vector instructions or vector memory requiring alignment of operands.

Abstract: A convolution operation method and a processing device for performing the same are provided. The method is performed by a processing device. The processing device includes a main processing circuit and a plurality of basic processing circuits. The basic processing circuits are configured to perform convolution operation in parallel. The technical solutions disclosed by the present disclosure can provide short operation time and low energy consumption.

Abstract: Techniques are described for a time series probabilistic forecasting framework that combines recurrent neural networks (RNNs) with a flexible, nonparametric representation of the output distribution. The representation is based on the nonparametric quantile function (instead of, for example, a parametric density function) and is trained by minimizing a continuous ranked probability score (CRPS) derived from the quantile function. Unlike methods based on parametric probability density functions and maximum likelihood estimation, the techniques described herein can flexibly adapt to different output distributions without manual intervention. Furthermore, the nonparametric nature of the quantile function provides a significant boost in the approach's robustness, making it more readily applicable to a wide variety of time series datasets.

Abstract: Methods, apparatus, systems and articles of manufacture to provide an image modality maintenance smart find are disclosed. The example method includes identifying an imaging device based on an image of the imaging device. The method further includes determining at least one of a make, a model, or a modality of the imaging device based on the identification. The method further includes identifying a fleet of imaging devices corresponding to the imaging device. The method further includes storing error information corresponding to an issue of the imaging device in correspondence with the fleet of imaging devices and update a model corresponding to the fleet based on the error information. The method further includes deploying the model to a device of a technician.

Abstract: Embodiments employ an inference method for neural networks that enforces deterministic constraints on outputs without performing post-processing or expensive discrete search over the feasible space. Instead, for each input, the continuous weights are nudged until the network's unconstrained inference procedure generates an output that satisfies the constraints. This is achieved by expressing the hard constraints as an optimization problem over the continuous weights and employing backpropagation to change the weights of the network. Embodiments optimize over the energy of the violating outputs; since the weights directly determine the output through the energy, embodiments are able to manipulate the unconstrained inference procedure to produce outputs that conform to global constraints.