Systems and methods for mapping neuronal circuitry in accordance with embodiments of the invention are illustrated. One embodiment includes a method for generating a neuronal shape graph, including obtaining functional brain imaging data from an imaging device, where the functional brain imaging data includes a time-series of voxels describing neuronal activation over time in a patient's brain, lowering the dimensionality of the functional brain imaging data to a set of points, where each point represents the brain state at a particular time in the timeseries, binning the points into a plurality of bins, clustering the binned points, and generating a shape graph from the clustered points, where nodes in the shape graph represent a brain state and edges between the nodes represent transitions between brain states.

Example circuit implementations of Szegedy's quantization of the Metropolis-Hastings walk are presented. In certain disclosed embodiments, a quantum walk procedure of a Markov chain Monte Carlo simulation is implemented in which a quantum move register is reset at every step in the quantum walk. In further embodiments, a quantum walk procedure of a Markov chain Monte Carlo simulation is implemented in which an underlying classical walk is obtained using a Metropolis-Hastings rotation or a Glauber dynamics rotation. In some embodiments, a quantum walk procedure is performed in the quantum computing device to implement a Markov Chain Monte Carlo method; during the quantum walk procedure, an intermediate measurement is obtained; and a rewinding procedure of one or more but not all steps of the quantum walk procedure is performed if the intermediate measurement produces an incorrect outcome.

Described is a system for detecting and correcting perception errors in a perception system. In operation, the system generates a list of detected objects from perception data of a scene, which allows for the generation of a list of background classes from backgrounds in the perception data associated with the list of detected objects. For each detected object in the list of detected objects, a closest background class is identified from the list of background classes. Vectors can then be used to determine a semantic feature, which is used to identify axioms. An optimal perception parameter is then generated, which is used to adjust perception parameters in the perception system to minimize perception errors.

A computer-implement method comprises: training a classifier with labeled data from a dataset; classifying, by the trained classifier, unlabeled data from the dataset; providing, by the classifier to a policy gradient, a reward signal for each data/query pair; transferring, by the classifier to a ranker, learning; training, by the policy gradient, the ranker; ranking data from the dataset based on a query; and retrieving data from the ranked data in response to the query.

The disclosure relates to systems and methods for evaluating a blood vessel. The method includes receiving image data of the blood vessel acquired by an image acquisition device, and predicting, by a processor, blood vessel condition parameters of the blood vessel by applying a deep learning model to the acquired image data of the blood vessel. The deep learning model maps a sequence of image patches on the blood vessel to blood vessel condition parameters on the blood vessel, where in the mapping the entire sequence of image patches contribute to the blood vessel condition parameters. The method further includes providing the blood vessel condition parameters of the blood vessel for evaluating the blood vessel.

A method is for determining a processing sequence for processing an image, the processing sequence including a plurality of algorithms, each respective algorithm of the plurality of algorithms being configured to perform an image processing process on the image to generate a respective output. In an embodiment, the method includes determining one or more required outputs from the processing sequence; and determining, using a data processing system, the processing sequence based on the one or more required outputs determined, the data processing system being configured based on sequences previously determined.

Learning latent variable models with deep top-down architectures typically requires inferring latent variables for each training example based on posterior distribution of these latent variables. The inference step relies on either time-consuming long-run Markov chain Monte Carlo (MCMC) sampling or a separate inference model for variational learning. Embodiments of a short-run MCMC, such as a short-run Langevin dynamics, are used herein as an approximate flow-based inference engine. Bias existing in the output distribution of non-convergent short-run Langevin dynamics may be corrected by optimal transport (OT), which aims at transforming the biased distribution produced by finite-step MCMC to the prior distribution with a minimum transport cost. Experiment results verify the effectiveness of the OT correction for the short-run MCMC, and demonstrate that latent variable models trained by the disclosed strategy performed better than the variational auto-encoder in terms of image reconstruction, generation and anomaly detection.

The present invention belongs to the field of information technology, involving the techniques of fuzzy modeling, reinforcement learning, parallel computing, etc. It is a method combining granular computing and reinforcement learning for construction of long-term prediction interval and determination of its structure. Adopting real industrial data, the present invention constructs multi-layer structure for assigning information granularity in unequal length and establishes corresponding optimization model at first. Then considering the importance of the structure on prediction accuracy, Monte-Carlo method is deployed to learn the structural parameters. Based on the optimal multi-layer granular computing structure along with implementing parallel computing strategy, the long-term prediction intervals of gaseous generation and consumption are finally obtained. The proposed method exhibits superiority on accuracy and computing efficiency which satisfies the demand of real-world application. It can be also generalized to apply on other energy systems in steel industry.

A method is provided for detecting a higher-level action from one or more trajectories of real states. The trajectories are based on an experts' action demonstration. The method trains predictors to predict future states. Each predictor has a different duration of the higher-level action to be detected. The method predicts, using the predictors, the future states using past ones of the real states in the one or more trajectories as inputs for the predictors. The method determines if a match exists between any of the future states relative to a real future state with a corresponding same duration from the one or more trajectories. The method outputs a pair that includes the matching one of the future states as a prediction input and the real future state with the corresponding same duration from the one or more trajectories as the higher-level action corresponding thereto, responsive to the match existing.

A method may include generating, based a context-free grammar, a sample forming a corpus. The context-free grammar may include production rules for replacing a first nonterminal symbol with a second nonterminal symbol and/or a terminal symbol. The sample may be generated by rewriting recursively a first text string to form a second text string associated with the sample. The first text string may be rewritten by applying the production rules to replace nonterminal symbols included in the first text string until no nonterminal symbols remain in the first text string. A machine learning model may be trained, based on the corpus, to process a natural language. Related methods and articles of manufacture are also disclosed.