Abstract: The present invention relates to dimensionality reduction for machine learning (ML) models. Herein are techniques that individually rank features and combine features based on their rank to achieve an optimal combination of features that may accelerate training and/or inferencing, prevent overfitting, and/or provide insights into somewhat mysterious datasets. In an embodiment, a computer calculates, for each feature of a training dataset, a relevance score based on: a relevance scoring function, and statistics of values, of the feature, that occur in the training dataset. A rank based on relevance scores of the features is calculated for each feature. A sequence of distinct subsets of the features, based on the ranks of the features, is generated. For each distinct subset of the sequence of distinct feature subsets, a fitness score is generated based on training a machine learning (ML) model that is configured for the distinct subset.

Abstract: Provided are techniques for unified cognition for a virtual personal cognitive assistant. A personal cognitive agent creates an association with an entity and a personalized embodied cognition manager that includes an entity agent registry, wherein the personal cognitive agent comprises a virtual personal cognitive assistant. Selection of a first cognitive assistant agent from a first domain and a second cognitive assistant agent from a second domain are received. Input from the entity is received. A goal based on the input is identified. Unified cognition is provided by coordinating the first cognitive assistant agent of the first domain and the second cognitive assistant agent of the second domain to generate one or more actions to meet the goal. A response is provided to the input with an indication of the goal.

Abstract: Embodiments relate to a neural processor circuit with scalable architecture for instantiating one or more neural networks. The neural processor circuit includes a data buffer coupled to a memory external to the neural processor circuit, and a plurality of neural engine circuits. To execute tasks that instantiate the neural networks, each neural engine circuit generates output data using input data and kernel coefficients. A neural processor circuit may include multiple neural engine circuits that are selectively activated or deactivated according to configuration data of the tasks. Furthermore, an electronic device may include multiple neural processor circuits that are selectively activated or deactivated to execute the tasks.

Abstract: The present disclosure provides an on-device machine learning platform that enables sharing of machine-learned models between applications on a computing device. For example, a first application which has a machine-learned model for a specific task can expose the model to other applications through a system level application programming interface (API) for the other applications to use. Communications using the API can be handled by the on-device machine learning platform. In some implementations, some exchange of resources (e.g., computing resources) can be provided so that the first application is compensated for sharing the machine-learned model (e.g., on a per model invocation basis).

Abstract: Techniques facilitating guiding machine learning models and related components are provided. In one example, a computer-implemented method comprises identifying, by a device operatively coupled to a processor, a set of models, wherein the set of models includes respective model components; determining, by the device, one or more model relations among the respective model components, wherein the one or more model relations respectively comprise a vector of component relations between respective pairwise ones of the model components; and suggesting, by the device, a subset of the set of models based on a mapping of the component relations.

Abstract: A system and method for determining a relationship among data sets. The method includes selecting a first data set from a first table, and a second data set from a second table, forming an inclusion dependency pair of data based on the selected first data set and the selected second data set, determining a resultant of the inclusion dependency pair, and determining a primary key-foreign key relationship between the first data set and the second data set based on the determined resultant.

Abstract: Techniques regarding action detection based on motion in receptive fields of a neural network model are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a motion component that can extract a motion vector from a plurality of adaptive receptive fields in a deformable convolution layer of a neural network model. The computer executable components can also comprise an action detection component that can generate a spatio-temporal feature by concatenating the motion vector with a spatial feature extracted from the deformable convolution layer.

Abstract: Systems and methods can include a method for training a deep convolutional neural network to provide a patient radiation treatment plan, the method comprising collecting patient data from a group of patients, the patient data including at least one image of patient anatomy and a prior treatment plan, wherein the treatment plan includes predetermined machine parameters, and training a deep convolution neural network for regression by using the prior treatment plans and the corresponding collected patient data to determine a new treatment plan.

Abstract: A method of performing operations on a plurality of inputs and a same kernel using a delay time by using a same processor, and a neural network device thereof are provided, the neural network device includes input data including a first input and a second input, and a processor configured to obtain a first result by performing operations between the first input and a plurality of kernels, to obtain a second result by performing operations between the second input, which is received at a time delayed by a first interval from a time when the first input is received, and the plurality of kernels, and to obtain output data using the first result and the second result. The neural network device may include neuromorphic hardware and may perform convolutional neural network (CNN) mapping.

Abstract: A process-implemented neural network method includes obtaining a plurality of kernels and an input feature map; determining a pruning index indicating a weight location where pruning is to be performed commonly within the plurality of kernels; and performing a Winograd-based convolution operation by pruning a weight corresponding to the determined pruning index with respect to each of the plurality of kernels.

Abstract: In one aspect, a computer-implemented automated flow synthesis platform configured to use an artificial intelligence (AI) engine is disclosed and includes a reaction chamber configured to synthesize a sequence, detectors configured to monitor the synthesis of the sequence in the reaction chamber, wherein the synthesis uses an automated flow process, and a computing device communicatively coupled to the detectors. The computing device receives measurements from the one or more detectors, wherein the measurements comprise a spectral profile at each coupling of each amino acid in the sequence, trains, using training data comprising the measurements, machine learning models to determine a synthesizing recipe that enables the sequence to be synthesized, wherein the synthesizing recipe comprises parameters used during the automated flow process to synthesize the sequence, and controls, using the synthesizing recipe, the synthesis of the sequence in the reaction chamber.

Abstract: An Artificial Intelligence (AI) based performance prediction system predicts the performance and behavior of an entity via a complex structure made of iterative and parallel machine learning (ML) model rebuilds with real time data collection. The engine selects a best model at every level and scores the entity to help in predicting the behavior of the entity. Model selection is based on various model selection criteria. The selected model determines a propensity score that indicates a likelihood of the entity migrating from a currently categorized segment to another segment of higher or lower value. Accordingly, messages or alerts with one or more of corrective actions or system enhancements can be transmitted based on the status of the entity via various targeting channels and a post treatment analysis is carried out to find the effect of the corrective actions on the entity.

Abstract: A processor for computing at least one convolution layer of a convolutional neural network is provided, in response to an input event, the convolutional neural network comprising at least one convolution kernel, the convolution kernel containing weight coefficients. The processor comprises at least one convolution module configured to compute the one or more convolution layers, each convolution module comprising a set of elementary processing units for computing the internal value of the convolution-layer neurons that are triggered by the input event, each convolution module being configured to match the weight coefficients of the kernel with certain at least of the elementary processing units of the module in parallel, the number of elementary processing units being independent of the number of neurons of the convolution layer.

Abstract: Systems and/or devices for efficient and intuitive methods for implementing artificial neural networks specifically designed for parallel AI processing are provided herein. In various implementations, the disclosed systems, devices, and methods complement or replace conventional systems, devices, and methods for parallel neural processing that (a) greatly reduce neural processing time necessary to process more complex problem sets; (b) implement neuroplasticity necessary for self-learning; and (c) introduce the concept and application of implicit memory, in addition to explicit memory, necessary to imbue an element of intuition. With these properties, implementations of the disclosed invention make it possible to emulate human consciousness or awareness.

Abstract: Methods and systems for detecting and correcting anomalies include comparing a new time series segment, generated by a sensor in a cyber-physical system, to previous time series segments of the sensor to generate a similarity measure for each previous time series segment. It is determined that the new time series represents anomalous behavior based on the similarity measures. A corrective action is performed on the cyber-physical system to correct the anomalous behavior.

Abstract: Training corpus refinement and incremental updating includes obtaining a training corpus having training samples, refining the training corpus to produce a refined training corpus of data, by applying to the training corpus overlap and noise reduction treatments, maintaining an incremental intelligence database based on filtered user feedback and having candidate feedback training samples to augment the refined training corpus, controlling integration of the candidate feedback training samples with the refined training corpus, and augmenting the refined training corpus with at least some of the candidate feedback training samples to produce an augmented training corpus.

Abstract: A computer system trains a machine learning model to estimate a real-world measurement of a feature of a structure. The machine learning model is trained using a plurality of digital image sets, wherein each image set depicts a particular structure, and a plurality of measurements, wherein each measurement is a measurement of a feature of a particular structure. After the machine learning model is trained, it is used to estimate a measurement of a feature of a particular structure depicted in a particular image set.

Abstract: An information extraction support device includes a receptor, a pattern generator, a data generator, and an output controller. The receptor receives input of a first training example for learning a model used in at least one of extraction of information and extraction of a relation between a plurality of pieces of information, and clue information indicating a basis on which the first training example is used for learning. The pattern generator generates a supervised pattern for generating a training example used for learning, using the first training example and the clue information. The data generator generates a second training example using the supervised pattern. The output controller outputs the second training example and the clue information that is used to generate the supervised pattern having generated the second training example.

Abstract: First parameters of a variational Gaussian process (VGP) (including a positive-definite matrix-valued slack parameter) are initialized and iteratively modified change an objective function comprising an expected log-likelihood for each training data item under a respective Gaussian distribution with a predictive variance depending on the slack parameter. Modifying the first parameters comprises, for each training data item, determining a respective gradient estimator for the expected log-likelihood and modifying the first parameters in dependence on the determined gradient estimators. At an optimal value of the slack parameter, the slack parameter equals an inverse of a covariance matrix for the set of inducing variables, and the objective function corresponds to a variational lower bound of a marginal log-likelihood for a posterior distribution corresponding to the GP prior conditioned on the training data.

Abstract: A neural network system for generating a quality assurance alert is provided. A computing device analyzes a quality assurance profile. A computing device arranges data in neurons of, at least, a first layer of a neural network. A computing device generates a threshold level of prediction of quality assurance based, at least in part, on output data from a neural network. A computing device applies output data from a neural network to a regression profile to determine a probability that a quality assurance issue will occur. A computing device generates a message that includes a quality assurance evaluation based, at least, on the determined probability that the quality assurance issue will occur.