Abstract: In an example, an apparatus comprises a plurality of execution units comprising at least a first type of execution unit and a second type of execution unit and logic, at least partially including hardware logic, to expose embedded cast operations in at least one of a load instruction or a store instruction; determine a target precision level for the cast operations; and load the cast operations at the target precision level. Other embodiments are also disclosed and claimed.

Abstract: Provided is an apparatus configured to determine a common neural network based on a comparison between a first neural network included in a first application program and a second neural network included in a second application program, utilize the common neural network when the first application program or the second application program is executed.

Abstract: A graph neural network (GNN)-based prediction system for total organic carbon (TOC) in shale solves the problem that the existing shale TOC prediction method cannot fully analyze the complex nonlinear relationship between all logging curves and TOC. The prediction system adopts a method including: acquiring and preprocessing a plurality of logging curves of a target well location in a target shale bed to acquire a plurality of standardized logging curves, windowing the plurality of standardized logging curves, and inputting the windowed logging curves and weight matrix into a trained GNN-based TOC prediction network to acquire TOC of the target well location. The prediction system inputs the plurality of logging curves as correlative multi-dimensional dynamic graph data for analysis and can acquire the complex nonlinear relationship between the logging curves and TOC, thus improving the prediction accuracy of TOC.

Abstract: Disclosed herein are techniques for implementing a large fully-connected layer in an artificial neural network. The large fully-connected layer is grouped into multiple fully-connected subnetworks. Each fully-connected subnetwork is configured to classify an object into an unknown class or a class in a subset of target classes. If the object is classified as the unknown class by a fully-connected subnetwork, a next fully-connected subnetwork may be used to further classify the object. In some embodiments, the fully-connected layer is grouped based on a ranking of target classes.

Abstract: At a rule processing unit of an evolving, self-organized machine learning-based resource management service, a rule of a first rule set is applied to a value of a first collected metric, resulting in the initiation of a first corrective action. A set of metadata indicating the metric value and the corrective action is transmitted to a repository, and is used as part of an input data set for a machine learning model trained to generate rule modification recommendations. In response to determining that the corrective actions did not meet a success criterion, an escalation message is transmitted to another rule processing unit.

Abstract: A construction method of human-object-space interaction model based on knowledge graph belongs to the technical field of knowledge graph construction and smart communities and includes steps of: obtaining information from a large number of active and passive sensing devices and thereby building a knowledge base; and fusing perceptual information in the knowledge base, forming entity-relation-entity structured data, and building a general knowledge graph conceptual model with entity-relation attributes. The construction method can overcome technical problems such as difficulty in multi-source information extraction, inability to fuse heterogeneous data, and inability of interaction of human-object-space caused by poor universality of perception technology and complex entity relations in a smart community environment, and provide a method support for monitoring and early warning of dangerous events in the smart community and community environment situational awareness.

Abstract: Embodiments of the invention include computer-implemented methods, computer systems, and computer program products for predicting sensory perception. A non-limiting example of the computer-implemented method includes receiving at a processor a library including a plurality of indexed sensory descriptors. A sensory target descriptor is also received at the processor. The processor is configured to calculate a coefficient matrix based in part on the semantic distance between an indexed sensory descriptor and a sensory target descriptor. The processor is further configured to generate a perceptual descriptor prediction for the sensory target.

Abstract: Mechanisms for generating different lines of questioning based on evaluation of a previous line of questioning are provided. A set of evidential data specifying a plurality of concept entities and input specifying a scenario to be evaluated are received. The scenario specifies a hypothetical link between at least two of the concept entities. A first set of questions corresponding to the at least two information concept entities are evaluated based on the set of evidential data. Based on results of evaluating the first set of questions, a second set of questions is automatically generated to further expand upon and investigate the results of evaluating the first set of questions. The second set of questions are processed and an indication of the scenario and a corresponding measure of support for or against the scenario being a valid scenario is output.

Abstract: Embodiments of the present invention provide a computer-implemented method for performing unsupervised feature representation learning for text data. The method generates reference text data having a set of random text sequences, in which each text sequence of set of random text sequences is of a random length and comprises a number of random words, and in which each random length is sampled from a minimum length to a maximum length. The random words of each text sequence in the set are drawn from a distribution. The method generates a feature matrix for raw text data based at least in part on a set of computed distances between the set of random text sequences and the raw text data. The method provides the feature matrix as an input to one or more machine learning models.

Abstract: The disclosure discloses a method of neural network model computation-oriented intermediate representation and apparatus thereof. The method includes the following steps: S1, parsing an input model file so as to acquire topological structure information of a neural network; S2, constructing a logical computation graph; S21, inferring physical layout information of each operator in the logical computation graph; S22, inferring meta attributes of each operator in the logical computation graph; S23, inferring description information of input and output logical tensors of each operator in the logical computation graph; S3, constructing a physical computation graph; S31, generating a physical computation graph, etc.

Abstract: A machine learning hardware accelerator architecture and associated techniques are disclosed. The architecture features multiple memory banks of very wide SRAM that may be concurrently accessed by a large number of parallel operational units. Each operational unit supports an instruction set specific to machine learning, including optimizations for performing tensor operations and convolutions. Optimized addressing, an optimized shift reader and variations on a multicast network that permutes and copies data and associates with an operational unit that support those operations are also disclosed.

Abstract: An input weight pattern of a machine learning model may be received. The input weight pattern may be pruned to produce an output weight pattern based on a predetermined pruning algorithm. The pruning algorithm may include partitioning the input weight pattern into a plurality of sub-patterns, each row of the input weight pattern including sub-rows of a first number of sub-patterns, and each column of the input weight pattern including sub-columns of a second number of sub-patterns; and pruning sub-columns and sub-rows from the plurality of sub-patterns to achieve predetermined column and row sparsities respectively, with a constraint that at least one sub-row in each row of the input weight pattern is not pruned. The output weight pattern may further be compressed to produce a compact weight pattern. The compact weight pattern has lower memory and computational overheads as compared to the input weight pattern for the machine learning model.

Abstract: The present disclosure discloses a neural network processing module, in which a mapping unit is configured to receive an input neuron and a weight, and then process the input neuron and/or the weight to obtain a processed input neuron and a processed weight; and an operation unit is configured to perform an artificial neural network operation on the processed input neuron and the processed weight. Examples of the present disclosure may reduce additional overhead of the device, reduce the amount of access, and improve efficiency of the neural network operation.

Abstract: Systems and methods for projecting one or more trends in electronic data and generating enhanced data. A system includes a data forecasting system is in electronic communication with one or more electronic data sources via an electronic network. The data forecasting system is configured to: monitor the electronic data source(s) for data that meet one or more predetermined criteria; obtain at least a portion of the monitored data from electronic data source(s) based on the predetermined criteria; create a data set from the obtained data; derive one or more data values associated with the data set over a predetermined period according to a forward-looking term methodology; and utilize the data set and the derived value(s) over the predetermined period to derive at least one data forecast metric associated with the data set.

Abstract: Embodiments for assessing energy in a thermal energy fluid transfer system in a cloud computing environment by a processor. Behavior of the thermal energy fluid transfer system, associated with a heating service, a cooling service, or a combination thereof, may be learned according to collected data to identify one or more energy usage events. An energy usage assessment operation may be performed using temperature signal disambiguation operations, with data collected over a selected time period by one or more non-intrusive Internet of Things (IoT) sensors located at one or more selected positions in the thermal energy fluid transfer system, to learn the system performance indicators, and when coupled with ingested expected policy behavior, identify one or more energy usage waste events according to the learned behavior in real time.

Abstract: A risk prediction method is executed by a computer of a risk predictor using a convolutional neural network. The method includes making the convolutional neural network acquire an input image taken by an in-vehicle camera installed on a vehicle. The method also includes making the convolutional neural network estimate a risk area and a feature of the risk area, the risk area being in the acquired input image. The risk area has a possibility that a moving object may appear from the risk area into a travelling path of the vehicle, and the moving object may collide with the vehicle in a case where the vehicle simply continues running. The method further includes making the convolutional neural network output the estimated risk area and the estimated feature of the risk area as a risk predicted for the input image.

Abstract: A system and method to reduce weight storage bits for a deep-learning network includes a quantizing module and a cluster-number reduction module. The quantizing module quantizes neural weights of each quantization layer of the deep-learning network. The cluster-number reduction module reduces the predetermined number of clusters for a layer having a clustering error that is a minimum of the clustering errors of the plurality of quantization layers. The quantizing module requantizes the layer based on the reduced predetermined number of clusters for the layer and the cluster-number reduction module further determines another layer having a clustering error that is a minimum of the clustering errors of the plurality of quantized layers and reduces the predetermined number of clusters for the another layer until a recognition performance of the deep-learning network has been reduced by a predetermined threshold.

Abstract: A method for optimizing a reservoir operation for multiple objectives based on a GCN and a NSGA-II algorithm. The method includes collecting relevant data for reservoir flood-control operation and establishing a multi-objective optimization model for the flood control. An initial population is obtained. Grouping individuals by an encoding operation and the grouped classifications are nodes of the GCN, and mapping parent-child relationships obtained by crossover and mutation operations as edges between the nodes in the GCN. A preliminary Pareto frontier is obtained, abscissas of the preliminary Pareto frontier are grouped and labeled, and a GCN model is trained by using the grouping labels and the graphic structure obtained in Step 2. The nodes in the graphic structure are classified by using the trained GCN model, and a uniformity of the Pareto frontier is adjusted. A set of non-inferior schemes of the multi-objective optimization problem for the reservoir operation is output.

Abstract: A method of operating a neural network system includes merging, by a processor, a first operation group in a first neural network and a second operation group in a second neural network, including identical operations, as a shared operation group; selecting, by the processor, a first hardware to execute the shared operation group, from among a plurality of hardware; and executing the shared operation group by using the first hardware.

Abstract: Method, apparatus and product for utilizing stochastic controller to provide user-controlled notification rate of wearable-based events. The method comprises obtaining events issued by a module based on analysis of multiple sensor readings of one or more sensors of a wearable device. The method further comprises determining by a stochastic controller whether to provide an alert to a user based on the events and based on a user preference, wherein the user preference is indicative of a desired notification rate of the user, wherein the stochastic controller comprises a stochastic model of an environment. Based on such determination, alerts are outputted to the user.