Abstract: Systems, methods, and apparatuses for providing dynamic, prioritized spectrum utilization management. The system includes at least one monitoring sensor, at least one data analysis engine, at least one application, a semantic engine, a programmable rules and policy editor, a tip and cue server, and/or a control panel. The tip and cue server is operable utilize the environmental awareness from the data processed by the at least one data analysis engine in combination with additional information to create actionable data.

Abstract: The disclosure presents herein a method to train a classifier in a machine learning using more than one simultaneous sample to address class imbalance problem in any discriminative classifier. A modified representation of the training dataset is obtained by simultaneously considering features based representations of more than one sample. A modification to an architecture of a classifier is needed into handling the modified date representation of the more than one samples. The modification of the classifier directs same number of units in the input layer as to accept the plurality of simultaneous samples in the training dataset. The output layer will consist of units equal to twice the considered number of classes in the classification task, therefore, the output layer herein will have four units for two-class classification task. The disclosure herein can be implemented to resolve the problem of learning from low resourced data.

Abstract: In one embodiment, a computer-implemented method performed by a data processing (DP) accelerator, includes receiving, at the DP accelerator, first data representing a set of training data from a host processor; receiving, at the DP accelerator, a watermark kernel from the host processor; and executing the watermark kernel within the DP accelerator on an artificial intelligence (AI) model. The watermark kernel, when executed, is configured to: generate a watermark, train the AI model using the set of training data, and implant the watermark within the AI model during training of the AI model. The DP accelerator then transmits second data representing the trained AI model having the watermark implanted therein to the host processor. In an embodiment, the method further includes receiving a pre-trained AI model and the training is performed for the pre-trained AI model.

Abstract: Disclosed is an apparatus for performing a convolution operation in a convolutional neural network. The apparatus may comprise a selector for selecting one or more nonzero elements of a weight parameter, a selector for selecting a data item(s) corresponding to selected nonzero elements in input feature data, and a calculator unit for performing an operation. The apparatus may realize the convolution operation in a sparsified convolutional neural network efficiently through the hardware.

Abstract: Embodiments of the present disclosure relate to a method, device and computer program product for deploying a machine learning model. The method comprises: receiving an intermediate representation indicating processing of a machine learning model, learning parameters of the machine learning model, and a computing resource requirement for executing the machine learning model, the intermediate representation, the learning parameters, and the computing resource requirement being determined based on an original code of the machine learning model, the intermediate representation being irrelevant to a programming language of the original code; determining, at least based on the computing resource requirement, a computing node and a parameter storage node for executing the machine learning model; storing the learning parameters in the parameter storage node; and sending the intermediate representation to the computing node for executing the machine learning model with the stored learning parameters.

Abstract: A computing device generates synthetic tabular data.

Abstract: In one embodiment, a computing device includes an input sensor providing an input data; a programmable logic device (PLD) implementing a convolutional neural network (CNN), wherein: each compute block of the PLD corresponds to one of a multiple of convolutional layers of the CNN, each compute block of the PLD is placed in proximity to at least two memory blocks, a first one of the memory blocks serves as a buffer for the corresponding layer of the CNN, and a second one of the memory blocks stores model-specific parameters for the corresponding layer of the CNN.

Abstract: A method for controlling a physical process includes receiving an input dataset corresponding to the physical process. The method further includes determining a data model based on the input dataset. The data model includes a plurality of latent space variables of a machine learning model. The method also includes receiving a plurality of reference models corresponding to a plurality of classes. Each of the plurality of reference models includes a corresponding plurality of latent space variables. The method includes comparing the data model with each of the plurality of reference models to generate a plurality of distance metric values. The method further includes selecting a reference model among the plurality of reference models based on the plurality of distance metric values. The method also includes controlling the physical process based on the selected reference model.

Abstract: Selective performance of deterministic computations for neural networks is disclosed, including: obtaining a statistical model for a selection layer of the neural network, the statistical model indicating probabilities that corresponding values are selected by the selection layer, the statistical model being generated using historical data; selectively performing a subset of a plurality of deterministic computations on new input data to the neural network, the plurality of deterministic computations being associated with the deterministic computation layer, the selective performance of the deterministic computations being based at least in part on the statistical model and generating a computation result; and outputting the computation result to another layer in the neural network.

Abstract: A management system operates in conjunction with entities to provide service recommendations for objects of users. The management system trains a machine learning model used to generate the service recommendations for the objects. The machine learning model is trained based on historical service entries including descriptions of services previously performed and identifiers used by entities to categorize types of services. The management system generates training data by classifying the historical service entries into predetermined service classifications based on text in the historical service entries. After the machine learning model is trained, the management system generates a recommendation of services for an object based on likelihoods of selection of the predetermined service classifications.

Abstract: The present disclosure relates to a computer-implemented method for use in an electronic design. Embodiments may include receiving, using at least one processor, a user input corresponding to a command in an electronic design automation environment. Embodiments may further include comparing the user input with a portion of an electronic design database. Embodiments may also include providing a final command suggestion based upon, at least in part, the comparison.

Abstract: In accordance with aspects and embodiments, an improved similarity based learning machine and methods of similarity based machine learning are provided. More specifically, the learning machines and machine learning methods of the present disclosure advantageously define subjects by attributes, assign a first similarity score to each of the subjects, from the first similarity score, calculate attribute scaling factors, and use the attribute scaling factors to generate an improved similarity score. In accordance with aspects and embodiments, the improved similarity scores may be used to improve machine learning.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting actions to be performed by an agent interacting with an environment. In one aspect, a system comprises a grid cell neural network and an action selection neural network. The grid cell network is configured to: receive an input comprising data characterizing a velocity of the agent; process the input to generate a grid cell representation; and process the grid cell representation to generate an estimate of a position of the agent in the environment; the action selection neural network is configured to: receive an input comprising a grid cell representation and an observation characterizing a state of the environment; and process the input to generate an action selection network output.

Abstract: An AI model is trained by determining insights for a sequence of computations used in the AI model. The sequence is applied to encrypted data and label pair(s), wherein computational details of each of the computations are defined. Information may also be committed for selected ones of the sequence of computations into a distributed database. The committed information may include computational details used in processing performed for the selected computations, and the distributed database may have a property that the committed information for each selected computation is linked with a verifiable signature of integrity with a previously committed computation in the sequence. Indication is received from an end-user computer system of selected computation(s). Computational details of the indicated selected computation(s) are sent toward the end-user computer system for use by the end-user computer system for verifying the indicated selected computation(s).

Abstract: Techniques for analysis of verification parameters and reduction of training data are provided. A plurality of test results is received, where each of the plurality of test results specifies a respective one or more parameters and a respective one or more events. A list of parameters used to stimulate computing logic is determined. Additionally, a plurality of relevant parameters is generated, corresponding to parameters in the list of parameters that have at least two distinct values specified in the plurality of test results. A plurality of training cases is generated based on the plurality of test results and the plurality of relevant parameters. Further, a neural network is generated for design verification of the computing logic based on the plurality of relevant parameters. The neural network is trained based on the plurality of training cases.

Abstract: An action recognition system is provided that includes a device configured to capture a video sequence formed from a set of unlabeled testing video frames. The system further includes a processor configured to pre-train a recognition engine formed from a reference set of CNNs on a still image domain that includes labeled training still image frames. The processor adapts the recognition engine to a video domain to form an adapted engine, by applying non-reference CNNs to domains that include the still image and video domains and a degraded image domain that includes labeled synthetically degraded versions of the frames in the still image domain. The video domain includes random unlabeled training video frames. The processor recognizes, using the adapted engine, an action performed by at least one object in the sequence, and controls a device to perform a response action in response to an action type of the action.

Abstract: The disclosure provides an approach for collecting system state data relating to whether certain system states overload a processor assigned to a controller of the system. The approach further involves using the collected data to train a regression machine learning algorithm to predict whether indented or desired system states will result in processor overload. Depending on the prediction, the approach takes one of several steps to efficiently change system state.

Abstract: The present invention provides a system and method of side-stepping the need to retrain neural network model after initially trained using a simulator by comparing real-world data to data predicted by the simulator for the same inputs, and developing a mapping correlation that adjusts real world data toward the simulation data. Thus, the decision logic developed in the simulation-trained model is preserved and continues to operate in an altered reality. A threshold metric of similarity can be initially provided into the mapping algorithm, which automatically adjusts real world data to adjusted data corresponding to the simulation data for operating the neural network model when the metric of similarity between the real world data and the simulation data exceeds the threshold metric. Updated learning can continue as desired, working in the background as conditions are monitored.

Abstract: Split an input dataset into training and test datasets; the former includes a plurality of data examples, each represented as a feature vector, and having an associated true label. Split the training dataset into a plurality of training data subsets; for each, train a corresponding machine learning model to obtain a plurality of such models, and apply same to the test dataset to obtain a plurality of predicted labels and prediction scores. For each of the plurality of examples, compute an agreement metric based on a corresponding one of the associated true labels; corresponding ones of the predicted labels; and corresponding ones of the prediction scores. Based on the computed metric, select, for at least some of the true label values, appropriate ones of the data examples to be added to a regression set. Add the appropriate ones of the data examples from the test dataset to the regression set.

Abstract: A self-learning computer-based system has access to multiple runtime modules that are each capable of performing a particular algorithm. Each runtime module implements the algorithm with different code or runs in a different runtime environment. The system responds to a request to run the algorithm by selecting the runtime module or runtime environment that the system predicts will provide the most desirable results based on parameters like accuracy, performance, cost, resource-efficiency, or policy compliance. The system learns how to make such predictions through training sessions conducted by a machine-learning component. This training teaches the system that previous module selections produced certain types of results in the presence of certain conditions. After determining whether similar conditions currently exist, the system uses rules inferred from the training sessions to select the runtime module most likely to produce desired results.