Abstract: Methods and systems for generating a prediction value of a Neural Network (NN). The method is executable by a processor and comprises generating, by the processor employing a feature extraction sub-network, a plurality of features based on an input object, generating, by the processor employing a detection sub-network, a detection output based on the plurality of features, the detection sub-network having been trained to generate the detection output indicative of a human-interpretable output for a given portion of the input object; generating, by the processor employing a prediction sub-network, the prediction value based on the human-interpretable output and the given portion of the input object; and providing, by the processor, an indication of the prediction value and the human-interpretable output via a user interface.

Abstract: Methods, systems, and computer-readable media for bi-modal understanding of natural language (NL) and artificial neural network architectures (NA), with reference to an example implementation framework entitled “ArchBERT”. A model and method of training the model for bi-modal understanding of NL and NA are described. The model trained in bi-modal understanding of NL and NA can be deployed to perform tasks such as processing NL to perform reasoning relating to NA, architectural question answering, architecture clone detection, bi-modal architecture clone detection, clone architecture search, and/or bi-modal clone architecture search.

Abstract: Methods, systems, and computer-readable media for bi-modal generation of natural language (NL) and artificial neural network architectures (NA), with reference to an example implementation framework entitled “ArchGenBERT”. A model and method of training the model for bi-modal generation of NL and NA are described. The model trained for bi-modal generation of NL and NA can be deployed to perform a number of useful tasks to assist with designing, describing, translating, and modifying neural network architectures.

Abstract: A method of combinatorial optimization using hybrid temporo-attentional branching. Variable embeddings for the variable features, constraint embeddings for constraint features and edge embeddings for edge features are generated for each mixed integer linear program (MILP) sample in a dataset. The constraint embeddings are updated by a first graph attention network (GAT) of a neural network based on an attention of neighbouring nodes using the variable embeddings, constraint embeddings and edge embeddings. The variable embeddings are updated by a second GAT of the neural network based on an attention of neighbouring nodes using the variable embeddings, updated constraint embeddings and edge embeddings. A Gated Recurrent Unit (GRU) of the neural network generates a representation vector based on the updated variable embeddings for an input sequence consisting of all MILP samples in the dataset. Variables for a first MILP sample are selected from the representation vector in accordance with a branching policy.

Abstract: The present disclosure provides a method and system for adapting a machine learning model, such as an object detection model, to account for domain shift. The method includes receiving a labeled data elements and target image samples and performing a plurality of model adaptation epochs. Each adaptation epoch includes: predicting for each of the target image samples, using the machine learning model configured by a current set of configuration parameters, a corresponding target class label for the respective target data object included in the target image sample; generating a plurality of labeled mixed data elements that each include: (i) a mixed image sample including a source data object from one of the source image samples and a target data object from one of the target image samples, and (ii) the corresponding source class label for the source data object and the corresponding target class label for the target data object.

Abstract: Systems and methods for generating a visual image from audio data and for training the same. The method may include: mapping audio data registered with a microphone array onto closest visual representations in a data manifold for latent representation of images of a visual modality; and generating a visual image of the visual modality from the closest visual representations.

Abstract: The present disclosure provides a computer implemented method and system for generating an algebraic modelling language (AML) formulation of natural language text description of an optimization problem. The computer implemented method includes generating, based on the natural language text description, a text markup language intermediate representation (IR) of the optimization problem, the text markup language IR including an IR objective declaration that defines an objective for the optimization problem and a first IR constraint declaration that indicates a first constraint for the optimization problem. The computer implemented also includes generating, based on the text markup language IR, the AML formulation of the optimization problem, the AML formulation including an AML objective declaration that defines the objective for the optimization problem and a first AML constraint declaration that indicates the first constraint for the optimization problem.

Abstract: Method and system for predicting a label for an input sample. A first label is predicted for the input sample using a first machine learning (ML) model that has been trained to map samples to a first set of labels; If the first label satisfies prediction accuracy criteria it is outputted as the predicted label for the input sample; if the first label does not satisfy the prediction accuracy criteria, a second label is predicted for the input sample using a second ML model that has been trained to map samples to a second set of labels that includes the first set of labels and a set of additional labels, and the second label is outputted as the predicted label for the input sample.

Abstract: Methods and systems for generating a semantically augmented image are disclosed. An embedding is generated for each object label associated with a segmented input image. For each embedding associated with a respective object label, a similarity score is computed between the embedding associated with the object label and an embedding representing an object class in an object bank storing a plurality of object images. At least one object is selected, the selected object being associated with a respective object image in the object bank, the selected at least one object being from an identified object class that is identified as contextually relevant to at least one object label associated with the segmented input image, based at least on the similarity score. The selected object is added into the segmented input image to generate the augmented image.

Abstract: A data sharing system for sharing datasets of data providers to data consumers and transferring incentives from the data consumers to the data providers in response to the data-sharing. The system comprises a multi-angle alliance guided data valuation module for fair allocation of the incentives between the data consumers. The system also comprises a flexible-scenario routed dataset comparison module for evaluating the data provided by the data providers via one of a plurality of evaluating routes. The system provides enhanced use of computer cloud and enables both data alliance and growing capacity of artificial intelligence (AI) supermodels for sustainable data sharing. Moreover, the system uses coreset based Shapley valuation method for efficient data valuation.

Abstract: System and method for splitting a trained neural network into a first neural network for execution on a first device and a second neural network for execution on a second device. The splitting is performed to optimize, within an accuracy constraint, an overall latency of: the execution of the first neural network on the first device to generate a feature map output based on input data, transmission of the feature map output from the first device to the second device, and execution of the second neural network on the second device to generate an inference output based on the feature map output from the first device.

Abstract: Methods and systems for generating a semantically augmented image are disclosed. An embedding is generated for each object label associated with a segmented input image. For each embedding associated with a respective object label, a similarity score is computed between the embedding associated with the object label and an embedding representing an object class in an object bank storing a plurality of object images. At least one object is selected, the selected object being associated with a respective object image in the object bank, the selected at least one object being from an identified object class that is identified as contextually relevant to at least one object label associated with the segmented input image, based at least on the similarity score. The selected object is added into the segmented input image to generate the augmented image.