Abstract: There is disclosed a method and system for executing commands. The method comprises configuring an input event topic subscriber and a command orchestrator process. The input event topic subscriber is invoked. The input event topic subscriber receives an event. The event comprises an event context and associated data. The event is transformed into a command. The command orchestrator is invoked. The command is input to the command orchestrator. The command orchestrator adds contextual information to the command. The command orchestrator schedules execution of the command. The execution of the command is tracked. A returned data object corresponding to the command is received and output.

Abstract: A computer-implemented method for explaining an image classifier, the method comprising: receiving an initial image, the initial image having been wrongly classified by the image classifier; receiving an initial gradient of a function executed by the image classifier generated while classifying the initial image, the function being indicative of a probability for the initial image to belong to an initial class; converting the initial image into a latent vector, the latent vector being a representation of the initial image in a latent space; generating a plurality of perturbation vectors using the initial gradient of the function executed by the image classifier; combining the latent vector with each one of the plurality of perturbation vectors, thereby obtaining a plurality of modified vectors; for each one of the plurality of modified vectors, reconstructing a respective image, thereby obtaining a plurality of reconstructed images; transmitting the reconstructed images to the image classifier; for each one o

Abstract: System and method for producing an adversarial article that may be used to disrupt an automated visual tracking process. An input module receives input related to a specific automated visual tracking process. Based on that input, a pattern-design module generates an adversarial pattern. The adversarial pattern may then be applied to an article, which may be any kind of physical or virtual object. The tracker's normal processing modes are disrupted when the tracker attempts to process an image containing the adversarial article(s). The tracker may be mounted on an autonomous vehicle, a mobile robot, or other mobile or stationary camera surveillance system.

Abstract: Systems and components for use with neural networks. An execution block and a system architecture using that execution block are disclosed. The execution block uses a fully connected stack of layers and one output is a forecast for a time series while another output is a backcast that can be used to determine a residual from the input to the execution block. The execution block uses a waveform generator sub-unit whose parameters can be judiciously selected to thereby constrain the possible set of waveforms generated. By doing so, the execution block specializes its function. The system using the execution block has been shown to be better than the state of the art in providing solutions to the time series problem.

Abstract: A method for extracting information from a document, comprising: receiving an identification of an entity to be extracted from the document; identifying candidates from the document, each candidate corresponding to a given element contained in the document and having a given location within the document; embedding the candidates, thereby obtaining an embedding vector for each candidate; for each candidate, comparing in a semantic space the respective embedding vector to previous embedding vectors associated with previous entity values previously chosen for the entity, thereby obtaining a first comparison result; for each candidate, comparing in a pixel space the given location within the document of the candidate to a location associated with the previous entity values previously chosen for the entity, thereby obtaining a second comparison result; sorting the candidates using the first and second comparison results obtained for each candidate, thereby obtaining sorted candidates; and outputting the sorted can

Abstract: Methods and systems for managing network resources enabling network services over a network and for managing maintenance of network resources. The method comprises determining a desired performance level for the network services, the desired performance level being associated with service metrics that establish compliance with a service level agreement; accessing internal data relating to operations of the network and external data not relating to operations of the network; generating a prediction of a network service pattern based on the desired performance level of the network services, the internal data and the external data; identifying a decision scenario for orchestration of the network resources, the decision scenario establishing a configuration of the network resources, the decision scenario being generated based on a correlation of the prediction of the network service pattern and availability of the network resources; and causing to adapt the network resources based on the decision scenario.

Abstract: A system and non-transitory storage medium for performing object classification using a trained machine learning algorithm (MLA). The MLA includes an embedding layer and a classification layer. A byte representation of an object is received. A set of embedding indices is generated based on the byte representation of the object. The MLA embeds, using the embedding layer, the set of embedding indices to obtain an input vector and predicts an estimated class based on the input vector. In some implementations, the set of embedding indices is generated by parsing the byte representation to obtain byte n-grams and by applying a hash function on the byte n-grams.

Abstract: There is provided a non-transitory storage medium and a system for generating an abstractive summary of a document using an abstractive machine learning algorithm (MLA). A document including a plurality of text sequences is received. An extractive summary of the document is generated, the extractive summary including a set of summary text sequences which is a subset of the plurality of text sequences. The abstractive MLA generates, based on the set of summary text sequences and at least a portion of the plurality of text sequences, an abstractive summary of the document including a set of abstractive text sequences, at least one abstractive text sequence not being included in the plurality of text sequences.

Abstract: Systems and methods for automatically detecting and isolating objects in images. An image containing at least one object of interest is segmented by a segmentation module, based on the class of object each pixel of the image depicts. A bounding module then determines coordinates of a predetermined shape that covers at least a portion of the at least one object of interest. An application module then applies a bounding box having those coordinates and having the predetermined shape to the original image. In some embodiments, the coordinates are determined based on a mask layer that is based on the object classes in the image. In other embodiments, the coordinates are determined based on the mask layer and on an edge mask layer. Some embodiments comprise at least one neural network. In some embodiments, the objects of interest are text objects.

Abstract: Systems and methods relating to multitask transfer learning. Neural networks are used to accomplish a number of tasks and the results of these tasks are used to determine parameters common to these and other tasks. These parameters can then be used to accomplish other related tasks. In the description, data fitting as well as image related tasks are used. Task conditioning as well as the use of a KL regularizer have greatly improved results when testing the methods of the invention.

Abstract: Systems and methods for routing a document based on the contents of this document. The content of this document is first subjected to a recognition process and then the result is subjected to multiple types of analysis. Based on the results of the analysis (including contextual analysis), a destination is determined along with any timelines detailed in the document. As well, a severity of the document, indicating the severity of consequences if the document is not handled quickly, is determined. Based on these, an urgency tag and/or a severity tag are assigned to the document. A final destination is determined based on the output of the analysis of the severity, the urgency, and of the destination.

Abstract: Systems and method for use in assisting a user in data aggregation tasks. A system determines the type of data needed by the user to complete the data aggregation task and, based on an indication of the data needed, queries multiple data sources. The results from the multiple data sources are then collated and aligned as necessary. Inconsistencies in the data are resolved or flagged to the user for attention. A completed form or a presentation set of data is then presented to the user for validation.

Abstract: Systems and methods relating to machine learning. An edge device runs a new data point on a first neural network and determines activations on the layers within that neural network. The first neural network is a fully trained network based on a second neural network on a server. The activation data for the various layers in the first neural network are, starting with the output layer, sequentially transmitted to the server. The server continuously receives this activation data and continuously compares it with previously encountered activation data for the second neural network. If the received activation data is within an expected range, then the edge device is instructed to stop sending activation data. Otherwise, the server continues to receive the activation data for the other layers until the new data point is received by the server or the activation data is within the expected range of previously encountered activation data.

Abstract: There is provided a method and a system for training an extractive machine learning algorithm (MLA) to generate extractive summaries of text documents. Reference documents and associated extractive summaries are received. The extractive MLA is then trained to generate an extractive summary, where the training includes, for a given reference document, encoding, using a sentence encoder, a plurality of reference sentences to obtain an associated plurality of sentence representations, encoding, using a document encoder, the associated plurality of sentence representations to obtain a document representation, extracting, using a decoder and based on the associated plurality of sentence representations and the document representation, a first reference sentence of the plurality of reference sentences to obtain a first extracted sentence. A given parameter is updated based on the first extracted sentence and the given reference document summary.

Abstract: A method and system for managing a dataset. An artificial intelligence (AI) model is to be used on the dataset. A data mask describes a labeling status of the data items. A loop is repeated until patience parameters are satisfied. The loop comprises receiving trusted labels provided by trusted labelers; updating the data mask; from a labelled data items subset, training the AI model; cloning the trained AI model into a local AI model on processing nodes; creating and chunking a randomized unlabeled subset into data subsets for dispatching to the processing nodes; receiving an indication that predicted label answers have been inferred by the processing nodes using the local AI model; computing a model uncertainty measurement from statistical analysis of the predicted label answers. The patience parameters include one or more of a threshold value on the model uncertainty measurement and information gain between different training cycles.

Abstract: Systems and methods relating to enhancing capabilities of robotic process automation systems. A system and method includes recognizing and analyzing the components of a user interface on which at least one task is to be executed. The task can be executed regardless of changes to the user interface as the components of the task are based on the presence and function of areas of the user interface and not on the location of the components necessary to execute the task.

Abstract: There is described a computer-implemented method and system for classifying images, the computer-implemented method comprising: receiving an image to be classified, generating a vector representation of the image to be classified using an image embedding method, comparing the vector representation of the image to predefined vector representations of the predefined image categories, and identifying a relevant category amongst the predefined image categories based on the comparison, the relevant category being associated with the image to be classified and outputting the relevant category.

Abstract: A method and a system for training a machine learning algorithm (MLA) for object classification. The machine learning algorithm includes an embedding layer and a classification layer. A set of embedding indices representing a reference object is received. The set of embedding indices has been generated based on a byte representation of the reference object. A label associated with the reference object indicative of a reference class the objects belongs to is received. The MLA is iteratively trained to classify objects by embedding the set of embedding indices to obtain an input vector and by predicting an estimated class based on the input vector, and updating a parameter of at least one of the embedding layer and the updated embedding layer. The set of embedding indices is generated by parsing the byte representation to obtain byte n-grams and by applying a hash function on the byte n-grams.

Abstract: A system identifies anomalies in an image of an object. An input image of the object containing zero or more anomalies is supplied to an image encoder. The image encoder generates an image model. The image model is applied to an image decoder that forms a substitute non-anomalous image of the object. Differences between the input image and the substitute non-anomalous image identify zero or more areas of the input image that contain the zero or more the anomalies. The system implements a flow-based model and has been trained using (a) a set of augmented anomaly-free images of the object applied at the image encoder and (b) a reconstruction loss calculated based on a norm of differences between each augmented anomaly-free image of the object and a corresponding output image from the image decoder.

Abstract: There is described a computer-implemented method for generating a vector representation of an image, the computer-implemented method comprising: receiving a given image and semantic information about the given image; generating a first vector representation of the given image using an image embedding method; generating a second vector representation of the semantic information using a word embedding method; combining the first vector representation of the image to be embedded and the second vector representation of the semantic information together, thereby obtaining a modified vector representation for the image to be embedded; and outputting the modified vector representation.