Servicenow Canada Inc.

Boris Oreshkin

Dmitri Carpov

Francois Maillet

Bahador Khaleghi

Alexandre Lacoste

Paul Gagnon

Systems and methods for determining similarities between an input data set and a target data set with the data sets being vector representations of the features of a candidate potential copy and a target original. A feature extraction module receives an image of the potential copy and extracts the features of that candidate. The features of the target original may already be extracted or may be separately extracted. The resulting data sets for the candidate and the original are then passed through a decision module. The decision module determines a level of similarity between the features of the candidate and the features of the original. The output of the decision module provides an indication of this level of similarity and, depending on this level of similarity, an alert may be generated. A report module may be included to provide an explanation regarding the level of similarity.

System and method for detecting similarities

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.

Neural network execution block using fully connected layers

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.

Multiple task transfer learning

Systems, architectures, and approaches for use with neural networks. An execution block and a system architecture using a novel execution block are disclosed along with how such an execution block can be used. The execution block uses a fully connected stack of layers and parameters of this fully connected stack of layers are shared. The fully connected nature of the block and on-the-fly generated parameters allow for bypassing specialized training data sets. The system may be trained using non-task-specific training data sets and this allows the system to transfer what is learned to execute a different task. Thus, instead of having to obtain a specialized training data set for a specific task, a more generic training data set can be used to train and prepare the system for that specific task. Results have shown that performance is as good as than the state of the art in providing solutions.

Growing community of inventors

Montreal, Canada

Boris Oreshkin