Royal Bank of Canada

Yik Chau Lui

Yanshuai Cao

Weiguang Ding

Ruitong Huang

Cathal Smyth

Cory Fong

Janahan Mathuran Ramanan

Jaspreet Sahota

Yuanqiao Wu

Luyu Wang

Vikash Yadav

Sylvester King Chun Chiang

Ashkan Amiri

Zhengyi Qin

Bryce Croll

Yash Sharma

Athinthra Krishnaswamy Sethurajan

A system receives transaction data over time, and creates structured data based on the received transaction data. Purchase transactions that are associated with a purchase category are identified in the structured data and labeled. A recurrent neural network such as a long short-term memory (LSTM) network, in particular, a k-LSTM architecture using weighted averages to update hidden states and cell states, is trained to build a model. The model is used to predict the likelihood of a purchase transaction.

K-LSTM architecture for purchase prediction

A system, electronic device and method for improved neural network training are provided. The electronic device includes: a processor, a memory storing a Generative adversarial network (GAN) to learn from unlabeled data by engaging a generative model in an adversarial game with a discriminator; and one or more programs stored in the memory and configured to be executed by the one or more processors, the one or more programs including instructions for training the Generative adversarial network using a regularizer to encourage the discriminator to properly use its capacity and hidden representations of the discriminator to have high entropy.

System and method for improved neural network training

An electronic device and method of correcting bias for supervised machine learning data is provided. The electronic device comprises a processor and memory storing instructions which when executed by the processor configure the processor to perform the method. The method comprises training an auto-encoder with an unbiased subset of historical data, and applying the auto-encoder to correct historical data.

Correcting bias in supervised machine learning data

A system for generating an adversarial example in respect of a neural network, the adversarial example generated to improve a margin defined as a distance from a data example to a neural network decision boundary. The system includes a data receiver configured to receive one or more data sets including at least one data set representing a benign training example (x); an adversarial generator engine configured to: generate, using the neural network, a first adversarial example (Adv1) having a perturbation length epsilon1 against x; conduct a search in a direction (Adv1-x) using the neural network; and to generate, using the neural network, a second adversarial example (Adv2) having a perturbation length epsilon2 based at least on an output of a search in the direction (Adv1-x).

System and method for max-margin adversarial training

Systems, methods, and computer readable media are described to train a compressed neural network with high robustness. The neural network is first adversarially pre-trained with both original data as well as data perturbed by adversarial attacks for some epochs, then 'unimportant' weights or filters are pruned through criteria based on their magnitudes or other method (e.g., Taylor approximation of the loss function), and the pruned neural network is retrained with both clean and perturbed data for more epochs.

Robust pruned neural networks via adversarial training

A system and method for determining a reliability score indicative of a level of fidelity between high dimensional (HD) data and corresponding dimension-reduced (LD) data are provided. The system comprises a processor, and a non-transitory computer-readable medium having stored thereon program instructions executable by the processor. The processor is configured to perform the method. The method comprises performing a dimension reduction on the HD data (the dimension reduction resulting in the corresponding LD data), normalizing the HD data and LD data, determine N nearest neighbors of each data point in the HD data and LD data (respectively), determining HD neighbors and correspondence LD neighbors for each data point, determining LD neighbors and correspondence HD neighbors for each data point, determining a distance between the LD neighbors and correspondence LD neighbors, determining a distance between the HD neighbors and correspondence HD neighbors, determining a cost for the dimension reduction, and determining that the cost is within a fidelity range.

Device and method for assessing quality of visualizations of multidimensional data

There is provided a neural network system for detection of domain generation algorithm generated domain names, the neural network system comprising: an input receiver configured for receiving domain names from one or more input sources; a convolutional neural network unit including one or more convolutional layers, the convolutional unit configured for receiving the input text and processing the input text through the one or more convolutional layers; a recurrent neural network unit including one or more long short term memory layers, the recurrent neural network unit configured to process the output from the convolutional neural network unit to perform pattern recognition; and a classification unit including one or more classification layers, the classification unit configured to receive output data from the recurrent neural network unit to perform a determination of whether the input text or portions of the input text are DGA-generated or benign domain names.

Systems and methods for cyberbot network detection

There is provided a neural network system for detection of malicious code, the neural network system comprising: an input receiver configured for receiving input text from one or more code input sources; a convolutional neural network unit including one or more convolutional layers, the convolutional unit configured for receiving the input text and processing the input text through the one or more convolutional layers; a recurrent neural network unit including one or more long short term memory layers, the recurrent neural network unit configured to process the output from the convolutional neural network unit to perform pattern recognition; and a classification unit including one or more classification layers, the classification unit configured to receive output data from the recurrent neural network unit to perform a determination of whether the input text or portions of the input text are malicious code or benign code.

Growing community of inventors

Toronto, Canada

Yik Chau Lui