I
Irina Rish
Researcher at Université de Montréal
Publications - 221
Citations - 7792
Irina Rish is an academic researcher from Université de Montréal. The author has contributed to research in topics: Computer science & Approximation algorithm. The author has an hindex of 34, co-authored 198 publications receiving 6830 citations. Previous affiliations of Irina Rish include IBM & University of California, Irvine.
Papers
More filters
Patent
Facilitating a meeting using graphical text analysis
TL;DR: In this paper, a graph of words from speeches of the participants as the words are received from the participants is generated, and a graphical text analysis on the graph is performed to identify a cognitive state for each participant and a cognitive states for each subgroup of participants.
Patent
Using graphical text analysis to facilitate communication between customers and customer service representatives
TL;DR: In this paper, a method for facilitating communications between customers and customer service representatives is presented, which generates a graph of expressions of a customer and then selects a customer service representative from the plurality of the customer services representatives based on the interaction style of the customers and the interaction styles of the plurality.
Patent
Apparatus and Methods for Determining Availability and Performance of Entities Providing Services in a Distributed System Using Filtered Service Consumer Feedback
TL;DR: In this article, the authors proposed an approach to determine availability and performance of entities providing services in a distributed system using filtered service-consumer feedback in order to reduce the effect of circumstances unique to individual service consumers or to groups of service consumers that do not accurately reflect the actual availability or performance of service-providing entities.
Posted Content
Beyond Backprop: Alternating Minimization with co-Activation Memory.
Anna Choromanska,Sadhana Kumaravel,Ronny Luss,Irina Rish,Brian Kingsbury,Ravi Tejwani,Djallel Bouneffouf +6 more
TL;DR: A novel online algorithm for training deep feedforward neural networks that employs alternating minimization (block-coordinate descent) between the weights and activation variables and improves over stochastic gradient descent (SGD) with backpropagation in several ways.
Stability and Reproducibility in fMRI Analysis
TL;DR: This chapter contains sections titled Pseudo-ROC Prediction Versus Reproducibility (P, R) Curves, Multisubject Prediction Heterogeneity, Discussion, and Summary.