Publications

  • Stijn Eyerman
  • Wim Heirman
  • Kristof Du Bois
  • Joshua B. Fryman
  • Ibrahim Hur

Many-Core Graph Workload Analysis

Graph applications have specific characteristics that are not common in other application domains and therefore require thorough analysis to guide future graph processing hardware design. In this paper, we analyze multiple graph applications on current multi and many-core processors, and provide conclusions and recommendations for future designs. We restate well-known characteristics of graph applications, such…

View Publication

Towards Understanding End-of-trip Instructions in a Taxi Ride Scenario

We introduce a dataset containing human-authored descriptions of target locations in an "end-of-trip in a taxi ride" scenario. We describe our data collection method and a novel annotation scheme that supports understanding of such descriptions of target locations. Our dataset contains target location descriptions for both synthetic and real-world images as well as visual annotations…

View Publication

Constructing Deep Neural Networks by Bayesian Network Structure Learning

We introduce a principled approach for unsupervised structure learning of deep neural networks. We propose a new interpretation for depth and inter-layer connectivity where conditional independencies in the input distribution are encoded hierarchically in the network structure. Thus, the depth of the network is determined inherently (equal to the maximal order of independence in the…

View Publication

Evaluating Range-Based Anomaly Detectors

Classical anomaly detection (AD) is principally concerned with point-based anomalies, anomalies that occur at a single point in time. While point-based anomalies are useful, many real-world anomalies are range-based, meaning they occur over a period of time. Therefore, applying classical point-based accuracy measures to range-based AD systems can be misleading. In this paper, we present…

View Publication

Term Set Expansion

Term Set Expansion based NLP Architect by Intel AI Lab

We present SetExpander, a corpus-based system for expanding a seed set of terms into a more complete set of terms that belong to the same semantic class. SetExpander implements an iterative end-to-end workflow. It enables users to easily select a seed set of terms, expand it, view the expanded set, validate it, re-expand the validated…

View Publication

  • Amrita Mathuriya
  • Deborah Bard
  • Peter Mendygral
  • Lawrence Meadows
  • James Arnemann
  • Lei Shao
  • Siyu He
  • Tuomas Karna
  • Daina Moise
  • Simon J. Pennycook
  • Kristyn Maschoff
  • Jason Sewall
  • Nalini Kumar
  • Shirley Ho
  • Mike Ringenburg
  • Prabhat
  • Victor Lee

CosmoFlow: Using Deep Learning to Learn the Universe at Scale

Deep learning is a promising tool to determine the physical model that describes our universe. To handle the considerable computational cost of this problem, we present CosmoFlow: a highly scalable deep learning application built on top of the TensorFlow framework. CosmoFlow uses efficient implementations of 3D convolution and pooling primitives, together with improvements in threading…

View Publication

Multi-Task Learning as Multi-Objective Optimization

In multi-task learning, multiple tasks are solved jointly, sharing inductive bias between them. Multi-task learning is inherently a multi-objective problem because different tasks may conflict, necessitating a trade-off. A common compromise is to optimize a proxy objective that minimizes a weighted linear combination of per-task losses. However, this workaround is only valid when the tasks…

View Publication

Single Image Reflection Separation with Perceptual Losses

We present an approach to separating reflection from a single image. The approach uses a fully convolutional network trained end-to-end with losses that exploit low-level and high-level image information. Our loss function includes two perceptual losses: a feature loss from a visual perception network, and an adversarial loss that encodes characteristics of images in the…

View Publication

Deep Learning under Privileged Information Using Heteroscedastic Dropout

Unlike machines, humans learn through rapid, abstract model-building. The role of a teacher is not simply to hammer home right or wrong answers, but rather to provide intuitive comments, comparisons, and explanations to a pupil. This is what the Learning Under Privileged Information (LUPI) paradigm endeavors to model by utilizing extra knowledge only available during…

View Publication