Ryan Kiros


PhD Student
Machine Learning Group
Department of Computer Science
University of Toronto

I am a 2nd year PhD student under the supervision of Dr. Ruslan Salakhutdinov and Dr. Richard Zemel.
Contact: infer from the URL
Google scholar profile

Research

My research interests are in Statistical Machine Learning, Computer Vision and Natural Language Processing.

Education

Publications

2015

Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models
Ryan Kiros, Ruslan Salakhutdinov, Richard Zemel. TACL, 2015. (to appear)
[arXiv] [demo] [extra results] [code coming soon]

An encoder-decoder architecture for ranking and generating image descriptions.

2014

A Multiplicative Model for Learning Distributed Text-Based Attribute Representations
Ryan Kiros, Richard Zemel, Ruslan Salakhutdinov. NIPS, 2014.
[arXiv (old)]

A third order model for jointly learning distributed representations of words and document attributes.

Comparing algorithms for automated vessel segmentation in computed tomography scans of the lung: The VESSEL12 study
Rina D. Rudyanto et al. Medical Image Analysis, 2014.
[link]

The VESSEL12 segmentation study that subsumes our 2013 technical report below.

Multimodal Neural Language Models
Ryan Kiros, Ruslan Salakhutdinov, Richard Zemel. ICML, 2014.
[pdf] [project page and results]

Two new neural language models that can be conditioned on other modalities (such as images).

In-depth Interactive Visual Exploration for Bridging Unstructured and Structured Document Content
Axel J. Soto, Ryan Kiros, Vlado Keselj, Evangelos Milios. SDM Workshop on Exploratory Data Analysis, 2014.
[pdf]

Introducing ViTA-SSD, a visual text analytics tool for semi-structured data that utilizes a new deep learning algorithm.

2013

Learning Deep Representations, Embeddings and Codes from the Pixel Level of Natural and Medical Images
Ryan Kiros. Master's Thesis, University of Alberta, 2013.
[link]

MSc Outstanding Thesis Award.

Training Neural Networks with Stochastic Hessian-Free Optimization
Ryan Kiros. ICLR, 2013.
[pdf] [code] [openreview discussion]

A stochastic version of Martens' Hessian-Free Optimization for training deep nets.

Automatic Lung Vessel Segmentation via Stacked Multiscale Feature Learning
Ryan Kiros, Karteek Popuri, Matthew Low, Dana Cobzas, Martin Jagersand. Technical Report, 2013.
[pdf] [code] [competition page] [video] [results viewer]

1st place (out of 24) in the VESSEL12 segmentation challenge.

2012

Deep Representations and Codes for Image Auto-Annotation
Ryan Kiros and Csaba Szepesvari. NIPS, 2012.
[pdf] [supplementary] [code and features]

Learning binary codes for image annotation, using a deep unsupervised net.

Regularizers Versus Losses for Nonlinear Dimensionality Reduction
Yaoliang Yu, James Neufeld, Ryan Kiros, Xinhua Zhang, Dale Schuurmans. ICML, 2012.
[pdf] [supplementary]

A unifying view of non-parametric, nonlinear dimensionality reduction + 2 new convex regularizers.

On Linear Embeddings and Unsupervised Feature Learning
Ryan Kiros and Csaba Szepesvari. ICML Representation Learning Workshop, 2012. (Oral)
[pdf] [code]

Combining k-means feature learning with supervised linear t-distributed embeddings.

Representation Learning for Sparse, High Dimensional Multi-Label Classification
Ryan Kiros, Axel J. Soto, Evangelos Milios, Vlado Keselj. RSCTC, 2012.
[pdf] [competition page]

5th place (out of 126) in the JRS 2012 data mining competition.

Talks

Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models. LISA lab, Université de Montréal, 2014.
Generating image captions with neural networks. CIFAR Neural Computation and Adaptive Perception Summer School, University of Toronto, 2014.
A Multiplicative Model for Learning Distributed Text-Based Attribute Representations. ICML KPDLTM Workshop, Beijing, 2014.
Multimodal Neural Language Models. ICML, Beijing, 2014.
A Simple Baseline for Segmenting Medical Images. CIFAR Neural Computation and Adaptive Perception Summer School, University of Toronto, 2013.
Deep Representations and Codes for Image Auto-Annotation. University of Guelph, 2012.
On Linear Embeddings and Unsupervised Feature Learning. ICML Representation Learning Workshop, University of Edinburgh, 2012.
Copy Graphs: Compression, Reconstruction and Seed Identification. Canadian Undergraduate Mathematics Conference (CUMC), University of Waterloo, 2010.