Nan Rosemary Ke
nan.rosemary.ke at gmail dot com

I am a second year PhD student at the Montreal Institute for Learning Algorithms MILA, where I work on deep learning. I am advised by Professor Chris Pal. I recently spent time at Microsoft Research Maluuba.

Prior to joining MILA, I received a Bachelors in Computer Science at the University of Auckland. I also spent time at Carneigie Mellon University working on speech recognition and deep learning.

I am interested in new ways of training Recurrent Neural Networks, generative models and causal inference learning. I also spend time at Microsoft Research Maluuba, where I work on improved RNN training, generative models and language related research.

Google Scholar  /  GitHub

News
Talks
Research

I am interested in new ways of training Recurrent Neural Networks, generative models and causal inference learning.

Publications

Sparse Attentive BackTracking: Long Range Credit Assignment in Recurrent Networks
Nan Rosemary Ke, Anirudh Goyal, Olexa Bilaniuk, Jonathan Binas, Laurent Charlin, Chris Pal, Yoshua Bengio
ICML Workshop on Principled Approaches to Deep Learning, 2017
, under review for ICLR 2018

A major drawback of backpropagation through time (BPTT) is the difficulty of learning long-term dependencies, coming from having to propagate credit information backwards through every single step of the forward computation. This makes BPTT both computationally impractical and biologically implausible. For this reason, full backpropagation through time is rarely used on long sequences, and truncated backpropagation through time is used as a heuristic. However, this usually leads to biased estimates of the gradient in which longer term dependencies are ignored. Addressing this issue, we propose an alternative algorithm, Sparse Attentive Backtracking, which might also be related to principles used by brains to learn long-term dependencies. Sparse Attentive Backtracking learns an attention mechanism over the hidden states of the past and selectively backpropagates through paths with high attention weights. This allows the model to learn long term dependencies while only backtracking for a small number of time steps, not just from the recent past but also from attended relevant past states.

Twin Networks: Using the future to generate sequences
Nan Rosemary Ke*, Dmitry Serdyuk*, Alessandro Sordoni, Adam Trischler, Chris Pal, Yoshua Bengio
ICML Workshop on Speech and Language Processing, 2017
, under review for ICLR 2018

We propose a simple technique for encouraging generative RNNs to plan ahead. We train a “backward” recurrent network to generate a given sequence in reverse order, and we encourage states of the forward model to predict cotemporal states of the backward model. The backward network is used only during training, and plays no role during sampling or inference. We hypothesize that our approach eases modeling of long-term dependencies by implicitly forcing the forward states to hold information about the longer-term future (as contained in the backward states).

Ethical Challenges in Dialogue Systems
Peter Henderson, Koustav Sinha, Nicolas Gontier,Nan Rosemary Ke, Geneive Fried, Ryan Lowe, Joelle Pinea
to appear AIES, 2018

The use of dialogue systems as a medium for human-machine interaction is an increasingly prevalent paradigm. A growing number of dialogue systems use conversation strategies that are learned from large datasets. There are well documented instances where interactions with these system have resulted in biased or even offensive conversations due to the data-driven training process. Here, we highlight potential ethical issues that arise in dialogue systems research, including: implicit biases in data-driven systems, the rise of adversarial examples, potential sources of privacy violations, safety concerns, special considerations for reinforcement learning systems, and reproducibility concerns. We also suggest areas stemming from these issues that deserve further investigation. Through this initial survey, we hope to spur research leading to robust, safe, and ethically sound dialogue systems.


Z Forcing: Training Stochastic RNN's
Anirudh Goyal, Alessandro Sordoni, Marc-Alexandre Côté, Rosemary Nan Ke, Yoshua Bengio, Neural Information Processing System (NIPS), 2017
arXiv / code (coming soon)

We proposed a novel approach to incorporate stochastic latent variables in sequential neural networks. The method builds on recent architectures that use latent variables to condition the recurrent dynamics of the network. We augmented the inference network with an RNN that runs backward through the sequence and added a new auxiliary cost that forces the latent variables to reconstruct the state of that backward RNN, i.e. predict a summary of future observations.

Variational Walkback: Learning a Transition Operator as a Stochastic Recurrent Net
Anirudh Goyal, Nan Rosemary Ke, Surya Ganguli, Yoshua Bengio
Neural Information Processing System (NIPS), 2017
arXiv / blog post (coming soon) / code

We propose a novel method to directly learn a stochastic transition operator whose repeated application provides generated samples. Traditional undirected graphical models approach this problem indirectly by learning a Markov chain model whose stationary distribution obeys detailed balance with respect to a parameterized energy function.


A Deep Reinforcement Learning Chatbot
Iulian V. Serban, Chinnadhurai Sankar, Mathieu Germain, Saizheng Zhang, Zhouhan Lin, Sandeep Subramanian, Taesup Kim, Michael Pieper, Sarath Chandar, Nan Rosemary Ke, Sai Rajeshwar, Alexandre de Brebisson, Jose M. R. Sotelo, Dendi Suhubdy, Vincent Michalski, Alexandre Nguyen, Joelle Pineau and Yoshua Bengio, International Conference on Learning Representations (ICLR), 2017
arXiv

We present MILABOT: a deep reinforcement learning chatbot developed by the Montreal Institute for Learning Algorithms (MILA) for the Amazon Alexa Prize competition. MILABOT is capable of conversing with humans on popular small talk topics through both speech and text. The system consists of an ensemble of natural language generation and retrieval models, including template-based models, bag-of-words models, sequence-to-sequence neural network and latent variable neural network models. By applying reinforcement learning to crowdsourced data and real-world user interactions, the system has been trained to select an appropriate response from the models in its ensemble. The system has been evaluated through A/B testing with real-world users, where it performed significantly better than many competing systems. Due to its machine learning architecture, the system is likely to improve with additional data.


Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations
David Krueger, Tegan Maharaj, Janos Kramar, Mohammad Pezeshki, Nicolas Ballas,Nan Rosemary Ke, Anirudh Goyal Yoshua Bengio, Aaron Courville
Chris Pal
International Conference on Learning Representations (ICLR), 2017
arXiv / code

We propose zoneout, a novel method for regularizing RNNs. At each timestep, zoneout stochastically forces some hidden units to maintain their previous values. Like dropout, zoneout uses random noise to train a pseudo-ensemble, improving generalization. But by preserving instead of dropping hidden units, gradient information and state information are more readily propagated through time, as in feedforward stochastic depth networks.


Cascading Bandits for Large-Scale Recommendation Problems
Shi Zong, Hao Ni, Kenny Sung, Nan Rosemary Ke, Zheng Wen, Branislav Kveton Association for Uncertainty in Artificial Intelligence (UAI), 2016
arXiv

Most recommender systems recommend a list of items. The user examines the list, from the first item to the last, and often chooses the first attractive item and does not examine the rest. This type of user behavior can be modeled by the cascade model. In this work, we study cascading bandits, an online learning variant of the cascade model where the goal is to recommend K most attractive items from a large set of L candidate items. We propose two algorithms for solving this problem, which are based on the idea of linear generalization. The key idea in our solutions is that we learn a predictor of the attraction probabilities of items from their features, as opposing to learning the attraction probability of each item independently as in the existing work. This results in practical learning algorithms whose regret does not depend on the number of items L. We bound the regret of one algorithm and comprehensively evaluate the other on a range of recommendation problems. The algorithm performs well and outperforms all baselines