activity
20162019
most citedA Deep Reinforcement Learning Chatbot

200 citations · 255 across the 4 of their papers we have counts for

collaborators

5 papers

cs.LG201930 cited

Edge-labeling Graph Neural Network for Few-shot Learning

Jongmin Kim, Taesup Kim, Sungwoong Kim +1

In this paper, we propose a novel edge-labeling graph neural network (EGNN), which adapts a deep neural network on the edge-labeling graph, for few-shot learning. The previous grap…

cs.CL201814 cited

A Deep Reinforcement Learning Chatbot (Short Version)

Iulian V. Serban, Chinnadhurai Sankar, Mathieu Germain +15

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 capa…

cs.CL2017200 cited

A Deep Reinforcement Learning Chatbot

Iulian V. Serban, Chinnadhurai Sankar, Mathieu Germain +15

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 capa…

cs.CL201711 cited

Dynamic Layer Normalization for Adaptive Neural Acoustic Modeling in Speech Recognition

Taesup Kim, Inchul Song, Yoshua Bengio

Layer normalization is a recently introduced technique for normalizing the activities of neurons in deep neural networks to improve the training speed and stability. In this paper,…

cs.LG2016

Deep Directed Generative Models with Energy-Based Probability Estimation

Taesup Kim, Yoshua Bengio

Training energy-based probabilistic models is confronted with apparently intractable sums, whose Monte Carlo estimation requires sampling from the estimated probability distributio…