Carlton Downey — accepted AI-conference papers

2021

Identifying Driver Interactions via Conditional Behavior Prediction

Ekaterina Tolstaya, Reza Mahjourian, Carlton Downey, Balakrishnan Vadarajan, Benjamin Sapp, Dragomir Anguelov

ICRA 2021poster

Interactive driving scenarios, such as lane changes, merges and unprotected turns, are some of the most challenging situations for autonomous driving. Planning in interactive scenarios requires accurately modeling the reactions of other agents to different future actions of the ego agent. We develop…

Cited by 89 Source ↗Scholar ↗

2018

Initialization matters: Orthogonal Predictive State Recurrent Neural Networks

Krzysztof Choromanski, Carlton Downey, Byron Boots

ICLR 2018poster

Learning to predict complex time-series data is a fundamental challenge in a range of disciplines including Machine Learning, Robotics, and Natural Language Processing. Predictive State Recurrent Neural Networks (PSRNNs) (Downey et al.) are a state-of-the-art approach for modeling time-series data w…

Cited by 26 Source ↗PDF ↗Scholar ↗

2018

Learning and Inference in Hilbert Space with Quantum Graphical Models

Siddarth Srinivasan, Carlton Downey, Byron Boots

NeurIPS 2018poster

Quantum Graphical Models (QGMs) generalize classical graphical models by adopting the formalism for reasoning about uncertainty from quantum mechanics. Unlike classical graphical models, QGMs represent uncertainty with density matrices in complex Hilbert spaces. Hilbert space embeddings (HSEs) also…

Cited by 29 Source ↗PDF ↗code ↗Scholar ↗

2018

Speaker Diarization with LSTM

Quan Wang, Carlton Downey, Li Wan, Philip Andrew Mansfield, Ignacio López-Moreno

ICASSP 2018accepted

For many years, i-vector based audio embedding techniques were the dominant approach for speaker verification and speaker diarization applications. However, mirroring the rise of deep learning in various domains, neural network based audio embeddings, also known as <i xmlns:mml="http://www.w3.org/19…

Cited by 0 Source ↗Scholar ↗

2017

Predictive State Recurrent Neural Networks

Carlton Downey, Ahmed Hefny, Byron Boots, Geoffrey J. Gordon, Boyue Li

NeurIPS 2017poster

We present a new model, Predictive State Recurrent Neural Networks (PSRNNs), for filtering and prediction in dynamical systems. PSRNNs draw on insights from both Recurrent Neural Networks (RNNs) and Predictive State Representations (PSRs), and inherit advantages from both types of models. Like many…

Cited by 65 Source ↗PDF ↗code ↗Scholar ↗

2015

Supervised Learning for Dynamical System Learning

Ahmed Hefny, Carlton Downey, Geoffrey J. Gordon

NeurIPS 2015poster

Recently there has been substantial interest in spectral methods for learning dynamical systems. These methods are popular since they often offer a good tradeoffbetween computational and statistical efficiency. Unfortunately, they can be difficult to use and extend in practice: e.g., they can make i…

Cited by 80 Source ↗PDF ↗Scholar ↗