Search Results for author:
Found 10 papers, 3 papers with code
VN-Transformer: Rotation-Equivariant Attention for Vector Neurons
Rotation equivariance is a desirable property in many practical applications such as motion forecasting and 3D perception, where it can offer benefits like sample efficiency, better generalization, and robustness to input perturbations.
Learning and Inference in Hilbert Space with Quantum Graphical Models
Unlike classical graphical models, QGMs represent uncertainty with density matrices in complex Hilbert spaces.
Links: A High-Dimensional Online Clustering Method
We present a novel algorithm, called Links, designed to perform online clustering on unit vectors in a high-dimensional Euclidean space.
Initialization matters: Orthogonal Predictive State Recurrent Neural Networks
In this paper, we extend the theory of ORFs to Kernel Ridge Regression and show that ORFs can be used to obtain Orthogonal PSRNNs (OPSRNNs), which are smaller and faster than PSRNNs.
Speaker Diarization with LSTM
For many years, i-vector based audio embedding techniques were the dominant approach for speaker verification and speaker diarization applications.
Ranked #2 on
Speaker Diarization
on CALLHOME-109
Predictive State Recurrent Neural Networks
We present a new model, Predictive State Recurrent Neural Networks (PSRNNs), for filtering and prediction in dynamical systems.
Practical Learning of Predictive State Representations
Unfortunately it is not obvious how to apply apply an EM style algorithm in the context of PSRs as the Log Likelihood is not well defined for all PSRs.
An Efficient, Expressive and Local Minima-free Method for Learning Controlled Dynamical Systems
We propose a framework for modeling and estimating the state of controlled dynamical systems, where an agent can affect the system through actions and receives partial observations.
Supervised Learning for Dynamical System Learning
To address this problem, we present a new view of dynamical system learning: we show how to learn dynamical systems by solving a sequence of ordinary supervised learning problems, thereby allowing users to incorporate prior knowledge via standard techniques such as L1 regularization.
Large-scale randomized-coordinate descent methods with non-separable linear constraints
We develop randomized (block) coordinate descent (CD) methods for linearly constrained convex optimization.
