Publications (10)
Parallel Tacotron: Non-Autoregressive and Controllable TTS
Isaac Elias, Heiga Zen, Jonathan Shen +4
Although neural end-to-end text-to-speech models can synthesize highly natural speech, there is still room for improvements to its efficiency and naturalness. This paper proposes a…
Learning Spatio-Temporal Specifications for Dynamical Systems
Suhail Alsalehi, Erfan Aasi, Ron Weiss +1
Learning dynamical systems properties from data provides important insights that help us understand such systems and mitigate undesired outcomes. In this work, we propose a framewo…
Latent Collaborative Retrieval
Jason Weston, Chong Wang, Ron Weiss +1
Retrieval tasks typically require a ranking of items given a query. Collaborative filtering tasks, on the other hand, learn to model user's preferences over items. In this paper we…
Autonomous Vision-Based Magnetic Microrobotic Pushing of Micro-Objects and Cells
Max Sokolich, Ceren Kirmizitas, Sambeeta Das +1
Accurate and autonomous transportation of micro-objects and biological cells can enable significant advances in a wide variety of research disciplines. Here, we present a novel, vi…
Scikit-learn: Machine Learning in Python
Fabian Pedregosa, Gaël Varoquaux, Alexandre Gramfort +16
Scikit-learn is a Python module integrating a wide range of state-of-the-art machine learning algorithms for medium-scale supervised and unsupervised problems. This package focuses…
Affinity Weighted Embedding
Jason Weston, Ron Weiss, Hector Yee
Supervised (linear) embedding models like Wsabie and PSI have proven successful at ranking, recommendation and annotation tasks. However, despite being scalable to large datasets t…
STL-based Optimization of Biomolecular Neural Networks for Regression and Control
Eric Palanques-Tost, Hanna Krasowski, Murat Arcak +2
Biomolecular Neural Networks (BNNs), artificial neural networks with biologically synthesizable architectures, achieve universal function approximation capabilities beyond simple b…
Metrics for Signal Temporal Logic Formulae
Curtis Madsen, Prashant Vaidyanathan, Sadra Sadraddini +5
Signal Temporal Logic (STL) is a formal language for describing a broad range of real-valued, temporal properties in cyber-physical systems. While there has been extensive research…
Learning a Tracking Controller for Rolling bots
Logan E Beaver, Max Sokolich, Suhail Alsalehi +3
Micron-scale robots (bots) have recently shown great promise for emerging medical applications. Accurate controlling bots, while critical to their successful deployment, is…
Model Predictive Control for Magnetically-Actuated Cellbots
Mehdi Kermanshah, Logan E. Beaver, Max Sokolich +5
This paper presents a control framework for magnetically actuated cellbots, which combines Model Predictive Control (MPC) with Gaussian Processes (GPs) as a disturbance estimator f…