no code implementations • 21 Dec 2021 • Adam Lesnikowski, Gabriel de Souza Pereira Moreira, Sara Rabhi, Karl Byleen-Higley
Synthetic data and simulators have the potential to markedly improve the performance and robustness of recommendation systems.
no code implementations • 14 Jan 2020 • Adam Lesnikowski, Valentin T. Bickel, Daniel Angerhausen
In this work we show that modern data-driven machine learning techniques can be successfully applied on lunar surface remote sensing data to learn, in an unsupervised way, sufficiently good representations of the data distribution to enable lunar technosignature and anomaly detection.
no code implementations • 29 Nov 2018 • Jiaming Zeng, Adam Lesnikowski, Jose M. Alvarez
One of the main challenges of deep learning tools is their inability to capture model uncertainty.
no code implementations • 8 Nov 2018 • Kashyap Chitta, Jose M. Alvarez, Adam Lesnikowski
Annotating the right data for training deep neural networks is an important challenge.
no code implementations • 6 Nov 2018 • Kashyap Chitta, Jose M. Alvarez, Adam Lesnikowski
In this paper, we introduce Deep Probabilistic Ensembles (DPEs), a scalable technique that uses a regularized ensemble to approximate a deep Bayesian Neural Network (BNN).
no code implementations • 6 Aug 2016 • Adam Lesnikowski
We applied a variety of parametric and non-parametric machine learning models to predict the probability distribution of rainfall based on 1M training examples over a single year across several U. S. states.