164 citations · 236 across the 5 of their papers we have counts for
5 papers
Towards a future space-based, highly scalable AI infrastructure system design
Blaise Agüera y Arcas, Travis Beals, Maria Biggs +6
If AI is a foundational general-purpose technology, we should anticipate that demand for AI compute -- and energy -- will continue to grow. The Sun is by far the largest energy sou…
Scalable Spatiotemporal Prediction with Bayesian Neural Fields
Feras Saad, Jacob Burnim, Colin Carroll +4
Spatiotemporal datasets, which consist of spatially-referenced time series, are ubiquitous in diverse applications, such as air pollution monitoring, disease tracking, and cloud-de…
Online Normalization for Training Neural Networks
Vitaliy Chiley, Ilya Sharapov, Atli Kosson +5
Online Normalization is a new technique for normalizing the hidden activations of a neural network. Like Batch Normalization, it normalizes the sample dimension. While Online Norma…
Flexpoint: An Adaptive Numerical Format for Efficient Training of Deep Neural Networks
Urs Köster, Tristan J. Webb, Xin Wang +11
Deep neural networks are commonly developed and trained in 32-bit floating point format. Significant gains in performance and energy efficiency could be realized by training and in…
Testing our conceptual understanding of V1 function
Urs Köster, Bruno Olshausen
Here we test our conceptual understanding of V1 function by asking two experimental questions: 1) How do neurons respond to the spatiotemporal structure contained in dynamic, natur…