no code implementations • 4 Sep 2023 • Dejan Grubisic, Bram Wasti, Chris Cummins, John Mellor-Crummey, Aleksandar Zlateski
Advanced compiler technology is crucial for enabling machine learning applications to run on novel hardware, but traditional compilers fail to deliver performance, popular auto-tuners have long search times and expert-optimized libraries introduce unsustainable costs.
1 code implementation • 2 May 2022 • Bram Wasti, José Pablo Cambronero, Benoit Steiner, Hugh Leather, Aleksandar Zlateski
We present LoopStack, a domain specific compiler stack for tensor operations, composed of a frontend, LoopTool, and an efficient optimizing code generator, LoopNest.
no code implementations • 21 Jun 2021 • Ran Lu, Aleksandar Zlateski, H. Sebastian Seung
Many approaches to 3D image segmentation are based on hierarchical clustering of supervoxels into image regions.
no code implementations • 4 Dec 2019 • Rati Gelashvili, Nir Shavit, Aleksandar Zlateski
Fast convolutions via transforms, either Winograd or FFT, had emerged as a preferred way of performing the computation of convolutional layers, as it greatly reduces the number of required operations.
no code implementations • 18 Mar 2019 • Sergiy Popovych, Davit Buniatyan, Aleksandar Zlateski, Kai Li, H. Sebastian Seung
Convolutional nets have been shown to achieve state-of-the-art accuracy in many biomedical image analysis tasks.
no code implementations • CVPR 2018 • Aleksandar Zlateski, Ronnachai Jaroensri, Prafull Sharma, Frédo Durand
We investigate the relationship between the quality of labels and the performance of ConvNets for semantic segmentation.
no code implementations • 17 Jun 2016 • Aleksandar Zlateski, Kisuk Lee, H. Sebastian Seung
Other things being equal, processing a larger image tends to increase throughput, because fractionally less computation is wasted on the borders of the image.
no code implementations • NeurIPS 2015 • Kisuk Lee, Aleksandar Zlateski, Vishwanathan Ashwin, H. Sebastian Seung
Efforts to automate the reconstruction of neural circuits from 3D electron microscopic (EM) brain images are critical for the field of connectomics.
2 code implementations • 22 Oct 2015 • Aleksandar Zlateski, Kisuk Lee, H. Sebastian Seung
Applying Brent's theorem to the task dependency graph implies that linear speedup with the number of processors is attainable within the PRAM model of parallel computation, for wide network architectures.
2 code implementations • NeurIPS 2015 • Kisuk Lee, Aleksandar Zlateski, Ashwin Vishwanathan, H. Sebastian Seung
Efforts to automate the reconstruction of neural circuits from 3D electron microscopic (EM) brain images are critical for the field of connectomics.
no code implementations • 1 May 2015 • Aleksandar Zlateski, H. Sebastian Seung
We present a method for hierarchical image segmentation that defines a disaffinity graph on the image, over-segments it into watershed basins, defines a new graph on the basins, and then merges basins with a modified, size-dependent version of single linkage clustering.