Publications by authors named "Aravind Sukumaran Rajam"
Article Synopsis
- Genome assembly is a key challenge in computational molecular biology, aiming to reconstruct genomes from short DNA sequences known as reads, where their order is critical to the assembly process.
- The article introduces BOA (bucket-order-assemble), a method that leverages bucketing and partitioning techniques to create a partial order of reads, facilitating independent assembly of disjoint blocks in parallel.
- Experimental results indicate that BOA enhances both the quality of genome assemblies and the efficiency of the assembly process.
Training models with massive inputs is a significant challenge in the development of Deep Learning pipelines to process very large digital image datasets as required by Whole Slide Imaging (WSI) in computational pathology and analysis of brain fMRI images in computational neuroscience. Graphics Processing Units (GPUs) represent the primary workhorse in training and inference of Deep Learning models. In order to use GPUs to run inference or training on a neural network pipeline, state-of-the-art machine learning frameworks like PyTorch and TensorFlow currently require that the collective memory on the GPUs must be larger than the size of the activations at any stage in the pipeline.
View Article and Find Full Text PDF