Swetha Mandava

Swetha Mandava is a Deep Learning engineer at NVIDIA where she develops optimized deep learning algorithms for applications in NLP/CV. She received her M.S in Electrical and Computer Engineering focusing on Machine learning from Carnegie Mellon University.

Posts by Swetha Mandava

AI / Deep Learning

Pretraining BERT with Layer-wise Adaptive Learning Rates

Training with larger batches is a straightforward way to scale training of deep neural networks to larger numbers of accelerators and reduce the training time. 10 MIN READ