arrow_back Object Detection using deep convolutional network
Recent advancements in Deep Learning techniques using GPUs.
Submitted by Sundara R Nagalingam (@nsundarrl) on Tuesday, 31 May 2016
NVIDIA has for long been a pioneer in providing the tools to facilitate deep learning. At the heart of deep learning lies the need to train Deep Neural Networks and then have these DNNs perform complex compute tasks in the shortest possible time. NVIDIA has made huge advances in developing a comprehensive software development kit, aimed at helping developers train DNNs at speeds that keep beating previous records. The solution includes cuDNN, cuSPARSE and cuBLAS libraries, DIGITS for training and NCCL to scale up the performance across multiple GPUs. Combined with the immense power of Tesla GPUs built on the newly launched Pascal architecture, this entire combination helps achieve the end goal of bigger and better DNNs driving deep learning problems across multiple domains. Customers such as Facebook, amongst many, are harnessing NVIDIA’s deep learning solutions to provide end user impact via their applications. In India, smart startups leverage our technology to develop intelligent solutions in the consumer space, intelligent video analytics, security, smart search and many more.
Evolution of Deep Learning (DL) techniques - Over view of modern DL stack (software and hardware)- Advances in GPU computation and how it helps to dramatically bring down DL training time - Modern tools CuDNN, CuSPARSE, cuBLAS, DIGITS-NCCL to improve intranode and internode scaling - Success Stories - DL Ecosystem in India from Enteprise and Startups perspective.
Mr. Sundara R Nagalingam is the Head of Manufacturing and Energy businesses for NVIDIA India. He is also responsible for managing the Deep Learning business ecosystem for the company.
He has twenty years of experience in solutions involving Visual Computing, Virtualization and High Performance Computing. He also has exposure to the work cultures of multiple countries in the Asia Pacific region.
He has a strong technical background and his areas of interest include Deep Learning, Big Data Analytics, IoT and Automotive Solutions.