Compensated-DNN: Energy efficient low-precision deep neural networks by compensating quantization errorsShubham JainSwagath Venkataramaniet al.2018DAC 2018
Exploiting approximate computing for deep learning accelerationChia-Yu ChenJungwook Choiet al.2018DATE 2018
POSTER: Design Space Exploration for Performance Optimization of Deep Neural Networks on Shared Memory AcceleratorsSwagath VenkataramaniJungwook Choiet al.2017PACT 2017
Scaledeep: A scalable compute architecture for learning and evaluating deep networksSwagath VenkataramaniAshish Ranjanet al.2017ISCA 2017
INVITED: Accelerator Design for Deep Learning Training: Extended Abstract: InvitedAnkur AgrawalChia-Yu Chenet al.2017DAC 2017
30 Apr 2024TWI840790Single Function To Perform Combined Matrix Multiplication And Bias Add Operations
21 Apr 2024JP7477249System-aware Selective Quantization For Performance Optimized Distributed Deep Learning
27 Nov 2023US11831467Programmable Multicast Protocol For Ring-topology Based Artificial Intelligence Systems
06 Nov 2023US11810340System And Method For Consensus-based Representation And Error Checking For Neural Networks
MOMori OharaDeputy Director, IBM Research Tokyo, Distinguished Engineer, Chief SW Engineer for Hybrid Cloud on IBM HW