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
29 Aug 2022US11429524Optimized Hierarchical Scratchpads For Enhanced Artificial Intelligence Accelerator Core Utilization
24 May 2021US11016840Low-overhead Error Prediction And Preemption In Deep Neural Network Using Apriori Network Statistics
16 Nov 2020US10838868Programmable Data Delivery By Load And Store Agents On A Processing Chip Interfacing With On-chip Memory Components And Directing Data To External Memory Components
MOMori OharaDeputy Director, IBM Research Tokyo, Distinguished Engineer, Chief SW Engineer for Hybrid Cloud on IBM HW