Architecting AI deployment: A systematic review of state-of-the-art and state-of-practice literature

MM John, H Holmström Olsson, J Bosch - Software Business: 11th …, 2021 - Springer
Companies across domains are rapidly engaged in shifting computational power and
intelligence from centralized cloud to fully decentralized edges to maximize value delivery …

Pipelined backpropagation at scale: training large models without batches

A Kosson, V Chiley, A Venigalla… - Proceedings of …, 2021 - proceedings.mlsys.org
New hardware can substantially increase the speed and efficiency of deep neural network
training. To guide the development of future hardware architectures, it is pertinent to explore …

Revealing the role of explainable AI: How does updating AI applications generate agility-driven performance?

M Masialeti, A Talaei-Khoei, AT Yang - International Journal of Information …, 2024 - Elsevier
This study examines the role of explainable AI in the relationship between updating a
portfolio of AI applications and performance. Updating a portfolio of AI applications relates to …

Self-Supervised Learning Implementation for Malware Detection

SJI Ismail, HP Gemilang… - 2022 8th International …, 2022 - ieeexplore.ieee.org
The huge and ever-increasing amount of malware complicates the malware detection
process. To detect malware, antivirus still relies on signature-based and heuristic-based …

Design Methods and Processes for ML/DL models

MM John - 2021 - diva-portal.org
Objective: The overall objective is to establish systematic and structured design methods
and processes for the end-to-end process of developing, deploying and successfully …

Machine learning (ML) model-based compiler

D Strenski, SR Sukumar - US Patent 11,847,436, 2023 - Google Patents
Abstract Systems and methods are provided for implementing a machine learning (ML)
model based compiler, language translator, and/or a decompiler. For example, the system …