AI RESEARCH
TRAM: Training Approximate Multiplier Structures for Low-Power AI Accelerators
arXiv CS.AI
•
ArXi:2605.08231v1 Announce Type: cross Reducing power consumption in AI accelerators is increasingly important. Approximate computing can reduce power consumption while keeping the accuracy loss small. Since multipliers are power-hungry components in AI models, this paper focuses on synthesizing low-power approximate multipliers (AxMs). Unlike prior works that design AxMs separately from AI model