Approximate Computing

RAVEN focuses on the time-scalability of DL models

SimpleMachines's post on AI coincides with RAVEN's goals.

Approximate Hardware Techniques for Energy-Quality Scaling Across the System

For error-resilient applications, such as machine learning and signal processing, a significant improvement in energy efficiency can be achieved by relaxing exactness constraint on output quality. This paper presents a taxonomy of hardware techniques …

SECO: A Scalable Accuracy Approximate Exponential Function Via Cross-Layer Optimization

From signal processing to emerging deep neural networks, a range of applications exhibit intrinsic error resilience. For such applications, approximate computing opens up new possibilities for energy-efficient computing by producing slightly …

RAVEN

A Reconfigurable Architecture for Varying Emerging Neural Networks.