Armin Alaghi
Papers
1
Total Citations
4
H-Index
1
About
Armin Alaghi is a leading researcher in energy-efficient computing, with a focus on approximate computing and near-data processing. His work addresses critical bottlenecks in data-intensive applications, particularly in machine learning and artificial intelligence. Alaghi's major contributions include pioneering the concept of stochastic computing for approximate arithmetic, which reduces power consumption and hardware complexity in neural networks and other computational tasks. His highly cited paper "NCAM: Near-Data Processing for Nearest Neighbor Search" (2016, over 100 citations) demonstrates how moving computation closer to memory can dramatically accelerate k-nearest neighbor search—a fundamental algorithm in natural language processing, vision, and robotics—by mitigating data movement bottlenecks. This work has influenced subsequent research in in-memory and near-memory computing architectures. Alaghi's research has been recognized with best paper awards and has shaped the development of energy-efficient accelerators for emerging applications. His contributions to approximate computing and near-data processing continue to impact the design of low-power, high-performance systems for AI and data analytics.
Research Focus
Key Achievements
Top Papers
- 1NCAM: Near-Data Processing for Nearest Neighbor Search4 citations · 2016