.png){kind=icon}
.png){kind=icon}
Return
Minimum Precision Requirements of General Margin Hyperplane Classifiers
.png){kind=icon}
PRE
AI
DOI：10.1109/JETCAS.2019.2910164.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Margin hyperplane classifiers such as support vector machines have achieved considerable success in various classification tasks. Their simplicity makes them suitable candidates for the design of embedded intelligent systems. Precision is an effective parameter to trade-off accuracy and resource utilization. We present analytical bounds on the precision requirements of general margin hyperplane classifiers. In addition, we propose a principled precision reduction scheme based on the tradeoff between input and weight precisions. We present simulation results that support our analysis and illustrate the gains of our approach in terms of reducing resource utilization. For instance, we show that a linear margin classifier with precision assignment dictated by our approach and applied to the two versus four task of the MNIST dataset is similar to 2 x more accurate than a standard 8 bits low precision implementation in spite of using similar to 2 x 10(4) fewer 1 hit full adders and similar to 2 x 10(3) fewer bits for data and weight representation.
Keywords:
Fixed-point
precision
accuracy
resource constrained machine learning
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3.8
Papers:
1.4K
Citations:
2.8K
