Scalable-effort classifiers for energy-efficient machine learning

88 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Why Should We Add Early Exits to Neural Networks? (2020, methodology): “separately train the auxiliary classifiers on top of it [67].”
Designing Adaptive Neural Networks for Energy-Constrained Image Classification (2018, methodology): “, conditional [19], scalable [32], etc.”
A Dynamic Deep Neural Network Design for Efficient Workload Allocation in Edge Computing (2017, methodology): “The concept of fast inference is based on the assumption that the number of network layers traversed by an input is positively correlated to its classification accuracy [19].”
A Survey of Techniques for Approximate Computing (2016, unknown): “…et al. 2015], error-resilient/tolerant [Esmaeilzadeh et al. 2012b], error-acceptable [Kahng and Kang 2012], tunable [Sidiroglou et al. 2011], having ‘forgiving nature’ [Venkataramani et al. 2015] and being ‘optional’ (vs. guaranteed/mandatory) [Chakradhar and Raghunathan 2010] variables/operations.”
Conditional Deep Learning for energy-efficient and enhanced pattern recognition (2015, background): “Algorithm 2: Methodology to test the CDLN Input: Test instance 𝐼!"”
Surprisal-Triggered Conditional Computation with Neural Networks (2020, background): “class in a classification problem; if the margin between the largest score and the second largest score is below a certain threshold, then a bigger model is used [18, 19, 20, 21, 22].”