All Tags
AWS
algorithm-design
architecture
cloud-principles
cost-reduction
data-centric
data-compression
data-processing
deployment
design
edge-computing
energy-footprint
hardware
libraries
locality
machine-learning
management
measured
migration
model-optimization
model-training
performance
queries
rebuilding
scaling
services
strategies
template
workloads
Tactic: Choose a Lightweight Algorithm Alternative
Tactic sort:
Awesome Tactic
Type: Architectural Tactic
Category: green-ml-enabled-systems
Title
Choose a Lightweight Algorithm Alternative
Description
Some algorithms may have lightweight alternatives. Using these lighter models can have a lower energy consumption without sacrificing other important quality attributes. For example, Sorbaro et al (2020) noted that a Spiking Neural Network (SNN) is seen as a lightweight alternative for a Convolutional Neural Network (CNN). CNN models can be converted to SNNs without a significant loss of accuracy or performance.
Participant
Data Scientist
Related software artifact
Algorithm
Context
Machine Learning
Software feature
Inference
Tactic intent
Improve energy efficiency by choosing lighter alternatives of existing algorithms, if possible.
Target quality attribute
Energy Efficiency
Other related quality attributes
Accuracy, Performance
Measured impact
< unknown >
Source
Martino Sorbaro, Qian Liu, Massimo Bortone, and Sadique Sheik. 2020. Optimizing the Energy Consumption of Spiking Neural Networks for Neuromorphic Applications. Frontiers in Neuroscience 14 (2020), 662 (DOI: https://doi.org/10.3389/fnins.2020.00662)Graphical representation
