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: Decrease Model Complexity
Tactic sort:
Awesome Tactic
Type: Architectural Tactic
Category: green-ml-enabled-systems
Title
Decrease Model Complexity
Description
Complex AI models have shown to have high energy consumption and therefore scaling down model complexity can contribute to environmental sustainability. Simplifying the model structure can lead to faster training and inference times, making it more efficient to deploy and use in real-world applications. For example, using simple three-layered Convolutional Neural Network (CNN) architectures (Morotti et al, 2021) and shallower Decision Trees (Abreu et al, 2020) has shown to be energy-efficient while still providing high levels of precision.
Participant
Data Scientist
Related software artifact
Algorithm
Context
Machine Learning
Software feature
Inference
Tactic intent
Improve energy efficiency by decreasing model complexity while still meeting accuracy requirements.
Target quality attribute
Energy Efficiency
Other related quality attributes
< unknown >
Measured impact
< unknown >
Source
Brunno A Abreu, Mateus Grellert, and Sergio Bampi. 2020. VLSI Design of Tree-Based Inference for Low-Power Learning Applications. In 2020 IEEE International Symposium on Circuits and Systems (ISCAS). IEEE, 1–5. [DOI](https://doi.org/10.3390/jimaging7080139); Elena Morotti, Davide Evangelista, and Elena Loli Piccolomini. 2021. A Green Prospective for Learned Post-Processing in Sparse-View Tomographic Reconstruction. Journal of Imaging 7, 8 (2021), 139. [DOI](https://doi.org/10.1109/ISCAS45731.2020.9180704)Graphical representation
