Please wait ...
0% Complete
Home
/
13th International Conference on Computer and Knowledge Engineering
Developing Convolutional Neural Networks using a Novel Lamarckian Co-Evolutionary Algorithm
Authors :
Zaniar Sharifi
1
Khabat Soltanian
2
Ali Amiri
3
1- Faculty of Electrical and Computer Engineering University of Zanjan
2- Faculty of Electrical and Computer Engineering University of Zanjan
3- Faculty of Electrical and Computer Engineering University of Zanjan
Keywords :
evolutionary algorithm،evolving deep neural networks،neural architecture search،co-evolution
Abstract :
Neural Architecture Search (NAS) methods autonomously discover high-accuracy neural network architectures, outperforming manually crafted ones. However, The NAS methods require high computational costs due to the high dimension search space and the need to train multiple candidate solutions. This paper introduces LCoDeepNEAT, an instantiation of Lamarckian genetic algorithms, which extends the foundational principles of the CoDeepNEAT framework. LCoDeepNEAT co-evolves CNN architectures and their respective final layer weights. The evaluation process of LCoDeepNEAT entails a single epoch of SGD, followed by the transference of the acquired final layer weights to the genetic representation of the network. In addition, it expedites the process of evolving by imposing restrictions on the architecture search space, specifically targeting architectures comprising just two fully connected layers for classification. Our method yields a notable improvement in the classification accuracy of candidate solutions throughout the evolutionary process, ranging from 2% to 5.6%. This outcome underscores the efficacy and effectiveness of integrating gradient information and evolving the last layer of candidate solutions within LCoDeepNEAT. LCoDeepNEAT is assessed across six standard image classification datasets and benchmarked against eight leading NAS methods. Results demonstrate LCoDeepNEAT’s ability to swiftly discover competitive CNN architectures with fewer parameters, conserving computational resources, and achieving superior classification accuracy compared to other approaches.
Papers List
List of archived papers
Extreme Gradient Boosting (XGBoost) Regressor and Shapley Additive Explanation for Crop Yield Prediction in Agriculture
Dennis A/L Mariadass - Ervin Gubin Moung - Maisarah Mohd Sufian - Ali Farzamnia
Ramp Progressive Secret Image Sharing using Ensemble of Simple Methods
Atieh Mokhtari - Mohammad Taheri
Minimizing Quantum Overhead: A Fault-Tolerant ALU Design with Reduced T Metrics
Sarallah Keshavarz - Shekoofeh Moghimi - Mohammad Reza Reshadinezhad
AVID: A VARIATIONAL INFERENCE DELIBERATION FOR META-LEARNING
Alireza Javaheri - Arsham Gholamzadeh Khoee - Saeed Reza Kheradpisheh - Hadi Farahani - Mohammad Ganjtabesh
FaaScaler: An Automatic Vertical and Horizontal Scaler for Serverless Computing Environments
Zahra Rezaei - Saeid Abrishami - Seid Nima Moeintaghavi
Security Analysis of MiniApps: Vulnerabilities, Exploits, and a Tailored Mitigation Framework
Keyhan Mohammadi - Arman Moradi - Reza Ebrahimi Atani
Towards Low-Overhead Mitigation of Trojan Bit-Flip Attacks on DNNs via Causal Inference
Bahare Gholami - Mohsen Raji
Leveraging a structure-based and learning-based predictor using various feature groups in bioinformatics (case study: protein-peptide region residue-level interaction)
Shima Shafiee - Abdolhossein Fathi
A Genetic-based Fusion Approach of Persian and Universal Phonetic results for Spoken Language Identification
Ashkan Moradi - Yasser Shekofteh - Saeed Zarei
Balanced Learning with Optimized Extra Trees Classifier for Reliable Lithology Identification in Imbalanced Well Log Data
Ali Daneshpour - Behnam Yousefimehr - Mehdi Ghatee
more
Samin Hamayesh - Version 46.0.2