More Like this

1. Convolutional Neural Network Optimization Using Modified NSGA-II

   Su, Zhidong Su; Sheng, Weihua; Zhang, Senlin (August 2021, The 11th IEEE International Conference on CYBER Technology in Automation, Control, and Intelligent Systems)

   null (Ed.)

   Convolutional Neural Networks (CNN) are becomin deeper and deeper. It is challenging to deploy the networks directly to embedded devices be- cause they may have different computational capacities. When deploying CNNs, the trade-off between the two objectives: accuracy and inference speed, should be considered. NSGA-II (Non-dominated Sorting Genetic Algorithm II) algorithm is a multi-objective optimiza- tion algorithm with good performance. The network architecture has a significant influence on the accuracy and inference time. In this paper, we proposed a con- volutional neural network optimization method using a modified NSGA-II algorithm to optimize the network architecture. The NSGA-II algorithm is employed to generate the Pareto front set for a specific convolutional neural network, which can be utilized as a guideline for the deployment of the network in embedded devices. The modified NSGA-II algorithm can help speed up the training process. The experimental results show that the modified NSGA-II algorithm can achieve similar results as the original NSGA-II algorithm with respect to our specific task and saves 46.20% of the original training time. 

   more » « less
2. Crystal structure prediction using neural network potential and age-fitness Pareto genetic algorithm

   https://doi.org/10.20517/jmi.2023.33  

   Omee, Sadman Sadeed; Wei, Lai; Hu, Ming; Hu, Jianjun (March 2024, Journal of materials Informatics)

   While crystal structure prediction (CSP) remains a longstanding challenge, we introduce ParetoCSP, a novel algorithm for CSP, which combines a multi-objective genetic algorithm (GA) with a neural network inter-atomic potential model to find energetically optimal crystal structures given chemical compositions. We enhance the updated multi-objective GA (NSGA-III) by incorporating the genotypic age as an independent optimization criterion and employ the M3GNet universal inter-atomic potential to guide the GA search. Compared to GN-OA, a state-of-the-art neural potential-based CSP algorithm, ParetoCSP demonstrated significantly better predictive capabilities, outperforming by a factor of $$ 2.562 $$ across $$ 55 $$ diverse benchmark structures, as evaluated by seven performance metrics. Trajectory analysis of the traversed structures of all algorithms shows that ParetoCSP generated more valid structures than other algorithms, which helped guide the GA to search more effectively for the optimal structures. Our implementation code is available at https://github.com/sadmanomee/ParetoCSP . 

   more » « less
3. Managing Objective Archives for Solution Set Reduction in Many-Objective Optimization

   https://doi.org/10.1109/SSCI52147.2023.10372007  

   Peerlinck, Amy; Sheppard, John (December 2023, IEEE Symposium Series on Computational Intelligence)

   As objectives increase in many-objective optimization (MaOO), often so do the number of non-dominated solutions, potentially resulting in solution sets with thousands of non-dominated solutions. Such a larger final solution set increases difficulty in visualization and decision-making. This raises the question: how can we reduce this large solution set to a more manageable size? In this paper, we present a new objective archive management (OAM) strategy that performs post-optimization solution set reduction to help the end-user make an informed decision without requiring expert knowledge of the field of MaOO. We create separate archives for each objective, selecting solutions based on their fitness as well as diversity criteria in both the objective and variable space. We can then look for solutions that belong to more than one archive to create a reduced final solution set. We apply OAM to NSGA-II and compare our approach to environmental selection finding that the obtained solution set has better hypervolume and spread. Furthermore, we compare results found by OAM-NSGA-II to NSGA-III and get competitive results. Additionally, we apply OAM to reduce the solutions found by NSGA-III and find that the selected solutions perform well in terms of overall fitness, successfully reducing the number of solutions. 

   more » « less
4. Multi-Objective level generator generation with Marahel

   https://doi.org/10.1145/3402942.3409606  

   Khalifa, Ahmed; Togelius, Julian (September 2020, International Conference on the Foundations of Digital Games)

   null (Ed.)

   This paper introduces a new system to design constructive level generators by searching the space of constructive level generators defined by Marahel language. We use NSGA-II, a multi-objective optimization algorithm, to search for generators for three different problems (Binary, Zelda, and Sokoban). We restrict the represen- tation to a subset of Marahel language to push the evolution to find more efficient generators. The results show that the generated generators were able to achieve good performance on most of the fitness functions over these three problems. However, on Zelda and Sokoban they tend to depend on the initial state than modifying the map. 

   more » « less
5. The Mutant β ^E202K Sliding Clamp Protein Impairs DNA Polymerase III Replication Activity

   https://doi.org/10.1128/JB.00303-21  

   Homiski, Caleb; Scotland, Michelle K.; Babu, Vignesh M.; Chodavarapu, Sundari; Maul, Robert W.; Kaguni, Jon M.; Sutton, Mark D. (November 2021, Journal of Bacteriology)

   Silhavy, Thomas J. (Ed.)

   ABSTRACT Expression of the Escherichia coli dnaN -encoded β clamp at ≥10-fold higher than chromosomally expressed levels impedes growth by interfering with DNA replication. We hypothesized that the excess β clamp sequesters the replicative DNA polymerase III (Pol III) to inhibit replication. As a test of this hypothesis, we obtained eight mutant clamps with an inability to impede growth and measured their ability to stimulate Pol III replication in vitro . Compared with the wild-type clamp, seven of the mutants were defective, consistent with their elevated cellular levels failing to sequester Pol III. However, the β E202K mutant that bears a glutamic acid-to-lysine substitution at residue 202 displayed an increased affinity for Pol IIIα and Pol III core (Pol IIIαεθ), suggesting that it could still sequester Pol III effectively. Of interest, β E202K supported in vitro DNA replication by Pol II and Pol IV but was defective with Pol III. Genetic experiments indicated that the dnaN E202K strain remained proficient in DNA damage-induced mutagenesis but was induced modestly for SOS and displayed sensitivity to UV light and methyl methanesulfonate. These results correlate an impaired ability of the mutant β E202K clamp to support Pol III replication in vivo with its in vitro defect in DNA replication. Taken together, our results (i) support the model that sequestration of Pol III contributes to growth inhibition, (ii) argue for the existence of an additional mechanism that contributes to lethality, and (iii) suggest that physical and functional interactions of the β clamp with Pol III are more extensive than appreciated currently. IMPORTANCE The β clamp plays critically important roles in managing the actions of multiple proteins at the replication fork. However, we lack a molecular understanding of both how the clamp interacts with these different partners and the mechanisms by which it manages their respective actions. We previously exploited the finding that an elevated cellular level of the β clamp impedes Escherichia coli growth by interfering with DNA replication. Using a genetic selection method, we obtained novel mutant β clamps that fail to inhibit growth. Their analysis revealed that β E202K is unique among them. Our work offers new insights into how the β clamp interacts with and manages the actions of E. coli DNA polymerases II, III, and IV. 

   more » « less