在人工智慧（AI）研究領域中，優化模型參數對於決定AI模型的性能和效率至關重要。通常用來優化參數的方法包括網格搜索和手動調整。本研究深入探討了生物啟發算法在優化影像分類模型超參數方面的效能，並比較和實驗了各種生物啟發優化算法，旨在找出最適合優化影像分類模型超參數的算法。
研究根據生物啟發優化算法更新解決方案的方式進行區分，將分其為三類。第一類根據上一代解的序列來更新解決方案。第二類著重於計算解決方案之間的向量，並以此進行更新。第三類則將過去迭代的資訊記錄在地圖中以作為生成新的解時的參考。此外，本研究還提出了一種融合螞蟻群優化和基因算法的混合算法，本研究使用三組資料集對演算法們的參數調整效果進行評估，並分析他們的優點與劣勢。
實驗結果與討論顯示，在不同類別的生物啟發算法中，表現各有千秋。第二類的表現較差，本研究認為原因是在搜索速度和範圍之間的平衡方面存在困難。第一類相對於第二類表現更佳，解決組合問題本來就是其擅長的領域，第三類在特定條件下可能超越第一類，其強調階層接連結的作法在本問題中有著不錯的表現。而本研究提出的算法則在所有資料集中展現出非常優異的性能。
總結而言，本研究成功地對模型進行了編碼，使其能夠利用生物啟發算法進行參數調整，並分析了每種算法的優勢與劣勢。未來研究若是想使用生物演算法對別的模型參數進行優化，可以參考本實驗所做出的結果與分析。

In the realm of artificial intelligence (AI) research, the optimization of model parameters plays a crucial role in determining the performance and efficiency of AI models. This research dives into the realm of bio-inspired algorithms, exploring their efficacy in optimizing hyperparameters for image classification models.
The research classifies the bio-inspired optimization algorithms into three groups based on their approach to updating solutions. The first group update their solutions based on the previous generation’s solutions sequence. The second group focuses on calculating distances between solutions to update them. The third group memorize past iteration information to generate new solutions. In addition, this study also proposes a hybrid algorithm combining ant colony optimization and genetic algorithms.
Results and discussions from the experiments reveal varying outcomes across the different categories of bio-inspired algorithms. The second category doesn’t do well. The first category shows a better performance compared to the first group. The third category may surpass the first under certain conditions. The algorithm proposed in this study exhibits optimal performance in general situations.
In conclusion, this study successfully encoded the model to allow parameter tuning using bio-inspired algorithms, and analyzed the strengths and weaknesses of each algorithm.

[1] Donahue, J., Hendricks, L.A., Rohrbach, M., Venugopalan, S., Guadarrama, S., Saenko, K., & Darrell, T. (2014). Long-term recurrent convolutional networks for visual recognition and description. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2625-2634.
[2] Liu, C.H., Chen, Z., Tang, J., Xu, J., & Piao, C. (2018). Energy-Efficient UAV Control for Effective and Fair Communication Coverage: A Deep Reinforcement Learning Approach. IEEE Journal on Selected Areas in Communications, 36, 2059-2070.
[3] Chen, X., Ma, H., Wan, J., Li, B., & Xia, T. (2016). Multi-view 3D Object Detection Network for Autonomous Driving. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 6526-6534.
[4] Karras, T., Laine, S., & Aila, T. (2018). A Style-Based Generator Architecture for Generative Adversarial Networks. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 4396-4405.
[5] Steinwart, I., & Christmann, A. (2008). Support vector machines. Wiley Interdisciplinary Reviews: Computational Statistics, 1.
[6] Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., & Liu, T. (2017). LightGBM: A Highly Efficient Gradient Boosting Decision Tree. Neural Information Processing Systems.
[7] LeCun, Y., Boser, B.E., Denker, J.S., Henderson, D., Howard, R.E., Hubbard, W.E., & Jackel, L.D. (1989). Handwritten Digit Recognition with a Back-Propagation Network. Neural Information Processing Systems.
[8] Mikolov, T., Karafiát, M., Burget, L., Černocký, J.H., & Khudanpur, S. (2010). Recurrent neural network based language model. Interspeech.
[9] Hochreiter, S., & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9, 1735-1780.
[10] Ledig, C., Theis, L., Huszár, F., Caballero, J., Aitken, A.P., Tejani, A., Totz, J., Wang, Z., & Shi, W. (2016). Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 105-114.
[11] Syarif, I., Prügel-Bennett, A., & Wills, G.B. (2016). SVM Parameter Optimization using Grid Search and Genetic Algorithm to Improve Classification Performance. TELKOMNIKA Telecommunication Computing Electronics and Control, 14, 1502-1509.
[12] Bergstra, J., & Bengio, Y. (2012). Random Search for Hyper-Parameter Optimization. J. Mach. Learn. Res., 13, 281-305.
[13] Liashchynskyi, P.B., & Liashchynskyi, P. (2019). Grid Search, Random Search, Genetic Algorithm: A Big Comparison for NAS. ArXiv, abs/1912.06059.
[14] Goldberg, D.E., & Holland, J.H. (1988). Genetic algorithms and Machine Learning. Machine Learning, 3, 95-99.
[15] Dorigo, M., & Gambardella, L.M. (1997). Ant colony system: a cooperative learning approach to the traveling salesman problem. IEEE Trans. Evol. Comput., 1, 53-66.
[16] Dorigo, M., Maniezzo, V., & Colorni, A. (1996). The Ant System: Optimization by a colony of cooperating agents.
[17] Kennedy, J., & Eberhart, R. (2002). Particle swarm optimization. Proceedings of ICNN'95 - International Conference on Neural Networks, 4, 1942-1948 vol.4.
[18] Salcedo-Sanz, S., Ser, J.D., Landa-Torres, I., Gil-Lopez, S., & Portilla-Figueras, J.A. (2014). The Coral Reefs Optimization Algorithm: A Novel Metaheuristic for Efficiently Solving Optimization Problems. The Scientific World Journal, 2014.
[19] Mirjalili, S.M., Mirjalili, S.M., & Lewis, A. (2014). Grey Wolf Optimizer. Adv. Eng. Softw., 69, 46-61.
[20] Heppner, F., & Grenander, U. (1990). A stochastic nonlinear model for coordinated bird flocks.
[21] MNIST Fashion from https://github.com/zalandoresearch/fashion-mnist
[22] A. Krizhevsky and G. Hinton. (2009). Learning Multiple Layers of Features From Tiny Images. [Online]. Available: http://www.cs.toronto.edu/kriz/cifar.html
[23] 10 Big Cats of the Wild from https://www.kaggle.com/datasets/gpiosenka/cats-in-the-wild-image-classification
[24] 10 Species of Monkey from https://www.kaggle.com/datasets/utkarshsaxenadn/ 10-species-of-monkey-multiclass-classification/data
[25] Animal Species Classification - V3 from https://www.kaggle.com/ datasets/utkarsh saxenadn/animal-image-classification-dataset
[26] Sun, Y., Xue, B., Zhang, M., Yen, G.G., & Lv, J. (2018). Automatically Designing CNN Architectures Using the Genetic Algorithm for Image Classification. IEEE Transactions on Cybernetics, 50, 3840-3854.
[27] Li, T., Luo, H., & Wu, C. (2021). A PSO-based fine-tuning algorithm for CNN. 2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT), 704-709.
[28] Mirjalili, S.M., & Lewis, A. (2016). The Whale Optimization Algorithm. Adv. Eng. Softw., 95, 51-67.