ABSTRACT
With the demand of integrated energy metering business and the rise of artificial intelligence technology, the data generation model of digital equipment has become the focus of attention. As the most widely used method in the field of image generation, the implicit method based on GAN has great development potential and strong domain expansion ability. The addition of reinforcement learning method makes the GAN correlation algorithm suitable for data generation of discrete data. This paper proposes an improved SeqGAN model, reconstructs the original SeqGAN model, improves the roll-out module of the original model, uses model parameters lagging behind the generator, and increases the stability of long sequence reinforcement learning. Compared with some existing popular algorithms, the performance of the proposed model algorithm is significantly better than that of the comparison algorithm when the training times are enough (more than 150 times), which lays a foundation for its application in data generation of digital equipment.
- P. Smolensky, Information processing in dynamical systems: Foundations of harmony theory, Colorado Univ at Boulder Dept of Computer Science, 1986.Google Scholar
- D. P. Kingma, and M. Welling, Auto-encoding variational bayes, arXiv preprint arXiv:1312.6114, 2013.Google Scholar
- I. J. Goodfellow, J. Pouget-Abadie, M. Mirza , Generative Adversarial Nets, Advances in Neural Information Processing Systems 27, Advances in Neural Information Processing Systems Z. Ghahramani, M. Welling, C. Cortes , eds., 2014.Google Scholar
- A. Radford, L. Metz, and S. Chintala, Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks, Computer Ence, 2015.Google Scholar
- J.-Y. Zhu, T. Park, P. Isola , Unpaired image-to-image translation using cycle-consistent adversarial networks. pp. 2223-2232.Google Scholar
- A. Brock, J. Donahue, and K. Simonyan, Large scale gan training for high fidelity natural image synthesis, arXiv preprint arXiv:1809.11096, 2018.Google Scholar
- T. Karras, T. Aila, S. Laine , Progressive growing of gans for improved quality, stability, and variation, arXiv preprint arXiv:1710.10196, 2017.Google Scholar
- L. Yu, W. Zhang, J. Wang , Seqgan: Sequence generative adversarial nets with policy gradient. In Proceedings of the AAAI conference on artificial intelligence (AAAI-17)Google Scholar
- M. Arjovsky, S. Chintala, and L. Bottou, Wasserstein Generative Adversarial Networks, in Proceedings of the 34th International Conference on Machine Learning, Proceedings of Machine Learning Research, 2017, pp. 214–223.Google Scholar
- L. Dinh, D. Krueger, and Y. Bengio, Nice: Non-linear independent components estimation, arXiv preprint arXiv:1410.8516, 2014.Google Scholar
- H. Larochelle, and I. Murray, The neural autoregressive distribution estimator. pp. 29-37.Google Scholar
- C. J. Watkins, and P. Dayan, Q-learning, Machine learning, vol. 8, no. 3-4, pp. 279-292, 1992.Google Scholar
- R. S. Sutton, D. A. McAllester, S. P. Singh , Policy gradient methods for reinforcement learning with function approximation. pp. 1057-1063.Google Scholar
- P. W. Glynn, Likelihood ratio gradient estimation for stochastic systems, Communications of the ACM, vol. 33, no. 10, pp. 75-84, 1990.Google ScholarDigital Library
- G. Sidorov, F. Velasquez, E. Stamatatos , Syntactic n-grams as machine learning features for natural language processing, Expert Systems with Applications, vol. 41, no. 3, pp. 853-860, 2014.Google ScholarDigital Library
- N. Srivastava, G. Hinton, A. Krizhevsky , Dropout: a simple way to prevent neural networks from overfitting, The journal of machine learning research, vol. 15, no. 1, pp. 1929-1958, 2014.Google Scholar
Recommendations
Revisiting Learning Paradigms for Multimedia Data Generation
MM '23: Proceedings of the 31st ACM International Conference on MultimediaWith the development of deep learning, multimedia data generation (e.g., image generation, audio synthesis, music composition, and video generation) has attracted a lot of attention. Deep learning methods for data generation usually build a mapping from ...
A multi-scenario text generation method based on meta reinforcement learning
Highlights- We propose a multi-scene text generation framework based on meta learning.
- We ...
AbstractMulti-scenario text generation is an essential task in natural language generation because of the multi-scene interlaced property of real-world problems. Traditional methods typically train the multi-scenario text ...
Controllable Data Generation by Deep Learning: A Review
Designing and generating new data under targeted properties has been attracting various critical applications such as molecule design, image editing and speech synthesis. Traditional hand-crafted approaches heavily rely on expertise experience and ...
Comments