Tytuł artykułu
Autorzy
Identyfikatory
Warianty tytułu
Increasing the potencial of generative artificial intelligence with prompt engineering
Konferencja
Konferencja Radiokomunikacji i Teleinformatyki (20-22.09.2023 ; Kraków, Polska)
Języki publikacji
Abstrakty
W artykule opisano różne techniki stosowane w algorytmach sztucznej inteligencji generatywnej, takie jak modele oparte na rozkładach prawdopodobieństwa, modele wariancyjne oraz modele sekwencyjne. Wyjaśniono podstawy tych technik oraz omówiono ich zastosowania w generowaniu obrazów, muzyki, tekstu czy mowy. Artykuł podkreśla znaczenie algorytmów generative AI jako narzędzi do twórczego generowania treści oraz prezentuje możliwe sposoby zwiększenia efektywności generowania tych treści z wykorzystaniem techniki prompt engineering.
The article describes various techniques used in generative artificial intelligence algorithms, such as models based on probability distributions, variance models and sequential models. The basics of these techniques are explained and their applications in generating images, music, text or speech are discussed. The article emphasizes the importance of generative AI algorithms as tools for creative content generation and presents possible ways to increase the efficiency of generating this content using the prompt engineering technique.
Wydawca
Rocznik
Tom
Strony
341--344
Opis fizyczny
Bibliogr. 23 poz.
Twórcy
autor
- Wojskowa Akademia Techniczna, Warszawa
autor
- Wojskowa Akademia Techniczna, Warszawa
Bibliografia
- [1] Foster David. 2019. „Generative Deep Learning: Teaching Machines to Paint, Write, Compose, and Play. First Edition”. Beijing, O’Reilly.
- [2] Radford Alec et al. 2019. “Language Models are Unsupervised Multitask Learners”
- [3] OpenAI. 2021. „DALL·E: Creating images from text”, accessed: 22.05.2023, https://openai.com/research/dall-e.
- [4] Romero Alberto. 2021. “GitHub Copilot — A New Generation of AI Programmers”. Towards Data Science, accessed: 22.05.2023, https://towardsdatascience.com/github-copilot-a-new-generation-of-aiprogrammers-327e3c7ef3ae.
- [5] Hiken Asa. 2023. “How generative AI is creating custom content in email marketing”.AdAge, accessed: 22.05.2023, https://adage.com/article/digital-marketing-ad-tech-news/how-generative-ai-creating-custom-content-email-marketing/2475106.
- [6] Kaliakatsos-Papakostas Maximos, Floros Andreas, Vrahatis Michael N.2020. “Artificial intelligence methods for music generation: a review and future perspectives” in Nature-Inspired Computation and Swarm Intelligence. Academic Press. 217-245.
- [7] Deveau Richelle, Joseph Griffin Sonia, Reis Steve. 2023. „AI-powered marketing and sales reach new heights with generative AI”. McKinsey & Company, accessed: 22.05.2023, https://www.mckinsey.com/capabilities/growth-marketing-andsales/our-insights/ai-powered-marketing-and-salesreach-new-heights-with-generative-ai.
- [8] Samiullah M., Albrecht D., Nicholson A. E., Ahmed, C. F. 2022. „A Review on Probabilistic Graphical Models and Tools”. Dhaka University Journal of Applied Science and Engineering, 6(2), 82–93.
- [9] Goodfellow Ian. et al. 2014. „Generative adversarial nets”. Advances in neural information processing systems, 2672–2680.
- [10] Van den Oord Aaron. et all. 2016. “Pixel Recurrent Neural Networks” Proceedings of the 33rd International Conference on Machine Learning.
- [11] Van den Oord Aaron. et all. 2016. “Conditional Image Generation with PixelCNN Decoders” 30th Conference on Neural Information Processing Systems, Barcelona, Spain.
- [12] Sharm Harashit. 2017. “Auto-Regressive Generative Models (PixelRNN, PixelCNN++)” Towards Data Science, accessed: 22.05.2023, https://towardsdatascience.com/auto-regressive-generative-models-pixelrnn-pixelcnn-32d192911173.
- [13] Kingma Diederik P., Welling Max. 2019. “An Introduction to Variational Autoencoders” Foundations and Trends in Machine Learning: 12 (4), 307-392.
- [14] Hyunjik Kim, Andriy Mnih. 2019. “Disentangling by Factorising”. Proceedings of the 35th International Conference on Machine Learning, Stockholm, Sweden, PMLR 80, 2018
- [15] Makhzani A., Shlens J., Jaitly N., Goodfellow I., Frey B. 2015. “Adversarial Autoencoders”, arXiv:1511.05644v2.
- [16] Vahdat Arash, Kautz Jan. 2020. “NVAE: A Deep Hierarchical Variational Autoencoder”. 34th Conference on Neural Information Processing Systems (NeurIPS 2020), Vancouver, Canada
- [17] Sherstinsky Alex. et al. 2020. “Fundamentals of Recurrent Neural Network (RNN) and Long Short Term Memory (LSTM) network”. Physica D: Nonlinear Phenomena, 404, 132306.
- [18] Chung J. et al. 2014. “Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling”. NIPS 2014 Deep Learning and Representation Learning Workshop
- [19] Vaswani A. et al. 2017. “Attention is all you need”. NIPS'17: Proceedings of the 31st International Conference on Neural Information Processing Systems, 6000-6010.
- [20] Radford Alec, et al. 2018. “Improving Language Understanding by Generative Pre-Training”.
- [21] OpenAI. “OpenAI Cookbook”, accessed: 22.05.2023, https://github.com/openai/openai-cookbook.
- [22] Open AI. “Best practices for prompt engineering with OpenAI API”, accessed: 22.05.2023, https://help.openai.com/en/articles/6654000-best-practices-for-prompt-engineering-with-openai-api.
- [23] Dokumentacja Midjourney, accessed: 22.05.2023, https://docs.midjourney.com/docs/prompts.
Uwagi
Opracowanie rekordu ze środków MEiN, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2022-2023).
Typ dokumentu
Bibliografia
Identyfikator YADDA
bwmeta1.element.baztech-51dd05a3-d8da-4da8-8dec-130e6a974eb5