Creativity and Machine Learning: A Survey
arXiv:2104.02726 · doi:10.1145/3664595
Abstract
There is a growing interest in the area of machine learning and creativity. This survey presents an overview of the history and the state of the art of computational creativity theories, key machine learning techniques (including generative deep learning), and corresponding automatic evaluation methods. After presenting a critical discussion of the key contributions in this area, we outline the current research challenges and emerging opportunities in this field.
arXiv commentPublished in ACM Computing Surveys at https://dl.acm.org/doi/10.1145/3664595
References in corpus (42)
- Auto-Encoding Variational Bayes
- Sequence to Sequence Learning with Neural Networks
- Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
- Transformers in Vision: A Survey
- Large Scale GAN Training for High Fidelity Natural Image Synthesis
- Categorical Reparameterization with Gumbel-Softmax
- Automatic chemical design using a data-driven continuous representation of molecules
- An Introduction to Variational Autoencoders
- Self-Attention Generative Adversarial Networks
- Conditional Image Generation with PixelCNN Decoders
- Time Series Forecasting With Deep Learning: A Survey
- The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
- Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Models
- Cascaded Diffusion Models for High Fidelity Image Generation
- MaskGAN: Better Text Generation via Filling in the______
- Towards artificial general intelligence via a multimodal foundation model
- A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications
- GANSynth: Adversarial Neural Audio Synthesis
- Image Transformer
- CAN: Creative Adversarial Networks, Generating "Art" by Learning About Styles and Deviating from Style Norms
- Long Text Generation via Adversarial Training with Leaked Information
- Event Representations for Automated Story Generation with Deep Neural Nets
- Diffusion Models: A Comprehensive Survey of Methods and Applications
- MuseGAN: Multi-track Sequential Generative Adversarial Networks for Symbolic Music Generation and Accompaniment
- Deep Learning for Procedural Content Generation
- Adversarial Feature Matching for Text Generation
- Jukebox: A Generative Model for Music
- A survey of multimodal deep generative models
- Controllable Neural Story Plot Generation via Reward Shaping
- Copyright in Generative Deep Learning
- Counterpoint by Convolution
- Music Transformer
- The Lovelace 2.0 Test of Artificial Creativity and Intelligence
- Transforming Exploratory Creativity with DeLeNoX
- The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics
- Reinforcement Learning for Generative AI: State of the Art, Opportunities and Open Research Challenges
- FUDGE: Controlled Text Generation With Future Discriminators
- Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images
- COCO_TS Dataset: Pixel-level Annotations Based on Weak Supervision for Scene Text Segmentation
- Neural Poetry: Learning to Generate Poems using Syllables
- An Interaction Framework for Studying Co-Creative AI
- Deep-speare: A Joint Neural Model of Poetic Language, Meter and Rhyme