Towards creativity characterization of generative models via group-based subset scanning

@article{Cintas2021TowardsCC,
  title={Towards creativity characterization of generative models via group-based subset scanning},
  author={C{\'e}lia Cintas and Payel Das and Brian Quanz and Skyler Speakman and Victor Akinwande and Pin-Yu Chen},
  journal={ArXiv},
  year={2021},
  volume={abs/2104.00479}
}
Deep generative models, such as Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs), have been employed widely in computational creativity research. However, such models discourage out-of-distribution generation to avoid spurious sample generation, thereby limiting their creativity. Thus, incorporating research on human creativity into generative deep learning techniques presents an opportunity to make their outputs more compelling and human-like. As we see the emergence… 

Figures from this paper

Domain-agnostic and Multi-level Evaluation of Generative Models

Results demonstrate that MPEGO provides a flexible, user-driven, and multi-level evaluation framework, with practical insights on the generation quality, and validate MPEGO using multiple generative models across several datasets from the material discovery domain.

Explaining Artificial Intelligence Generation and Creativity: Human interpretability for novel ideas and artifacts

Various motivations, algorithms, and methods for explaining either the workings of generative/creative AI algorithms or the generative /creative artifacts they produce are reviewed.

References

SHOWING 1-10 OF 44 REFERENCES

Creative Mind: Myths and Mechanisms

This Second Edition of The Creative Mind has been updated to include recent developments in artificial intelligence, with a new preface, introduction and conclusion by the author.

Gradient-based learning applied to document recognition

This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task, and Convolutional neural networks are shown to outperform all other techniques.

IEEE Transactions on Image Processing

  • 28(1):394–409,
  • 2019

Isolation Forest

The use of isolation enables the proposed method, iForest, to exploit sub-sampling to an extent that is not feasible in existing methods, creating an algorithm which has a linear time complexity with a low constant and a low memory requirement.

Generative Adversarial Nets

We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and a

In Advances in Neural Information Processing Systems

Bill Baird { Publications References 1] B. Baird. Bifurcation analysis of oscillating neural network model of pattern recognition in the rabbit olfactory bulb. In D. 3] B. Baird. Bifurcation analysis

Auto-Encoding Variational Bayes

A stochastic variational inference and learning algorithm that scales to large datasets and, under some mild differentiability conditions, even works in the intractable case is introduced.

Fast generalized subset scan for anomalous pattern detection

It is proved that the nonparametric scan statistics possess a novel property that allows for efficient optimization over the exponentially many subsets of the data without an exhaustive search, enabling FGSS to scale to massive and high-dimensional data sets.

DeepCreativity: Measuring Creativity with Deep Learning Techniques

A new measure, namely DeepCreativity, is introduced, based on Margaret Boden’s definition of creativity as composed by value, novelty and surprise, which is of general applicability and based on a case study of the generation of 19th century American poetry.

Creativity and Machine Learning: A Survey

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 is presented.