Low-complexity art
Encyclopedia
Low-Complexity Art was introduced by Jürgen Schmidhuber
in 1997. He characterizes it as the computer age equivalent of minimal art
. Low-Complexity Art is based on algorithmic information theory
: it has low Kolmogorov complexity
, that is, it can be generated by a short algorithm. Schmidhuber provided several examples. He also described an algorithmic theory of beauty
and aesthetics
based on the principles of algorithmic information theory
and minimum description length
. It explicitly addresses the subjectivity
of the observer
and postulates: among several input data classified as comparable by a given subjective observer, the most pleasing one has the shortest description, given the observer’s previous knowledge and his particular method for encoding the data. One of Schmidhuber's examples: mathematician
s enjoy simple proofs with a short description in their formal language
. Another example draws inspiration from 15th century proportion studies by Leonardo da Vinci
and Albrecht Dürer
, describing a human face whose proportions can be described by very few bit
s of information
.
Schmidhuber explicitly distinguishes between what's beautiful
and what's interesting. He assumes that any observer continually tries to improve the predictability
and compressibility of the observations by discovering regularities such as repetitions and symmetries and fractal
self-similarity
. Whenever the observer's learning process (which may be a predictive neural network
) leads to improved data compression such that the observations can be described by fewer bits
than before, the temporary interestingness of the data corresponds to the number of saved bits, and thus (in the continuum
limit) to the first derivative of subjectively perceived beauty
. A reinforcement learning
algorithm can be used to maximize the future expected data compression progress. It will motivate the learning observer to execute action sequences that cause additional interesting input data with yet unknown but learnable predictability or regularity. The principles can be implemented on artificial agents which then exhibit a form of artificial curiosity
.
While Low-Complexity Art does not require a priori restrictions of the description size, the basic ideas are related to the size-restricted intro categories of the demoscene
, where very short computer programs are used to generate
pleasing graphical and musical output.
Jürgen Schmidhuber
Jürgen Schmidhuber is a computer scientist and artist known for his work on machine learning, universal Artificial Intelligence , artificial neural networks, digital physics, and low-complexity art. His contributions also include generalizations of Kolmogorov complexity and the Speed Prior...
in 1997. He characterizes it as the computer age equivalent of minimal art
Minimalism
Minimalism describes movements in various forms of art and design, especially visual art and music, where the work is set out to expose the essence, essentials or identity of a subject through eliminating all non-essential forms, features or concepts...
. Low-Complexity Art is based on algorithmic information theory
Algorithmic information theory
Algorithmic information theory is a subfield of information theory and computer science that concerns itself with the relationship between computation and information...
: it has low Kolmogorov complexity
Kolmogorov complexity
In algorithmic information theory , the Kolmogorov complexity of an object, such as a piece of text, is a measure of the computational resources needed to specify the object...
, that is, it can be generated by a short algorithm. Schmidhuber provided several examples. He also described an algorithmic theory of beauty
Beauty
Beauty is a characteristic of a person, animal, place, object, or idea that provides a perceptual experience of pleasure, meaning, or satisfaction. Beauty is studied as part of aesthetics, sociology, social psychology, and culture...
and aesthetics
Aesthetics
Aesthetics is a branch of philosophy dealing with the nature of beauty, art, and taste, and with the creation and appreciation of beauty. It is more scientifically defined as the study of sensory or sensori-emotional values, sometimes called judgments of sentiment and taste...
based on the principles of algorithmic information theory
Algorithmic information theory
Algorithmic information theory is a subfield of information theory and computer science that concerns itself with the relationship between computation and information...
and minimum description length
Minimum description length
The minimum description length principle is a formalization of Occam's Razor in which the best hypothesis for a given set of data is the one that leads to the best compression of the data. MDL was introduced by Jorma Rissanen in 1978...
. It explicitly addresses the subjectivity
Subjectivity
Subjectivity refers to the subject and his or her perspective, feelings, beliefs, and desires. In philosophy, the term is usually contrasted with objectivity.-Qualia:...
of the observer
Observation
Observation is either an activity of a living being, such as a human, consisting of receiving knowledge of the outside world through the senses, or the recording of data using scientific instruments. The term may also refer to any data collected during this activity...
and postulates: among several input data classified as comparable by a given subjective observer, the most pleasing one has the shortest description, given the observer’s previous knowledge and his particular method for encoding the data. One of Schmidhuber's examples: mathematician
Mathematician
A mathematician is a person whose primary area of study is the field of mathematics. Mathematicians are concerned with quantity, structure, space, and change....
s enjoy simple proofs with a short description in their formal language
Formal language
A formal language is a set of words—that is, finite strings of letters, symbols, or tokens that are defined in the language. The set from which these letters are taken is the alphabet over which the language is defined. A formal language is often defined by means of a formal grammar...
. Another example draws inspiration from 15th century proportion studies by Leonardo da Vinci
Leonardo da Vinci
Leonardo di ser Piero da Vinci was an Italian Renaissance polymath: painter, sculptor, architect, musician, scientist, mathematician, engineer, inventor, anatomist, geologist, cartographer, botanist and writer whose genius, perhaps more than that of any other figure, epitomized the Renaissance...
and Albrecht Dürer
Albrecht Dürer
Albrecht Dürer was a German painter, printmaker, engraver, mathematician, and theorist from Nuremberg. His prints established his reputation across Europe when he was still in his twenties, and he has been conventionally regarded as the greatest artist of the Northern Renaissance ever since...
, describing a human face whose proportions can be described by very few bit
Bit
A bit is the basic unit of information in computing and telecommunications; it is the amount of information stored by a digital device or other physical system that exists in one of two possible distinct states...
s of information
Information
Information in its most restricted technical sense is a message or collection of messages that consists of an ordered sequence of symbols, or it is the meaning that can be interpreted from such a message or collection of messages. Information can be recorded or transmitted. It can be recorded as...
.
Schmidhuber explicitly distinguishes between what's beautiful
Beauty
Beauty is a characteristic of a person, animal, place, object, or idea that provides a perceptual experience of pleasure, meaning, or satisfaction. Beauty is studied as part of aesthetics, sociology, social psychology, and culture...
and what's interesting. He assumes that any observer continually tries to improve the predictability
Predictability
Predictability is the degree to which a correct prediction or forecast of a system's state can be made either qualitatively or quantitatively.-Predictability and Causality:...
and compressibility of the observations by discovering regularities such as repetitions and symmetries and fractal
Fractal
A fractal has been defined as "a rough or fragmented geometric shape that can be split into parts, each of which is a reduced-size copy of the whole," a property called self-similarity...
self-similarity
Self-similarity
In mathematics, a self-similar object is exactly or approximately similar to a part of itself . Many objects in the real world, such as coastlines, are statistically self-similar: parts of them show the same statistical properties at many scales...
. Whenever the observer's learning process (which may be a predictive neural network
Neural network
The term neural network was traditionally used to refer to a network or circuit of biological neurons. The modern usage of the term often refers to artificial neural networks, which are composed of artificial neurons or nodes...
) leads to improved data compression such that the observations can be described by fewer bits
BITS
BITS or bits may refer to:* Plural of bit* Background Intelligent Transfer Service, a file transfer protocol* Birla Institute of Technology and Science, a technology school in Pilani, Rajasthan, India, with campuses in Goa, Hyderabad, and Dubai...
than before, the temporary interestingness of the data corresponds to the number of saved bits, and thus (in the continuum
Continuum (theory)
Continuum theories or models explain variation as involving a gradual quantitative transition without abrupt changes or discontinuities. It can be contrasted with 'categorical' models which propose qualitatively different states.-In physics:...
limit) to the first derivative of subjectively perceived beauty
Beauty
Beauty is a characteristic of a person, animal, place, object, or idea that provides a perceptual experience of pleasure, meaning, or satisfaction. Beauty is studied as part of aesthetics, sociology, social psychology, and culture...
. A reinforcement learning
Reinforcement learning
Inspired by behaviorist psychology, reinforcement learning is an area of machine learning in computer science, concerned with how an agent ought to take actions in an environment so as to maximize some notion of cumulative reward...
algorithm can be used to maximize the future expected data compression progress. It will motivate the learning observer to execute action sequences that cause additional interesting input data with yet unknown but learnable predictability or regularity. The principles can be implemented on artificial agents which then exhibit a form of artificial curiosity
Curiosity
Curiosity is an emotion related to natural inquisitive behavior such as exploration, investigation, and learning, evident by observation in human and many animal species. The term can also be used to denote the behavior itself being caused by the emotion of curiosity...
.
While Low-Complexity Art does not require a priori restrictions of the description size, the basic ideas are related to the size-restricted intro categories of the demoscene
Demoscene
The demoscene is a computer art subculture that specializes in producing demos, which are non-interactive audio-visual presentations that run in real-time on a computer...
, where very short computer programs are used to generate
Procedural generation
Procedural generation is a widely used term in the production of media; it refers to content generated algorithmically rather than manually. Often, this means creating content on the fly rather than prior to distribution...
pleasing graphical and musical output.