Bart Kosko
Encyclopedia
Bart Andrew Kosko is a writer and professor of electrical engineering and law at the University of Southern California
(USC). He is notable as a researcher and popularizer of fuzzy logic
, neural network
s, and noise
, and author of several trade books and textbooks on these and related subjects of machine intelligence
.
and federal court, and worked part-time as a law clerk
for the Los Angeles District Attorney
's Office.
Kosko is a political and religious skeptic
. He is a contributing editor of the libertarian
periodical Liberty
, where he has published essays on “Palestinian vouchers” and the experience of taking the infamous California bar examination
.
and the cyber-thriller novel
Nanotime, about a possible World War III
that takes place in two days of the year 2030. The novel’s title coins the term “nanotime” to describe the time speed-up that occurs when fast computer chips, rather than slow brains, house minds.
Kosko has a distinctive minimalist prose style, not even using commas in his last several books.
, neural networks, and noise.
In fuzzy logic, he introduced fuzzy cognitive map
s, fuzzy subsethood, additive fuzzy systems, fuzzy approximation theorems, optimal fuzzy rules, fuzzy associative memories, various neural-based adaptive fuzzy systems, ratio measures of fuzziness, the shape of fuzzy sets, the conditional variance of fuzzy systems, and the geometric view of (finite) fuzzy sets as points in hypercubes and its relationship to the on-going debate of fuzziness versus probability
.
In neural networks, Kosko introduced the unsupervised technique of differential Hebbian learning
, sometimes called the “differential synapse,” and most famously the BAM or bidirectional associative memory
family of feedback neural architectures, with corresponding global stability theorems.
In noise
, Kosko introduced the concept of adaptive stochastic resonance
, using neural-like learning algorithms to find the optimal level of noise to add to many nonlinear systems to improve their performance. He proved many versions of the so-called “forbidden interval theorem,” which guarantees that noise will benefit a system if the average level of noise does not fall in an interval of values.
University of Southern California
The University of Southern California is a private, not-for-profit, nonsectarian, research university located in Los Angeles, California, United States. USC was founded in 1880, making it California's oldest private research university...
(USC). He is notable as a researcher and popularizer of fuzzy logic
Fuzzy logic
Fuzzy logic is a form of many-valued logic; it deals with reasoning that is approximate rather than fixed and exact. In contrast with traditional logic theory, where binary sets have two-valued logic: true or false, fuzzy logic variables may have a truth value that ranges in degree between 0 and 1...
, 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...
s, and noise
Noise
In common use, the word noise means any unwanted sound. In both analog and digital electronics, noise is random unwanted perturbation to a wanted signal; it is called noise as a generalisation of the acoustic noise heard when listening to a weak radio transmission with significant electrical noise...
, and author of several trade books and textbooks on these and related subjects of machine intelligence
Artificial intelligence
Artificial intelligence is the intelligence of machines and the branch of computer science that aims to create it. AI textbooks define the field as "the study and design of intelligent agents" where an intelligent agent is a system that perceives its environment and takes actions that maximize its...
.
Personal background
Kosko holds Bachelors degrees in philosophy and in economics from USC, a Masters degree in applied mathematics from UC San Diego, a PhD in electrical engineering from UC Irvine, and an online J.D. in law from the online Concord Law School. He is an attorney licensed in CaliforniaCalifornia
California is a state located on the West Coast of the United States. It is by far the most populous U.S. state, and the third-largest by land area...
and federal court, and worked part-time as a law clerk
Law clerk
A law clerk or a judicial clerk is a person who provides assistance to a judge in researching issues before the court and in writing opinions. Law clerks are not court clerks or courtroom deputies, who are administrative staff for the court. Most law clerks are recent law school graduates who...
for the Los Angeles District Attorney
Los Angeles County District Attorney
The District Attorney of Los Angeles County prosecutes felony and misdemeanor crimes that occur within the jurisdiction of Los Angeles County, California....
's Office.
Kosko is a political and religious skeptic
Skepticism
Skepticism has many definitions, but generally refers to any questioning attitude towards knowledge, facts, or opinions/beliefs stated as facts, or doubt regarding claims that are taken for granted elsewhere...
. He is a contributing editor of the libertarian
Libertarianism
Libertarianism, in the strictest sense, is the political philosophy that holds individual liberty as the basic moral principle of society. In the broadest sense, it is any political philosophy which approximates this view...
periodical Liberty
Liberty (1987)
Liberty is a leading libertarian journal founded in 1987 by R. W. Bradford in Port Townsend, Washington, and currently edited from San Diego, California, by Stephen Cox...
, where he has published essays on “Palestinian vouchers” and the experience of taking the infamous California bar examination
Bar examination
A bar examination is an examination conducted at regular intervals to determine whether a candidate is qualified to practice law in a given jurisdiction.-Brazil:...
.
Writing
Kosko’s most popular book to date was the international best-seller Fuzzy Thinking, about man and machines thinking in shades of gray, and his most recent book was Noise. He has also published short fictionShort story
A short story is a work of fiction that is usually written in prose, often in narrative format. This format tends to be more pointed than longer works of fiction, such as novellas and novels. Short story definitions based on length differ somewhat, even among professional writers, in part because...
and the cyber-thriller novel
Novel
A novel is a book of long narrative in literary prose. The genre has historical roots both in the fields of the medieval and early modern romance and in the tradition of the novella. The latter supplied the present generic term in the late 18th century....
Nanotime, about a possible World War III
World War III in popular culture
World War III is a common theme in popular culture. Since the 1940s, countless books, films, and television programmes have used the theme of nuclear weapons and a third global war. The presence of the Soviet Union as an international rival armed with nuclear weapons created a persistent fear in...
that takes place in two days of the year 2030. The novel’s title coins the term “nanotime” to describe the time speed-up that occurs when fast computer chips, rather than slow brains, house minds.
Kosko has a distinctive minimalist prose style, not even using commas in his last several books.
Research
Kosko’s technical contributions have been in three main areas: fuzzy logicFuzzy logic
Fuzzy logic is a form of many-valued logic; it deals with reasoning that is approximate rather than fixed and exact. In contrast with traditional logic theory, where binary sets have two-valued logic: true or false, fuzzy logic variables may have a truth value that ranges in degree between 0 and 1...
, neural networks, and noise.
In fuzzy logic, he introduced fuzzy cognitive map
Fuzzy cognitive map
A Fuzzy cognitive map is a cognitive map within which the relations between the elements of a "mental landscape" can be used to compute the "strength of impact" of these elements. The theory behind that computation is fuzzy logic.Fuzzy cognitive maps are signed fuzzy digraphs...
s, fuzzy subsethood, additive fuzzy systems, fuzzy approximation theorems, optimal fuzzy rules, fuzzy associative memories, various neural-based adaptive fuzzy systems, ratio measures of fuzziness, the shape of fuzzy sets, the conditional variance of fuzzy systems, and the geometric view of (finite) fuzzy sets as points in hypercubes and its relationship to the on-going debate of fuzziness versus probability
Probability
Probability is ordinarily used to describe an attitude of mind towards some proposition of whose truth we arenot certain. The proposition of interest is usually of the form "Will a specific event occur?" The attitude of mind is of the form "How certain are we that the event will occur?" The...
.
In neural networks, Kosko introduced the unsupervised technique of differential Hebbian learning
Hebbian theory
Hebbian theory describes a basic mechanism for synaptic plasticity wherein an increase in synaptic efficacy arises from the presynaptic cell's repeated and persistent stimulation of the postsynaptic cell...
, sometimes called the “differential synapse,” and most famously the BAM or bidirectional associative memory
Bidirectional Associative Memory
Bidirectional associative memory is a type of recurrent neural network. BAM was introduced by Bart Kosko in 1988. There are two types of associative memory, auto-associative and hetero-associative. BAM is hetero-associative, meaning given a pattern it can return another pattern which is...
family of feedback neural architectures, with corresponding global stability theorems.
In noise
Colors of noise
While noise is by definition derived from a random signal, it can have different characteristic statistical properties corresponding to different mappings from a source of randomness to the concrete noise. Spectral density is such a property, which can be used to distinguish different types of noise...
, Kosko introduced the concept of adaptive stochastic resonance
Stochastic resonance
Stochastic resonance is a phenomenon that occurs in a threshold measurement system when an appropriate measure of information transfer is maximized in the presence of a non-zero level of stochastic input noise thereby lowering the response...
, using neural-like learning algorithms to find the optimal level of noise to add to many nonlinear systems to improve their performance. He proved many versions of the so-called “forbidden interval theorem,” which guarantees that noise will benefit a system if the average level of noise does not fall in an interval of values.