Leo Breiman

from Wikipedia, the free encyclopedia

Leo Breiman (* 27. January 1928 in New York City ; † 5. July 2005 in Berkeley , California ) was a US -American statisticians , who at the University of California, Berkeley worked.

Breiman was the only son of the Eastern European immigrants Max and Lena Breiman, his father was a tailor. He grew up in San Francisco and Los Angeles , where he attended Roosevelt High School until 1945. In 1949 he successfully completed a physics degree at Caltech , in 1950 he earned a master's degree in mathematics from Columbia University , and in 1954 he graduated with a Ph.D. at the University of California at Berkeley, where she then taught probability theory. Since the previous education of his students seemed too unrelated to practice, he also taught mathematics in a school for a time. After a few years he stopped teaching, first wrote a textbook on probability theory and then worked as a statistical consultant, also for UNESCO in Liberia . From 1980 he worked again at UCLA , where he set up a department for computer-aided statistical calculation, which was later able to take on tasks for other institutions. In 1993 he stopped his activity, but continued to supervise some students and published some of his best-known works only after the end of his official teaching activities (including Random Forest ).

Breiman worked at the interface between computer science and statistics, especially in the field of machine learning . His most important contributions are his work on decision trees ( CART algorithm for decision making: Classification and Regression Trees ) and the compilation of decision trees for bootstrap samples. He called these bootstrap combinations bagging . Another method he helped develop is called random forest .

Breiman has received numerous honors and awards. He was elected a member of the United States National Academy of Sciences and the American Academy of Arts and Sciences (1999).

Web links