V četrtek, 9. marca, se nadaljuje serija predavanj FRI Piškot. V poletnem semestru se bomo ob zanimivih temah, kavi in piškotih družili ob četrtkih med 14. in 15. uro.

Na prvem Piškotu v novem terminu bo Jaka Demšar predstavil svoje raziskovalno delo s področja strojnega učenja, za katero je prejel fakultetno Prešernovo nagrado. Se vidimo v četrtek, 9. 3., ob 14. uri v predavalnici P22.

Detecting concept drift using model explanation

Povzetek

In the field of incremental learning, detecting and understanding changes (concept drift) is crucial for success of classification algorithms. To gain insight into the classification predictions, we employed incremental explanation techniques and used the resulting stream of explanations as a basis for a novel concept drift detection method. The majority of current change detection algorithms rely on either monitoring of classifier's performance or comparisons of data distributions where minimal attention is paid to the inner working of the algorithm itself (its comprehensibility). We devised a novel concept drift detection algorithm that relies on various techniques of measuring dissimilarities in vectors of the stream of explanations. The developed methods were evaluated on a new synthetic data stream generator where we control for common factors in incremental environments to confirm its use feasibility. The result is a robust yet sensitive generalized concept drift detector (it can act as a wrapper for an arbitrary classifier), which also diminishes the black-box nature of the learning process, especially with regards to understanding changes detected.

Življenjepis

Jaka Demšar se je rodil v Ljubljani, osnovno šolo pa obiskoval v Škofji Loki, kjer je tudi zaključil gimnazijo kot zlati maturant. V okviru študija na interdisciplinarnem magistrskem študijskem programu Računalništvo in matematika se je raziskovalno ukvarjal s strojnim učenjem, natančneje z odkrivanjem vzorcev v podatkovnih tokovih, pri čemer se je usmeril v zaznavanje sprememb in razumevanje ter vizualizacijo znanja pri rudarjenju podatkovnih tokov. Na to temo je za magisterij, ki ga je izdelal pod mentorstvom izr. prof. dr. Zorana Bosnića, prejel fakultetno Prešernovo nagrado.