Сравнение на методи

	Проследяване на знанията	Бейсианска мрежа	LSTM	Модел на Раш
Област	Образователна аналитика	Бейсови методи	Дълбоко обучение	Психометрия
Семейство	Machine learning	Bayesian methods	Machine learning	Latent structure
Година на възникване	1994	1988	1997	1960
Създател	Albert Corbett & John Anderson	Judea Pearl	Hochreiter, S. & Schmidhuber, J.	Georg Rasch
Тип	Probabilistic student modeling	Probabilistic graphical model	Recurrent neural network (gated memory cell)	Item Response Theory / Latent trait model
Основополагащ източник	Corbett, A. T., & Anderson, J. R. (1994). Knowledge tracing: Modeling the acquisition of procedural knowledge. User Modeling and User-Adapted Interaction, 4(4), 253–278.	Pearl, J. (1988). Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann. ISBN: 978-1558604797	Hochreiter, S. & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735–1780.	Rasch, G. (1960). Probabilistic Models for Some Intelligence and Attainment Tests. Danish Institute for Educational Research, Copenhagen.
Други названия	BKT, Bayesian Knowledge Tracing, Deep Knowledge Tracing, Bilgi İzleme	Bayes network, belief network, probabilistic graphical model, directed graphical model	LSTM (Uzun Kısa Dönem Bellek Ağı), long short-term memory, LSTM network, recurrent neural network with memory cells	1PL IRT, one-parameter logistic model, Rasch Modeli — 1PL IRT, 1PL model
Свързани	3	4	5	6
Резюме	Knowledge Tracing (KT) is a student-modeling technique that estimates, at each moment in time, the probability that a learner has mastered a target knowledge component. Introduced by Corbett and Anderson in 1994, the classical Bayesian Knowledge Tracing (BKT) model treats skill acquisition as a two-state Hidden Markov Model driven by four interpretable parameters: prior knowledge, learning rate, slip, and guess. Deep variants (DKT, DKVMN, AKT) later replaced HMMs with recurrent and transformer architectures.	A Bayesian network is a probabilistic graphical model, introduced by Judea Pearl in 1988, that encodes a set of variables and their conditional dependencies as a directed acyclic graph (DAG). Each node represents a variable; each directed edge encodes a direct probabilistic influence. By combining Bayes' rule with the graph's conditional independence structure, the model supports reasoning under uncertainty — computing the probability of any variable given observed evidence about others.	LSTM (Long Short-Term Memory) is a recurrent neural network architecture, introduced by Sepp Hochreiter and Jürgen Schmidhuber in 1997, that can learn long-term dependencies in sequential data and is widely used for time-series and sequence prediction. It keeps an internal memory that lets information persist across many time steps.	The Rasch model, introduced by Georg Rasch in 1960, is the simplest member of the Item Response Theory (IRT) family. It assigns a single difficulty parameter to each test item and places both item difficulties and person abilities on the same logit scale, enabling direct, sample-independent comparison of items and persons.