Name
Abstract | ||
|---|---|---|
Motivation: Several different threads of research have been proposed for modeling and mining temporal data. On the one hand, approaches such as dynamic Bayesian networks (DBNs) provide a formal probabilistic basis to model relationships between time-indexed random vari- ables but these models are intractable to learn in the general case. On the other, algorithms such as frequent episode mining are scalable to large datasets but do not exhibit the rigorous probabilistic interpretations that are the mainstay of the graphical models literature. Results: We present a unification of these two seemingly diverse threads of research, by demonstrating how dy- namic (discrete) Bayesian networks can be inferred from the results of frequent episode mining. This helps bridge the modeling emphasis of the former with the counting emphasis of the latter. First, we show how, under rea- sonable assumptions on data characteristics and on in- fluences of random variables, the optimal DBN structure can be computed using a greedy, local, algorithm. Next, we connect the optimality of the DBN structure with the notion of fixed-delay episodes and their counts of distinct occurrences. Finally, to demonstrate the practical feasi- bility of our approach, we focus on a specific (but broadly applicable) class of networks, called excitatory networks, and show how the search for the optimal DBN structure can be conducted using just information from frequent episodes. Application on datasets gathered from mathe- matical models of spiking neurons as well as real neuro- science datasets are presented. Availability: Algorithmic implementations, simulator codebases, and datasets are available from our website at http://neural-code.cs.vt.edu/dbn. |
Year | Venue | Keywords |
|---|---|---|
2009 | Clinical Orthopaedics and Related Research | event sequences,dynamic bayesian networks,temporal data mining.,temporal probabilistic networks,frequent episodes,indexation,random variable,temporal data,bayesian network,dynamic bayesian network,neural code,graphical model,temporal |
Field | DocType | Volume |
Data mining,Random variable,Computer science,Temporal database,Bayesian network,Artificial intelligence,Probabilistic logic,Graphical model,Mathematical model,Machine learning,Dynamic Bayesian network,Scalability | Journal | abs/0904.2 |
Citations | PageRank | References |
2 | 0.44 | 10 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Debprakash Patnaik | 1 | 191 | 14.89 |
| Srivatsan Laxman | 2 | 421 | 21.65 |
| Naren Ramakrishnan | 3 | 1913 | 176.25 |