E
Eyal Kolman
Researcher at EMC Corporation
Publications - 38
Citations - 451
Eyal Kolman is an academic researcher from EMC Corporation. The author has contributed to research in topics: Fuzzy rule & Artificial neural network. The author has an hindex of 12, co-authored 38 publications receiving 450 citations. Previous affiliations of Eyal Kolman include Tel Aviv University & Bar-Ilan University.
Papers
More filters
Journal ArticleDOI
Are artificial neural networks white boxes
Eyal Kolman,Michael Margaliot +1 more
TL;DR: A novel Mamdani-type fuzzy model, referred to as the all-permutations fuzzy rule base (APFRB), is introduced, and it is shown that it is mathematically equivalent to a standard feedforward neural network.
Patent
Detecting risky domains
TL;DR: In this article, a technique for detecting risky domains is proposed, which comprises collecting information in connection with a domain and generating a profile comprising at least one metric associated with the domain based on the collected information.
Patent
Unsupervised aggregation of security rules
TL;DR: In this paper, a processing device comprises a processor coupled to a memory and is configured to obtain at least one rule set utilized to detect malicious activity in a computer network, to determine one or more trigger conditions for each of a plurality of rules of the at least rule set, to identify alerts generated responsive to the determined trigger conditions, to compute correlations between respective pairs of the plurality of rule based on the identified alerts, and to aggregate groups of two or more of rules into respective aggregated rules based at least in part on the computed correlations.
Journal ArticleDOI
Extracting symbolic knowledge from recurrent neural networks---A fuzzy logic approach
Eyal Kolman,Michael Margaliot +1 more
TL;DR: A new approach for extracting symbolic information from recurrent neural networks (RNNs) is presented, based on the mathematical equivalence between a specific fuzzy rule-base and functions composed of sums of sigmoids, that can be used to provide a comprehensible explanation of the RNN functioning.
Patent
Rendering transaction data to identify fraud detection rule strength
TL;DR: In this paper, a rules server computer provides a general graph from a group of transaction entries to define a subgroup of the group of fraudulent and authentic transactions on an electronic display.