100 citations · 104 across the 15 of their papers we have counts for
16 papers
DL101 Neural Network Outputs and Loss Functions
Fernando Berzal
The loss function used to train a neural network is strongly connected to its output layer from a statistical point of view. This technical report analyzes common activation functi…
Differential Privacy Regularization: Protecting Training Data Through Loss Function Regularization
Francisco Aguilera-Martínez, Fernando Berzal
Training machine learning models based on neural networks requires large datasets, which may contain sensitive information. The models, however, should not expose private informati…
Enhancing Community Detection in Networks: A Comparative Analysis of Local Metrics and Hierarchical Algorithms
Julio-Omar Palacio-Niño, Fernando Berzal
The analysis and detection of communities in network structures are becoming increasingly relevant for understanding social behavior. One of the principal challenges in this field…
Beyond Trend Following: Deep Learning for Market Trend Prediction
Fernando Berzal, Alberto Garcia
Trend following and momentum investing are common strategies employed by asset managers. Even though they can be helpful in the proper situations, they are limited in the sense tha…
On the use of local structural properties for improving the efficiency of hierarchical community detection methods
Julio-Omar Palacio-Niño, Fernando Berzal
Community detection is a fundamental problem in the analysis of complex networks. It is the analogue of clustering in network data mining. Within community detection methods, hiera…
Evaluation Metrics for Unsupervised Learning Algorithms
Julio-Omar Palacio-Niño, Fernando Berzal
Determining the quality of the results obtained by clustering techniques is a key issue in unsupervised machine learning. Many authors have discussed the desirable features of good…
An Automorphic Distance Metric and its Application to Node Embedding for Role Mining
Víctor Martínez, Fernando Berzal, Juan-Carlos Cubero
Role is a fundamental concept in the analysis of the behavior and function of interacting entities represented by network data. Role discovery is the task of uncovering hidden role…
The NOESIS Network-Oriented Exploration, Simulation, and Induction System
Víctor Martínez, Fernando Berzal, Juan-Carlos Cubero
Network data mining has become an important area of study due to the large number of problems it can be applied to. This paper presents NOESIS, an open source framework for network…
The ModelCC Model-Based Parser Generator
Luis Quesada, Fernando Berzal, Juan-Carlos Cubero
Formal languages let us define the textual representation of data with precision. Formal grammars, typically in the form of BNF-like productions, describe the language syntax, whic…
Scanning and Parsing Languages with Ambiguities and Constraints: The Lamb and Fence Algorithms
Luis Quesada, Fernando Berzal, Francisco J. Cortijo
Traditional language processing tools constrain language designers to specific kinds of grammars. In contrast, model-based language processing tools decouple language design from l…
A DSL for Mapping Abstract Syntax Models to Concrete Syntax Models in ModelCC
Luis Quesada, Fernando Berzal, Juan-Carlos Cubero
ModelCC is a model-based parser generator that decouples language design from language processing. ModelCC provides two different mechanisms to specify the mapping from an abstract…
A Model-Driven Probabilistic Parser Generator
Luis Quesada, Fernando Berzal, Francisco J. Cortijo
Existing probabilistic scanners and parsers impose hard constraints on the way lexical and syntactic ambiguities can be resolved. Furthermore, traditional grammar-based parsing too…
A Lexical Analysis Tool with Ambiguity Support
Luis Quesada, Fernando Berzal, Francisco J. Cortijo
Lexical ambiguities naturally arise in languages. We present Lamb, a lexical analyzer that produces a lexical analysis graph describing all the possible sequences of tokens that ca…
Treating Insomnia, Amnesia, and Acalculia in Regular Expression Matching
Luis Quesada, Fernando Berzal, Francisco J. Cortijo
Regular expressions provide a flexible means for matching strings and they are often used in data-intensive applications. They are formally equivalent to either deterministic finit…
A Constraint-Satisfaction Parser for Context-Free Grammars
Luis Quesada, Fernando Berzal, Francisco J. Cortijo
Traditional language processing tools constrain language designers to specific kinds of grammars. In contrast, model-based language specification decouples language design from lan…
Fence - An Efficient Parser with Ambiguity Support for Model-Driven Language Specification
Luis Quesada, Fernando Berzal, Francisco J. Cortijo
Model-based language specification has applications in the implementation of language processors, the design of domain-specific languages, model-driven software development, data i…