Brazil

Filter selection in convolutional neural networks aims at finding the most important filters in a convolutional layer, with the goal of reducing computational costs and needed storage, as well as understanding the networks’ inner workings. In this paper we propose an entropy-based filter selection method that ranks filters based on the mutual information between their activations and the output classes using validation data. Our proposed method outperforms using filters’ absolute weights sum by a large margin, allowing to regain better performance with fewer filters.

BRACIS 2020

Entropy-Based Filter Selection in CNNs Applied to Text Classification

convolutional neural networks

filter pruning

mutual information

ICPR 2020 is the premier international conference on Pattern Recognition, gathering leading researchers from around the world to present their latest achievements in Pattern Analysis and Recognition, applied Artificial Intelligence and Machine Learning. The topic of the year is " Putting Artificial intelligence to work on Patterns". 
For the first time, ICPR has employed a two-round review process similar to journal submissions, with new papers allowed to be submitted in either the first or second round and papers submitted in the first round and not accepted allowed to be revised and re-submitted for second round review. 

In this edition of the **ICPR 2020** Conference, there are 1407 Oral/Poster presentations organized in five Tracks: 
- Artificial Intelligence, Machine Learning for Pattern Analysis; 
- Biometrics, Human Analysis and Behavior Understanding; Computer Vision, Robotics and Intelligent Systems; 
- Document and Media Analysis; and 
- Image and Signal Processing. 

The **ICPR 2020** Main Conference program also includes 7 Keynotes from prominent world-renowned scientists, 8 Tutorials, 28 Demos, 8 Challenges, 2 Panels, as well as an Industry/Sponsor Exhibition. In addition, 41 Workshops on a range of important current and emerging research topics complete the ICPR 2020 program. 


ICPR 2020

technical paper

The 9th Brazilian Conference on Intelligent Systems (BRACIS), the 16h Encontro Nacional de Inteligência Artificial e Computacional (ENIAC), and the 12th Concurso de Teses e Dissertações em Inteligência Artificial e Computacional (CTDIAC) was held from 20 to 23 October, 2020.

BRACIS originated from the combination of the two most important scientific events in Brazil in Artificial Intelligence (AI) and Computational Intelligence (CI): the Brazilian Symposium on Artificial Intelligence - SBIA (22 editions), and the Brazilian Symposium on Neural Networks - SBRN (13 editions). ENIAC is a national forum for researchers, practitioners, educators and students to present and discuss innovations, trends, experiences, developments and work in progress in the fields of Artificial and Computational Intelligence. CTDIAC is a satellite event whose goals are to disseminate and award the best dissertations and theses (MSc and PhDs concluded in Brazilian universities from June 2018 to May 2020) in Artificial and Computational Intelligence areas.

In this year, the Symposium on Knowledge Discovery, Mining and Learning (KDMiLe) will be held in conjunction with BRACIS 2020. This sysposium aims at integrating researchers, practitioners, developers, students and users to present their research results, to discuss ideas, and to exchange techniques, tools, and practical experiences – related to the Data Mining and Machine Learning areas.

The Plackett-Luce model represents discrete choices from a set of items and it is often applied to rank aggregation problems.
The iterative majorization-minorization method is among the most relevant approaches for finding the maximum likelihood estimation of the parameters of the Plackett-Luce model, but its convergence might be slow. A noninformative initialization is usually adopted which assumes all items are equally relevant at the first step of the iterative inference process. This paper investigates the adoption of approximate inference methods which could allow a better initialization, leading to a smaller number of iterations required for the convergence of majorization-minorization. Two alternatives are adopted: a spectral inference method from the literature and also a novel approach based on a Poisson probabilistic model. Empirical evaluation is performed using synthetic and real-world datasets. It was revealed that initialization provided by an approximate method can lead to statistically significant reductions in both the number of iterations required and also in the overall computational time when compared to the scheme usually adopted for majorization-minorization.

On Improving the Efficiency of Majorization-Minorization for the Inference of Rank Aggregation Models

The Quadratic Assignment Problem (QAP) is an example of combinatorial optimization problem and it belongs to NP-hard class. QAP assigns interconnected facilities to locations while minimizing the cost of transportation of the flow of commodities between facilities. Hyper-Heuristics (HH) is a high-level approach that automatically selects or generates heuristics for solving complex problems.
In this paper is proposed the use of a selection HH to solve the multi-objective QAP (mQAP). This HH is based on the MOEA/DD (Evolutionary Many-Objective Optimization Algorithm Based on Dominance and Decomposition) and Choice Function strategy. The heuristics selected by HH correspond to the operators that generate new solutions in an iteration of the multi-objective evolutionary algorithm. IGD metric and statistical tests are applied in order to evaluate the algorithm performances in 22 mQAP instances. The effectiveness of the proposed method is shown and it is favorably compared with three other evolutionary multi-objective algorithms: IBEA, SMS-EMOA e MOEAD/DRA.

The main objective of nonlinear dynamic system identification is to model the behaviour of the systems under analysis from input-output signals.
To approach this problem, the Laguerre-Volterra network architecture combines the connectionist approach with Volterra-based processing to achieve good performances when modeling high-order nonlinearities, while retaining interpretability of the system's characteristics. 
In this research we assess the performances of three metaheuristics in the optimization of Laguerre-Volterra Networks using synthetic input-output data, a task in which only the simulated annealing metaheuristic was previously evaluated.

Evaluation of Metaheuristics in the Optimization of Laguerre-Volterra Networks for Nonlinear Dynamic System Identification

This article presents the cognitive model of the EvoLogic Intelligent Tutoring System, developed to assist in the teaching-learning process of Natural De-duction in Propositional Logic. EvoLogic consists of 3 agents, among which, the Pedagogical agent (treated here as the student model) and the Specialist agent (based on a Genetic Algorithm) compose the cognitive model. This cognitive model allows an efficient model tracing mechanism to be developed, which will follow each student's step during the theorem-proof. The purpose of the article, in addition to presenting the EvoLogic, is to analyze the efficiency of the ITS in a known exercise that has already been studied in the literature (applied to 57 students). The results show that the EvoLogic obtained all the solutions presented by the students, allowing it to follow the student's steps, providing real-time feedback, based on the steps that the students are taking (in real-time), known as model tracing.

EvoLogic: Intelligent Tutoring System to Teach Logic

Typically, an agent society is composed of at least three main components, namely, the set of its individual agents, the set of multi-agent organisations that help coordinate the actions of those agents, and the environment that those agents share. However, other levels have also been pointed out in the agent society literature, for example, the internal normative systems that regulate the structure and operation of the organisations themselves and, more generally, the overarching cultural system of the society. Many types of formal semantics for such systems, such as for example operational semantics, are not immediately suitable for systems that have ongoing operations at several architectural levels and requiring that those levels synchronise when particular events occur. This paper addresses this problem by proposing an approach to giving formal semantics to multi-level agent societies. The approach allows for the reuse of existing semantics for the separate levels, improves readability, and reduces the number of inference rules to be written.

A Multi-Level Approach to the Formal Semantics of Agent Societies

The Software Project Scheduling Problem (SPSP) aims to allocate employees to tasks in the development of a software project, such that the cost and duration, two conflicting goals, are minimized. The dynamic model of SPSP, called DSPSP, considers that some unpredictable events may occur during the project life cycle, like the arrival of new tasks, which implies on schedule updating along the project. In the context of Search-Based Software Engineering, this work proposes the use of dynamic optimization strategies, based on memory, together with the particle swarm optimization algorithm (PSO) to solve the DSPSP. The results suggest that the addition of these dynamic strategies improves the quality of the solutions in comparison with the application of the PSO algorithm only.

Dynamic Software Project Scheduling Problemwith PSO and Dynamic Strategies Based onMemory

Data clustering is one of the most primitive tasks in pattern recognition, although it is known to be a NP-hard grouping task. Given its complexity, standard clustering methods, such as the partitional data clustering algorithms, are easily trapped in local minimum solutions, due to their lack of good global searching mechanisms. Evolutionary Algorithms (EAs) and Swarm Intelligence (SIs) methods, such
as Group Search Optimization (GSO) and Backtracking Search Optimization (BSA), are commonly employed to deal with clustering task, given their capabilities to handle global search problems. In this work, a new hybrid evolutionary algorithm between GSO and BSA is presented, named BGSO, to tackle clustering problem, which combines the best features of GSO and the historical mechanisms of BSA. Also, BGSO is developed in the context of Automatic Clustering approach, which means that it is able to predict the best number of nal clusters, so no prior assumption about the data set at hand is required. The proposed approach is compared to standard GSO, BSA and other three EAs and SIs from the literature by means of nine real-world problems, showing promising results considering four clustering metrics.

Backtracking Group Search Optimization: A Hybrid Approach for Automatic Data Clustering

Real-world discrete problems are often also dynamic making them very challenging to be optimized. Here we focus on the employment of evolutionary algorithms to deal with such problems. In the last few years, many evolutionary optimization algorithms have investigated dynamic problems, being that some of the most recent papers investigate formulations with more than one objective to be optimized at the
same time. Although evolutionary optimization had revealed very competitive algorithms in different applications, both multiobjective formulations and dynamic problems need to apply specic strategies to perform well. In this work, we investigate four algorithms proposed for dynamic multiobjective problems: DNSGA-II, MOEA/D-KF, MS-MOEA and DNSGA-III. The rst three were previously proposed in the literature, where they were applied just in continuous problems. We aim to observe the behavior of these algorithms in a discrete problem: the Dynamic Multiobjective Knapsack Problems (DMKP). Our results have shown that some of them are also promising for applying to problems with discrete space.

Applying Dynamic Evolutionary Optimization to the Multiobjective Knapsack Problem

The physiological signs are a reliable source to identify stress states, and wearable sensors provide precise identification of physiological signs associated with the stress occurrence. The literature review shows that the use of physiological signs as a source for stress patterns identification is still a critical investigation subject. Few studies evaluate the effect of combining several different signals and the implications of the data acquisition procedures and details. The objective of this article is to investigate the possible integration of data obtained from heart rate variability (HFV), electrocardiographic (ECG), electrodermal activity (EDA) and electromyography (EMG) to detect stress patterns, considering a new experimental protocol to data acquisition. The data acquisition involved the Trier Social Stress Test (TSST), wearable sensor monitoring, and complementary stress perception instruments, resulting in a publicly available dataset. This dataset was evaluated using different machine learning classifiers, considering the obtained annotated data and exploring different physiological features and its combinations.

Evaluating a New Approach to Data Fusion in Wearable Physiological Sensors for Stress Monitoring

The aquatic environment is subject to a series of contaminants resulting from anthropogenic activity which may compromise biota health and the quality of water resources. There is an imperative need for cost-effective, accurate and online solutions for monitoring aquatic environments. The present work proposes the construction of aquatic pollution biosensors for detecting both petrochemical and anti-fouling paint compounds based on the behavioral analysis of Perna perna mussels through multiple classifier systems. Networks of mussels instrumented with Hall effect sensors and magnets were exposed to Water-Accommodated Fraction of diesel and micro-particles of anti-fouling paint. The hourly behavioral parameters average amplitude, transition frequency and amount of motion reversals were used to infer the contamination status (polluted or not) through voting classifiers. Results presented high accuracy (95.8%) in predicting diesel pollution and non-pollution while lack of data and intrinsic characteristics of anti-fouling paints provided less significant results for detecting its compounds. This paper has demonstrated a promising use of artificial intelligence in the construction of aquatic pollution biosensors using behavioral analysis of bivalve mollusks.

Entropy-Based Filter Selection in CNNs Applied to Text Classification

Downloads

Next from BRACIS 2020

On Improving the Efficiency of Majorization-Minorization for the Inference of Rank Aggregation Models

Similar lecture

Crowdsourced Verification for Operating Calving Surveillance Systems at an Early Stage

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Entropy-Based Filter Selection in CNNs Applied to Text Classification

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from BRACIS 2020

On Improving the Efficiency of Majorization-Minorization for the Inference of Rank Aggregation Models

Similar lecture

Crowdsourced Verification for Operating Calving Surveillance Systems at an Early Stage

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads