|Danilo Vasconcellos Vargas||Last modified date：2022.11.08|
Associate Professor / Faculty of Information Science and Electrical Engineering, Kyushu University / Department of Informatics / Faculty of Information Science and Electrical Engineering
|1.||D. V. Vargas and J. Lauwereyns, “Setting the space for deliberation in decision-making”, Cognitive Neurodynamics, 2021.04, Decision-making models in the behavioral, cognitive, and neural sciences typically consist of forced-choice paradigms with two alternatives. While theoretically it is feasible to translate any decision situation to a sequence of binary choices, real-life decision-making is typically more complex and nonlinear, involving choices among multiple items, graded judgments, and deferments of decision-making. Here, we discuss how the complexity of real-life decision-making can be addressed using conventional decision-making models by focusing on the interactive dynamics between criteria settings and the collection of evidence. Decision-makers can engage in multi-stage, parallel decision-making by exploiting the space for deliberation, with non-binary readings of evidence available at any point in time. The interactive dynamics principally adhere to the speed-accuracy tradeoff, such that increasing the space for deliberation enables extended data collection. The setting of space for deliberation reflects a form of meta-decision-making that can, and should be, studied empirically as a value-based exercise that weighs the prior propensities, the economics of information seeking, and the potential outcomes. Importantly, the control of the space for deliberation raises a question of agency. Decision-makers may actively and explicitly set their own decision parameters, but these parameters may also be set by environmental pressures. Thus, decision-makers may be influenced—or nudged in a particular direction—by how decision problems are framed, with a sense of urgency or a binary definition of choice options. We argue that a proper understanding of these mechanisms has important practical implications toward the optimal usage of space for deliberation..|
|2.||Y. Jiang (South China University of Technology) and D. V. Vargas,, “Preliminary Results for Subpopulation Algorithm Based on Novelty (SAN) Compared with the State of the Art”, IEEE CYBCONF 2021, 2021.04.|
|3.||S. Gaysornkaew, D. V. Vargas and F. Tsumori,, “Parameter Optimization via CMA-ES for Implementation in the Active Control of Magnetic Pillar Arrays”, IEEE CYBCONF 2021, 2021.04.|
|4.||Y. F. Tham and D. V. Vargas,, “Towards learning Hierarchical Structures with SyncMap”, IEEE CYBCONF 2021, 2021.04.|
|5.||L. Bingli, T. Kanzaki and D. V. Vargas,, “Towards Understanding The Space of Unrobust Features of Neural Networks”, IEEE CYBCONF 2021, 2021.04.|
|6.||S. Kotyan and D. V. Vargas, , “Deep neural network loses attention to adversarial images”, AISafety Workshop (AISafety 2021), 2021.05.|
|7.||Po-Yuan Mao and Danilo Vasconcellos Vargas, “Preliminary results on Chunking with Recurrent Neural Networks”, SICE 2021, 2021.07.|
|8.||T. Ueda and D. V. Vargas, Towards Evaluating the Representation Learned by Variational AutoEncoders, SICE 2021, 2021.07.|
|9.||S. Kotyan and D. V. Vargas,, Adversarial Robustness Assessment: Why both L0 and L∞ Attacks Are Necessary, PLOS One, 2022.04.|
|10.||S. Kotyan, M. Matsuki, and D. V. Vargas, Transferability Of Features For Neural Networks Links To Adversarial Attacks and Defences, PLOS One, 2022.04.|
|11.||D. V. Vargas, T. Asabuki, Continual General Chunking Problem and SyncMap, AAAI 2021, 2020.12, Humans possess an inherent ability to chunk sequences into their constituent parts. In fact, this ability is thought to bootstrap language skills and learning of image patterns which might be a key to a more animal-like type of intelligence. Here, we propose a continual generalization of the chunking problem (an unsupervised problem), encompassing fixed and probabilistic chunks, discovery of temporal and causal structures and their continual variations. Additionally, we propose an algorithm called SyncMap that can learn and adapt to changes in the problem by creating a dynamic map which preserves the correlation between variables. Results of SyncMap suggest that the proposed algorithm learn near optimal solutions, despite the presence of many types of structures and their continual variation. When compared to Word2vec, PARSER and MRIL, SyncMap surpasses or ties with the best algorithm on 66% of the scenarios while being the second best in the remaining 34%. SyncMap's model-free simple dynamics and the absence of loss functions reveal that, perhaps surprisingly, much can be done with self-organization alone..|
|12.||Valencia R., Sham, B., D. V. Vargas, Preliminary study of applied Binary Neural Networks for Neural Cryptography, GECCO 2020, 2020.07.|
|13.||Shashank Kotayan, D. V. Vargas, Towards Evolving Robust Neural Architectures to Defend from Adversarial Attacks, GECCO 2020, 2020.07.|
|14.||Anh Duc Ta, D. V. Vargas, Towards improvement of SUNA in Multiplexers with preliminary results of simple Logic Gate neuron variation, GECCO 2020, 2020.07.|
|15.||Shashank Kotayan, D. V. Vargas, Is Neural Architecture Search A Way Forward to Develop Robust Neural Networks?, 人工知能学会全国大会 (JSAI 2020), 2020.06.|
|16.||D. V. Vargas, Jiawei Su, Understanding the one-pixel attack: Propagation maps and locality analysis, AIsafety workshop (AIsafety 2020), 2020.06.|
|17.||Shashank Kotayan, D. V. Vargas, Evolving Robust Neural Architectures to Defend from Adversarial Attacks, AIsafety workshop (AIsafety 2020), 2020.06.|
|18.||Steven Van Uytsel, Danilo Vasconcellos Vargas, Adversarial Machine Learning
A Blow to the Transportation Sharing Economy, Perspectives in Law, Business and Innovation, 10.1007/978-981-15-1350-3_11, 179-208, 2020.01, Adversarial machine learning has indicated that perturbations to a picture may disable a deep neural network from correctly qualifying the content of a picture. The progressing research has even revealed that the perturbations do not necessarily have to be large in size. This research has been transplanted to traffic signs. The test results were disastrous. For example, a perturbated stop sign was recognized as a speeding sign. Because visualization technology is not able to overcome this problem yet, the question arises who should be liable for accidents caused by this technology. Manufacturers are being pointed at and for that reason it has been claimed that the commercialization of autonomous vehicles may stall. Without autonomous vehicles, the sharing economy may not fully develop either. This chapter shows that there are alternatives for the unpredictable financial burden on the car manufacturers for accidents with autonomous cars. This chapter refers to operator liability, but argues that for reasons of fairness, this is not a viable choice. A more viable choice is a no-fault liability on the manufacturer, as this kind of scheme forces the car manufacturer to be careful but keeps the financial risk predicable. Another option is to be found outside law. Engineers could build infrastructure enabling automation. Such infrastructure may overcome the problems of the visualization technology, but could potentially create a complex web of product and service providers. Legislators should prevent that the victims of an accident, if it were still to occur, would face years in court with the various actors of this complex web in order to receive compensation..
|19.||Danilo Vasconcellos Vargas, One-Pixel Attack: Understanding and Improving Deep Neural Networks with Evolutionary Computation. In Deep Neural Evolution, Deep Neural Evolution, 2020.01, [URL].|
|20.||Jiawei Su, Danilo Vasconcellos Vargas, Kouichi Sakurai, One Pixel Attack for Fooling Deep Neural Networks, IEEE Transactions on Evolutionary Computation, 10.1109/TEVC.2019.2890858, 23, 5, 828-841, 2019.10, Recent research has revealed that the output of deep neural networks (DNNs) can be easily altered by adding relatively small perturbations to the input vector. In this paper, we analyze an attack in an extremely limited scenario where only one pixel can be modified. For that we propose a novel method for generating one-pixel adversarial perturbations based on differential evolution (DE). It requires less adversarial information (a black-box attack) and can fool more types of networks due to the inherent features of DE. The results show that 67.97% of the natural images in Kaggle CIFAR-10 test dataset and 16.04% of the ImageNet (ILSVRC 2012) test images can be perturbed to at least one target class by modifying just one pixel with 74.03% and 22.91% confidence on average. We also show the same vulnerability on the original CIFAR-10 dataset. Thus, the proposed attack explores a different take on adversarial machine learning in an extreme limited scenario, showing that current DNNs are also vulnerable to such low dimension attacks. Besides, we also illustrate an important application of DE (or broadly speaking, evolutionary computation) in the domain of adversarial machine learning: creating tools that can effectively generate low-cost adversarial attacks against neural networks for evaluating robustness..|
|21.||Lia T. Parsenadze, Danilo Vasconcellos Vargas, Toshiyuki Fujita, Linear Subspace Paradigm: An Investigation on a Novel Paradigm for Optimizing Deep Neural Networks, EUROGEN 2019, 2019.09.|
|22.||Shashank Kotayan, Danilo Vasconcellos Vargas, Venkanna U, Self-Training Autonomous Driving Agent, SICE 2019, 2019.09.|
|23.||Lia T. Parsenadze, Danilo Vasconcellos Vargas, Toshiyuki Fujita, Towards Solving Neural Networks with Optimization Trajectory Search, GECCO (Companion) 2019, 2019.09.|
|24.||Danilo Vasconcellos Vargas, Hiroaki Yoshioka, Daisuke Nakamura, Takatsugu Ono, Naoya Tate, Towards Evolutionary-based Classifiers Implemented with an Optical Fluorescent Voxels System, Optics and Photonics International Congress 2019, 2019.09.|
|25.||Vinicius Veloso de Melo, Danilo Vasconcellos Vargas, Wolfgang Banzhaf , Batch Tournament Selection for Genetic Programming, GECCO 2019, 2019.09.|
|26.||Di Li, Danilo Vasconcellos Vargas, Sakurai Kouichi, Universal Rules for Fooling Deep Neural Networks based Text Classification, In IEEE Congress on Evolutionary Computation (CEC) 2019, 2019.09.|
|27.||Jiawei Su, Danilo Vasconcellos Vargas, Kouichi Sakurai, Attacking convolutional neural network using differential evolution, IPSJ Transactions on Computer Vision and Applications, 10.1186/s41074-019-0053-3, 11, 1, 2019.02, The output of convolutional neural networks (CNNs) has been shown to be discontinuous which can make the CNN image classifier vulnerable to small well-tuned artificial perturbation. That is, images modified by conducting such alteration (i.e., adversarial perturbation) that make little difference to the human eyes can completely change the CNN classification results. In this paper, we propose a practical attack using differential evolution (DE) for generating effective adversarial perturbations. We comprehensively evaluate the effectiveness of different types of DEs for conducting the attack on different network structures. The proposed method only modifies five pixels (i.e., few-pixel attack), and it is a black-box attack which only requires the miracle feedback of the target CNN systems. The results show that under strict constraints which simultaneously control the number of pixels changed and overall perturbation strength, attacking can achieve 72.29%, 72.30%, and 61.28% non-targeted attack success rates, with 88.68%, 83.63%, and 73.07% confidence on average, on three common types of CNNs. The attack only requires modifying five pixels with 20.44, 14.28, and 22.98 pixel value distortion. Thus, we show that current deep neural networks are also vulnerable to such simpler black-box attacks even under very limited attack conditions..|
|28.||Wai Kyi Kyi Oo, Hiroshi Koide, Danilo Vasconcellos Vargas, Kouichi Sakurai, A new design for evaluating moving target defense system, 6th International Symposium on Computing and Networking Workshops, CANDARW 2018 Proceedings - 2018 6th International Symposium on Computing and Networking Workshops, CANDARW 2018, 10.1109/CANDARW.2018.00111, 561-563, 2018.12, Moving Target Defense (MTD) concept has been a feasible idea for reducing the possibility of attack happening through alternation attack surfaces or diversification the attribute or parameters of a protected system. As a result of applying MTD techniques to the system, an attacker would have more difficulties in exploiting a vulnerabilities of the target system. This study proposes an evaluation method of MTD systems combined with several different MTD techniques. The proposed method is a primary step in designing an evaluation model for the effectiveness of MTD. The main goal is to estimate the attack success ratio on the MTD systems mitigating from threats of executable binary file or malware injection. With the proposed evaluation method, we expect to prove that the MTD technology can enhance the security of a web server, and can be applied in a real-world information system. As our preliminary work done, we set up a prototype framework to validate the proposed work in a pseudo-experimental environment..|
|29.||Jiawei Su, Danilo Vasconcellos Vargas, Kouichi Sakurai, Empirical evaluation on robustness of deep convolutional neural networks activation functions against adversarial perturbation, 6th International Symposium on Computing and Networking Workshops, CANDARW 2018 Proceedings - 2018 6th International Symposium on Computing and Networking Workshops, CANDARW 2018, 10.1109/CANDARW.2018.00049, 223-227, 2018.12, Recent research has shown that deep convolutional neural networks (DCNN) are vulnerable to several different types of attacks while the reasons of such vulnerability are still under investigation. For instance, the adversarial perturbations can conduct a slight change on a natural image to make the target DCNN make the wrong recognition, while the reasons that DCNN is sensitive to such small modification are divergent from one research to another. In this paper, we evaluate the robustness of two commonly used activation functions of DCNN, namely the sigmoid and ReLu, against the recently proposed low-dimensional one-pixel attack. We show that the choosing of activation functions can be an important factor that influences the robustness of DCNN. The results show that comparing with sigmoid, the ReLu non-linearity is more vulnerable which allows the low dimensional one-pixel attack exploit much higher success rate and confidence of launching the attack. The results give insights on designing new activation functions to enhance the security of DCNN..|
|30.||Yuetong Zhu, Danilo Vasconcellos Vargas, Kouichi Sakurai, Neural cryptography based on the topology evolving neural networks, 6th International Symposium on Computing and Networking Workshops, CANDARW 2018 Proceedings - 2018 6th International Symposium on Computing and Networking Workshops, CANDARW 2018, 10.1109/CANDARW.2018.00091, 472-478, 2018.12, Modern cryptographic schemes is developed based on the mathematical theory. Recently works show a new direction about cryptography based on the neural networks. Instead of learning a specific algorithm, a cryptographic scheme is generated automatically. While one kind of neural network is used to achieve the scheme, the idea of the neural cryptography can be realized by other neural network architecture is unknown. In this paper, we make use of this property to create neural cryptography scheme on a new topology evolving neural network architecture called Spectrum-diverse unified neuroevolution architecture. First, experiments are conducted to verify that Spectrum-diverse unified neuroevolution architecture is able to achieve automatic encryption and decryption. Subsequently, we do experiments to achieve the neural symmetric cryptosystem by using adversarial training..|
|31.||Yao Xu, Hiroshi Koide, Danilo Vasconcellos Vargas, Kouichi Sakurai, Tracing MIRAI malware in networked system, 6th International Symposium on Computing and Networking Workshops, CANDARW 2018 Proceedings - 2018 6th International Symposium on Computing and Networking Workshops, CANDARW 2018, 10.1109/CANDARW.2018.00104, 534-538, 2018.12, In 2021, it is anticipated that there will be approximately 30 billion Internet of Things (IoT) devices. The tremendous aggregate value of the IoT makes it a tempting and lucrative target for cyber criminals. The breakout of Mirai malware, which compromises poorly secured IoT devices with factory-default username and passphrase to launch Distributed Denial of Service (DDoS) attacks, has raised broad awareness towards the need for increased IoT security. To better defend against Mirai infection and spread, it is critical to know how the malware operates as the first step. In this paper, we give a combined static and dynamic analysis of Mirai, basing on the results of which, we introduce the application of Threat Tracer. Threat tracer is an information system simulator initially developed to help design a system robust against Advanced Persistent Attacks(APT). It offers an intuitive track on how a cyber threat behaves in a complicated networked system. The feedback simultaneously contributes to revealing vulnerabilities of a system. Our work focuses on the replication of Mirai Malware's operating processes in Threat Tracer simulation. By achieving doing so, we believe it could offer a comprehensible description of how Mirai acts. Also, considering the continuous emergence of Mirai variants, the simulation serves as a predictor on upcoming threats' behavior patterns..|
|32.||Ryan J. Urbanowicz, Danilo Vasconcellos Vargas, Introducing learning classifier systems
Rules that capture complexity, 2018 Genetic and Evolutionary Computation Conference, GECCO 2018 GECCO 2018 Companion - Proceedings of the 2018 Genetic and Evolutionary Computation Conference Companion, 10.1145/3205651.3207869, 619-648, 2018.07.
|33.||Jiawei Su, Danilo Vasconcellos Vargas, Sanjiva Prasad, Sgandurra Daniele, Yaokai Feng, Kouichi Sakurai, Lightweight Classification of IoT Malware Based on Image Recognition, 42nd IEEE Computer Software and Applications Conference, COMPSAC 2018 Proceedings - 2018 IEEE 42nd Annual Computer Software and Applications Conference, COMPSAC 2018, 10.1109/COMPSAC.2018.10315, 664-669, 2018.06, The Internet of Things (IoT) is an extension of the traditional Internet, which allows a very large number of smart devices, such as home appliances, network cameras, sensors and controllers to connect to one another to share information and improve user experiences. IoT devices are micro-computers for domain-specific computations rather than traditional functionspecific embedded devices. This opens the possibility of seeing many kinds of existing attacks, traditionally targeted at the Internet, also directed at IoT devices. As shown by recent events, such as the Mirai and Brickerbot botnets, DDoS attacks have become very common in IoT environments as these lack basic security monitoring and protection mechanisms. In this paper, we propose a novel light-weight approach for detecting DDos malware in IoT environments. We extract the malware images (i.e., a one-channel gray-scale image converted from a malware binary) and utilize a light-weight convolutional neural network for classifying their families. The experimental results show that the proposed system can achieve 94:0% accuracy for the classification of goodware and DDoS malware, and 81:8% accuracy for the classification of goodware and two main malware families..|
|34.||Shiqian Yu, Danilo Vasconcellos Vargas, Kouichi Sakurai, Effectively Protect Your Privacy
Enabling Flexible Privacy Control on Web Tracking, 5th International Symposium on Computing and Networking, CANDAR 2017 Proceedings - 2017 5th International Symposium on Computing and Networking, CANDAR 2017, 10.1109/CANDAR.2017.26, 533-536, 2018.04, Third-party tracking, which can collect the users' privacy when users are surfing the Internet, has garnered much attention. Nowadays tracker-blocking tools often use a ruleset based on the domains and elements that need to be blocked. This results in blocking all access tracking, even though the website shows no sign about tracking users' privacy. And what's more, although the tracker-blocking tools try their best to block all the third-party tracking, not all the users dislike the advertisement. Some of them think if their privacy is fine, it's all right to accept advertisements. In this paper, we present a novel framework by using Word2Vec to block third-party tracking. Our goal is to create more flexible and well-developed ruleset that can help users to protect their privacy according to their needs. Instead of blocking all access tracking, we decide to pay more attention to the websites that have a strong probability to collect the users' privacy. We use Word2Vec to classify the websites, and our results show that after using our framework, the error rate drops from 71% to 24%. We believe it brings the new blood into the field of web privacy by providing not only the new third-party tracking tool but also a novel way of thinking about how to block the third-party tracking..
|35.||Danilo Vasconcellos Vargas, Junichi Murata, Spectrum-diverse neuroevolution with unified neural models, IEEE Transactions on Neural Networks and Learning Systems, 10.1109/TNNLS.2016.2551748, 28, 8, 1759-1773, 2017.08, Learning algorithms are being increasingly adopted in various applications. However, further expansion will require methods that work more automatically. To enable this level of automation, a more powerful solution representation is needed. However, by increasing the representation complexity, a second problem arises. The search space becomes huge, and therefore, an associated scalable and efficient searching algorithm is also required. To solve both the problems, first a powerful representation is proposed that unifies most of the neural networks features from the literature into one representation. Second, a new diversity preserving method called spectrum diversity is created based on the new concept of chromosome spectrum that creates a spectrum out of the characteristics and frequency of alleles in a chromosome. The combination of spectrum diversity with a unified neuron representation enables the algorithm to either surpass or equal NeuroEvolution of Augmenting Topologies on all of the five classes of problems tested. Ablation tests justify the good results, showing the importance of added new features in the unified neuron representation. Part of the success is attributed to the novelty-focused evolution and good scalability with a chromosome size provided by spectrum diversity. Thus, this paper sheds light on a new representation and diversity preserving mechanism that should impact algorithms and applications to come..|
|36.||Danilo Vasconcellos Vargas, Kouichi Sakurai, A Brief Review on Anomaly Detection and its Applications to Cybersecurity (情報通信システムセキュリティ), IEICE technical report, 116, 522, 37-42, 2017.03.|
|38.||Danilo Vasconcellos Vargas, Junichi Murata, Curious
Searching for unknown regions of space with a subpopulation-based algorithm, 2016 Genetic and Evolutionary Computation Conference, GECCO 2016 Companion GECCO 2016 Companion - Proceedings of the 2016 Genetic and Evolutionary Computation Conference, 10.1145/2908961.2908982, 145-146, 2016.07, Intrinsic motivation and novelty search are promising approaches to deal with plateaus, deceptive functions and other exploration problems where using only the main objective function is insufficient. However, it is not clear until now how and if intrinsic motivation (novelty search) can improve single objective algorithms in general. The hurdle is that using multi-objective algorithms to deal with single-objective problems adds an unnecessary overhead such as the search for non-dominated solutions. Here, we propose the Curious algorithm which is the first multi-objective algorithm focused on solving single-objective problems. Curious uses two subpopulations algorithms. One subpopulation is dedicated for improving objective function values and another one is added to search for unknown regions of space based on objective prediction errors. By using a differential evolution operator, genes from individuals in all subpopulations are mixed. In this way, the promising regions (solutions with high fitness) and unknown regions (solutions with high prediction error) are searched simultaneously. Because of thus realized strong yet well controlled novelty search, the algorithm possesses powerful exploration ability and outperforms usual single population based algorithms such as differential evolution. Thus, it demonstrates that the addition of intrinsic motivation is promising and should improve further single objective algorithms in general..
|39.||Danilo Vasconcellos Vargas, Hirotaka Takano, Junichi Murata, Novelty-Organizing Team of Classifiers in noisy and dynamic environments, IEEE Congress on Evolutionary Computation, CEC 2015 2015 IEEE Congress on Evolutionary Computation, CEC 2015 - Proceedings, 10.1109/CEC.2015.7257254, 2937-2944, 2015.09, In the real world, the environment is constantly changing with the input variables under the effect of noise. However, few algorithms were shown to be able to work under those circumstances. Here, Novelty-Organizing Team of Classifiers (NOTC) is applied to the continuous action mountain car as well as two variations of it: A noisy mountain car and an unstable weather mountain car. These problems take respectively noise and change of problem dynamics into account. Moreover, NOTC is compared with NeuroEvolution of Augmenting Topologies (NEAT) in these problems, revealing a trade-off between the approaches. While NOTC achieves the best performance in all of the problems, NEAT needs less trials to converge. It is demonstrated that NOTC achieves better performance because of its division of the input space (creating easier problems). Unfortunately, this division of input space also requires a bit of time to bootstrap..|
|40.||Danilo Vasconcellos Vargas, Hirotaka Takano, Junichi Murata, The relationship between (Un)fractured problems and division of input space, 17th Genetic and Evolutionary Computation Conference, GECCO 2015 GECCO 2015 - Companion Publication of the 2015 Genetic and Evolutionary Computation Conference, 10.1145/2739482.2768447, 981-987, 2015.07, Problems can be categorized as fractured or unfractured ones. A different set of characteristics are needed for learning algorithms to solve each of these two types of problems. However, the exact characteristics needed to solve each type are unclear. This article shows that the division of the input space is one of these characteristics. In other words, a study is presented showing that while fractured problems benefit from a finer division of the input space, unfractured problems benefit from a coarser division of input space. Many open questions still remains. And the article discusses two conjectures which can be used to solve fractured problems more easily..|
|41.||Danilo Vasconcellos Vargas, Junichi Murata, Hirotaka Takano, Alexandre Cláudio Botazzo Delbem, General subpopulation framework and taming the conflict inside populations, Evolutionary Computation, 10.1162/EVCO_a_00118, 23, 1, 1-36, 2015.03, Structured evolutionary algorithms have been investigated for some time. However, they have been under explored especially in the field of multi-objective optimization. Despite good results, the use of complex dynamics and structures keep the understanding and adoption rate of structured evolutionary algorithms low. Here, we propose a general subpopulation framework that has the capability of integrating optimization algorithms without restrictions as well as aiding the design of structured algorithms. The proposed framework is capable of generalizing most of the structured evolutionary algorithms, such as cellular algorithms, island models, spatial predator-prey, and restricted mating based algorithms. Moreover, we propose two algorithms based on the general subpopulation framework, demonstrating that with the simple addition of a number of single-objective differential evolution algorithms for each objective, the results improve greatly, even when the combined algorithms behave poorly when evaluated alone at the tests. Most importantly, the comparison between the subpopulation algorithms and their related panmictic algorithms suggests that the competition between different strategies inside one population can have deleterious consequences for an algorithm and reveals a strong benefit of using the subpopulation framework..|
|42.||Danilo Vasconcellos Vargas, Hirotaka Takano, Junichi Murata, Novelty-organizing team of classifiers - A team-individual multi-objective approach to reinforcement learning, 2014 53rd Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2014 Proceedings of the SICE Annual Conference, 10.1109/SICE.2014.6935299, 1785-1792, 2014.10, In reinforcement learning, there are basically two spaces to search: value-function space and policy space. Consequently, there are two fitness functions each with their associated trade-offs. However, the problem is still perceived as a single-objective one. Here a multi-objective reinforcement learning algorithm is proposed with a structured novelty map population evolving feedforward neural models. It outperforms a gradient based continuous input-output state-of-art algorithm in two problems. Contrary to the gradient based algorithm, the proposed one solves both problems with the same parameters and smaller variance of results. Moreover, the results are comparable even with other discrete action algorithms of the literature as well as neuroevolution methods such as NEAT. The proposed method brings also the novelty map population concept, i.e., a novelty map-based population which is less sensitive to the input distribution and therefore more suitable to create the state space. In fact, the novelty map framework is shown to be less dynamic and more resource efficient than variants of the self-organizing map..|
|43.||Danilo Vasconcellos Vargas, Hirotaka Takano, Junichi Murata, Novelty-Organizing Classifiers applied to classification and reinforcement learning
Towards flexible algorithms, 16th Genetic and Evolutionary Computation Conference, GECCO 2014 GECCO 2014 - Companion Publication of the 2014 Genetic and Evolutionary Computation Conference, 10.1145/2598394.2598429, 81-82, 2014, It is widely known that reinforcement learning is a more general problem than supervised learning. In fact, supervised learning can be seen as a class of reinforcement learning problems. However, only a couple of papers tested reinforcement learning algorithms in supervised learning problems. Here we propose a new and simpler way to abstract supervised learning for any reinforcement learning algorithm. Moreover, a new algorithm called Novelty-Organizing Classifiers is developed based on a Novelty Map population that focuses more on the novelty of the inputs than their frequency. A comparison of the proposed method with Self-Organizing Classifiers and BioHel on some datasets is presented. Even though BioHel is specialized in solving supervised learning problems, the results showed only a trade-off between the algorithms. Lastly, results on a maze problem validate the flexibility of the proposed algorithm beyond supervised learning problems. Thus, Novelty-Organizing Classifiers is capable of solving many supervised learning problems as well as a maze problem without changing any parameter at all. Considering the fact that no adaptation of parameters was executed, the proposed algorithm's basis seems interestingly flexible..
|44.||Danilo Vasconcellos Vargas, Hirotaka Takano, Junichi Murata, Self organizing classifiers
First steps in structured evolutionary machine learning, Evolutionary Intelligence, 10.1007/s12065-013-0095-x, 6, 2, 57-72, 2013.11, Learning classifier systems (LCSs) are evolutionary machine learning algorithms, flexible enough to be applied to reinforcement, supervised and unsupervised learning problems with good performance. Recently, self organizing classifiers were proposed which are similar to LCSs but have the advantage that in its structured population no balance between niching and fitness pressure is necessary. However, more tests and analysis are required to verify its benefits. Here, a variation of the first algorithm is proposed which uses a parameterless self organizing map (SOM). This algorithm is applied in challenging problems such as big, noisy as well as dynamically changing continuous input-action mazes (growing and compressing mazes are included) with good performance. Moreover, a genetic operator is proposed which utilizes the topological information of the SOM's population structure, improving the results. Thus, the first steps in structured evolutionary machine learning are shown, nonetheless, the problems faced are more difficult than the state-of-art continuous input-action multi-step ones..
|45.||Danilo Vasconcellos Vargas, Hirotaka Takano, Junichi Murata, Self organizing classifiers and niched fitness, 2013 15th Genetic and Evolutionary Computation Conference, GECCO 2013 GECCO 2013 - Proceedings of the 2013 Genetic and Evolutionary Computation Conference, 10.1145/2463372.2463501, 1109-1116, 2013.09, Learning classifier systems are adaptive learning systems which have been widely applied in a multitude of application domains. However, there are still some generalization problems unsolved. The hurdle is that fitness and niching pressures are difficult to balance. Here, a new algorithm called Self Organizing Classifiers is proposed which faces this problem from a different perspective. Instead of balancing the pressures, both pressures are separated and no balance is necessary. In fact, the proposed algorithm possesses a dynamical population structure that self-organizes itself to better project the input space into a map. The niched fitness concept is defined along with its dynamical population structure, both are indispensable for the understanding of the proposed method. Promising results are shown on two continuous multi-step problems. One of which is yet more challenging than previous problems of this class in the literature..|
|46.||Danilo Vasconcellos Vargas, 高野 浩貴, 村田 純一, The Motivation behind Low Dimensional Weak Learners Extends to Ensembles of Decision Trees (システム研究会 インテリジェント・システム・シンポジウム(FANシンポジウム)), 電気学会研究会資料. SA, 静止器研究会, 2013, 29, 23-26, 2013.09.|
|47.||Vinícius Veloso de Melo, Danilo Vasconcellos Vargas, Marcio Kassouf Crocomo, Phylogenetic Differential Evolution, Natural Computing for Simulation and Knowledge Discovery, 10.4018/978-1-4666-4253-9.ch002, 22-40, 2013.07, This paper presents a new technique for optimizing binary problems with building blocks. The authors have developed a different approach to existing Estimation of Distribution Algorithms (EDAs). Our technique, called Phylogenetic Differential Evolution (PhyDE), combines the Phylogenetic Algorithm and the Differential Evolution Algorithm. The first one is employed to identify the building blocks and to generate metavariables. The second one is used to find the best instance of each metavariable. In contrast to existing EDAs that identify the related variables at each iteration, the presented technique finds the related variables only once at the beginning of the algorithm, and not through the generations. This paper shows that the proposed technique is more efficient than the well known EDA called Extended Compact Genetic Algorithm (ECGA), especially for large-scale systems which are commonly found in real world problems..|
|48.||Danilo Vasconcellos Vargas, Hirotaka Takano, Junichi Murata, A study on the importance of selection pressure and low dimensional weak learners to produce robust ensembles, 15th Annual Conference on Genetic and Evolutionary Computation, GECCO 2013 GECCO 2013 - Proceedings of the 2013 Genetic and Evolutionary Computation Conference Companion, 10.1145/2464576.2480775, 1755-1756, 2013, Ensembles of classifiers have been studied for some time. It is widely known that weak learners should be accurate and diverse. However, in the real world there are many constraints and few have been said about the robustness of ensembles and how to develop it. In the context of ran- dom subspace methods, this paper addresses the question of developing ensembles to face problems under time con- straints. Experiments show that selecting weak learners based on their accuracy can be used to create robust en- sembles. Thus, the selection pressure in ensembles is a key technique to create not just effective ensembles but also robust ones. Moreover, the experiments motivate further research on ensembles made of low dimensional classifiers which achieve general accurate results..|
|49.||Danilo Vasconcellos Vargas, Hirotaka Takano, Junichi Murata, Contingency training, 2013 52nd Annual Conference of the Society of Instrument and Control Engineers of Japan, SICE 2013 SICE 2013: International Conference on Instrumentation, Control, Information Technology and System Integration - SICE Annual Conference 2013, Conference Proceedings, 1361-1366, 2013, When applied to high-dimensional datasets, feature selection algorithms might still leave dozens of irrelevant variables in the dataset. Therefore, even after feature selection has been applied, classifiers must be prepared to the presence of irrelevant variables. This paper investigates a new training method called Contingency Training which increases the accuracy as well as the robustness against irrelevant attributes. Contingency training is classifier independent. By subsampling and removing information from each sample, it creates a set of constraints. These constraints aid the method to automatically find proper importance weights of the dataset's features. Experiments are conducted with the contingency training applied to neural networks over traditional datasets as well as datasets with additional irrelevant variables. For all of the tests, contingency training surpassed the unmodified training on datasets with irrelevant variables and even outperformed slightly when only a few or no irrelevant variables were present..|
|50.||Danilo Vasconcellos Vargas, Hirotaka Takano, Junichi Murata, Continuous adaptive reinforcement learning with the evolution of Self Organizing Classifiers, 2013 IEEE 3rd Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL 2013 2013 IEEE 3rd Joint International Conference on Development and Learning and Epigenetic Robotics, ICDL 2013 - Electronic Conference Proceedings, 10.1109/DevLrn.2013.6652558, 2013, Learning classifier systems have been solving reinforcement learning problems for some time. However, they face difficulties under multi-step continuous problems. Adaptation may also become harder with time since the convergence of the population decreases its diversity. This article demonstrate that the novel Self Organizing Classifiers method can cope with dynamical multi-step continuous problems. Moreover, adaptation remains the same after convergence..|
|51.||Jean Paulo Martins, Antonio Helson Mineiro Soares, Danilo Vasconcellos Vargas, Alexandre Cláudio Botazzo Delbem, Multi-objective phylogenetic algorithm
Solving multi-objective decomposable deceptive problems, 6th International Conference on Evolutionary Multi-Criterion Optimization, EMO 2011 Evolutionary Multi-Criterion Optimization - 6th International Conference, EMO 2011, Proceedings, 10.1007/978-3-642-19893-9_20, 285-297, 2011.04, In general, Multi-objective Evolutionary Algorithms do not guarantee find solutions in the Pareto-optimal set. We propose a new approach for solving decomposable deceptive multi-objective problems that can find all solutions of the Pareto-optimal set. Basically, the proposed approach starts by decomposing the problem into subproblems and, then, combining the found solutions. The resultant approach is a Multi-objective Estimation of Distribution Algorithm for solving relatively complex multi-objective decomposable problems, using a probabilistic model based on a phylogenetic tree. The results show that, for the tested problem, the algorithm can efficiently find all the solutions of the Pareto-optimal set, with better scaling than the hierarchical Bayesian Optimization Algorithm and other algorithms of the state of art..
Unauthorized reprint of the contents of this database is prohibited.