Danilo Vasconcellos Vargas

Kyushu University | Kyudai · Department of Informatics

p>In the realm of RPGs, creating immersive, persona-driven dialogues remains a challenge, especially in intricate settings like Call of Cthulhu (CoC). Existing methodologies often falter in portraying character personas within complex conversations accurately. To address this, we introduce a novel card-based framework, utilizing the advanced Baichu...

p>In the realm of RPGs, creating immersive, persona-driven dialogues remains a challenge, especially in intricate settings like Call of Cthulhu (CoC). Existing methodologies often falter in portraying character personas within complex conversations accurately. To address this, we introduce a novel card-based framework, utilizing the advanced Baichu...

Reservoir computing (RC), first applied to temporal signal processing, is a recurrent neural network in which neurons are randomly connected. Once initialized, the connection strengths remain unchanged. Such a simple structure turns RC into a non-linear dynamical system that maps low-dimensional inputs into a high-dimensional space. The model's ric...

This paper presents a method for reproducing a simple central pattern generator (CPG) using a modified Echo State Network (ESN). Conventionally, the dynamical reservoir needs to be damped to stabilize and preserve memory. However, we find that a reservoir that develops oscillatory activity without any external excitation can mimic the behaviour of...

Self-organization is ubiquitous in nature and mind. However, machine learning and theories of cognition still barely touch the subject. The hurdle is that general patterns are difficult to define in terms of dynamical equations and designing a system that could learn by reordering itself is still to be seen. Here, we propose a learning system, wher...

Reservoir computing (RC), first applied to temporal signal processing, is a recurrent neural network in which neurons are randomly connected. Once initialized, the connection strengths remain unchanged. Such a simple structure turns RC into a non-linear dynamical system that maps low-dimensional inputs into a high-dimensional space. The model’s ric...

The reason for the existence of adversarial samples is still barely understood. Here, we explore the transferability of learned features to Out-of-Distribution (OoD) classes. We do this by assessing neural networks' capability to encode the existing features, revealing an intriguing connection with adversarial attacks and defences. The principal id...

There are different types of adversarial attacks and defences for machine learning algorithms which makes assessing the robustness of an algorithm a daunting task. Moreover, there is an intrinsic bias in these adversarial attacks and defences to make matters worse. Here, we organise the problems faced: a) Model Dependence, b) Insufficient Evaluatio...

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...

Adversarial algorithms have shown to be effective against neural networks for a variety of tasks. Some adversarial algorithms perturb all the pixels in the image minimally for the image classification task in image classification. In contrast, some algorithms perturb few pixels strongly. However, very little information is available regarding why t...

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...

Deep learning has brought many advances to various fields and enabled applications such as speech and visual recognition to flourish. However, recent findings show that Deep Neural Networks (DNN) still have many problems of their own. The many vulnerabilities present in DNNs unable their application to critical problems. Here, some of these vulnera...

The deployment of autonomous vehicles has been announced for years. Yet, full autonomous vehicles are not on public roads. Elon Musk, speaking at an event during the first half of 2020, stated that his firm will be able to present a fully autonomous vehicle technology by the end of the year. This statement is met with skepticism, especially because...

This edited book aims to address challenges facing the deployment of autonomous vehicles. Autonomous vehicles were predicted to hit the road by 2017. Even though a high degree of automation may have been achieved, vehicles that can drive autonomously under all circumstances are not yet commercially available, and the predictions have been adjusted....

Adversarial examples have shown that albeit highly accurate, models learned by machines, differently from humans,have many weaknesses. However, humans' perception is also fundamentally different from machines, because we do not see the signals which arrive at the retina but a rather complex recreation of them. In this paper, we explore how machines...

Humans possess an inherent ability to chunk sequences into their constituent parts. In fact, this ability is thought to bootstrap language skills to the 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), encompassi...

Recently, the one-pixel attack showed that deep neural networks (DNNs) can misclassify by changing only one pixel. Beyond a vulnerability, by demonstrating how easy it is to cause a change in classes, it revealed that DNNs are not learning the expected high-level features but rather less robust ones. In this chapter, recent findings further confirm...

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 di...

Lexicase selection achieves very good solution quality by introducing ordered test cases. However, the computational complexity of lexicase selection can prohibit its use in many applications. In this paper, we introduce Batch Tournament Selection (BTS), a hybrid of tournament and lexicase selection which is approximately one order of magnitude fas...

Modern gradient based optimization methods for deep neural networks demonstrate outstanding results on image classification tasks. However, methods that do not rely on gradient feedback fail to tackle deep network optimization. In the held of evolutionary computation, applying evolutionary algorithms directly to network weights remains to be an unr...

Deep neural networks were shown to misclassify slightly modified input images. Recently, many defenses have been proposed but none have improved consistently the robustness of neural networks. Here, we propose to use attacks as a function evaluation to automatically search for architectures that can resist such attacks. Experiments on neural archit...

Neural networks have been shown vulnerable to adversarial samples. Slightly perturbed input images are able to change the classification of accurate models, showing that the representation learned is not as good as previously thought.To aid the development of better neural networks, it would be important to evaluate to what extent are current neura...

In adversarial machine learning, there are a huge number of attacks of various types which makes the evaluation of robustness for new models and defenses a daunting task. To make matters worse, there is an inherent bias in attacks and defenses. Here, we organize the problems faced (model dependence, insufficient evaluation, unreliable adversarial s...

Intrinsically, driving is a Markov Decision Process which suits well the reinforcement learning paradigm. In this paper, we propose a novel agent which learns to drive a vehicle without any human assistance. We use the concept of reinforcement learning and evolutionary strategies to train our agent in a 2D simulation environment. Our model's archit...

Lexicase selection achieves very good solution quality by introducing ordered test cases. However, the computational complexity of lexicase selection can prohibit its use in many applications. In this paper, we introduce Batch Tournament Selection (BTS), a hybrid of tournament and lexicase selection which is approximately one order of magnitude fas...

Unit commitment and load dispatch problems are important and complex problems in power system operations that have being traditionally solved separately. In this paper, both problems are solved together without approximations or simplifications. In fact, the problem solved has a massive amount of grid-connected photovoltaic units, four pump-storage...

Deep neural networks were shown to be vulnerable to single pixel modifications. However, the reason behind such phenomena has never been elucidated. Here, we propose Propagation Maps which show the influence of the perturbation in each layer of the network. Propagation Maps reveal that even in extremely deep networks such as Resnet, modification in...

Recently, deep learning based natural language processing techniques are being extensively used to deal with spam mail, censorship evaluation in social networks, among others. However, there is only a couple of works evaluating the vulnerabilities of such deep neural networks. Here, we go beyond attacks to investigate, for the first time, universal...

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 incre...

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 th...

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 betwee...

The output of Convolutional Neural Networks (CNN) has been shown to be discontinuous which can make the CNN image classifier vulnerable to small well-tuned artificial perturbations. That is, images modified by adding such perturbations(i.e. adversarial perturbations) that make little difference to human eyes, can completely alter the CNN classifica...

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. Current IoT devices are typically micro-computers for domain-specific computations...

Recent research has revealed that the output of Deep neural networks(DNN) is not continuous and very sensitive to tiny perturbation on the input vectors and accordingly several methods have been proposed for crafting effective perturbation against the networks. In this paper, we propose a novel method for optically calculating extremely small adver...

In the domain of information security, code obfuscation is a feature often employed for malicious purposes. For example there have been quite a few papers reporting that obfuscated JavaScript frequently comes with malicious functionality such as redirecting to external malicious websites. In order to capture such obfuscation, a class of detectors b...

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...

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,...

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...

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 Classi-fiers (NOTC) is applied to the continuous action mountain car as well as two variations of it: a noisy mountain car and...

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 nove...

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 superv...

Abstract Structured evolutionary algorithms have been investigated for some time. However, they have been under-explored specially in the field of multi-objective optimization. Despite their good results, the use of complex dynamics and structures make their understanding and adoption rate low. Here, we propose the general subpopulation framework t...

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...

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 betwee...

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...

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 th...

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 random subspace methods, this paper addresses the question of developi...

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 incre...

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, com...

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...