Currently, many applications in Machine Learning are based on define new models to extract more information about data, In this case Deep Reinforcement Learning with the most common application in video games like Atari, Mario, and others causes an impact in how to computers can learning by himself with only information called rewards obtained from any action. There is a lot of algorithms modeled and implemented based on Deep Recurrent Q-Learning proposed by Deep-Mind used in AlphaZero and Go. In this document, We proposed Deep Recurrent Double Q-Learning that is an implementation of Deep Reinforcement Learning using Double Q-Learning algorithms and Recurrent Networks like LSTM and DRQN.

We all see the headlines nearly every day. Whether primitive (gunpowder) or cutting-edge (unmanned aerial vehicles) in the wrong hands, technology can empower bad actors and put our society at risk, creating a sense of helplessness and frustration. Current approaches to protecting our public venues are not up to the task, and, frankly appear to meet Einstein's definition of insanity: "doing the same thing over and over and expecting a different result." It is time to look past traditional defense technologies and see if newer approaches can tilt the pendulum back in the defender's favor. Artificial Intelligence (AI) can play a critical role here, helping to identify, classify and promulgate counteractions on potential threats faster than any security personnel.

The worldwide growth of maritime traffic and the development of the Automatic Identification System (AIS) has led to advances in monitoring systems for preventing vessel accidents and detecting illegal activities. In this work, we describe research gaps and challenges in machine learning for vessel behavior change and event detection, considering several constraints imposed by real-time data streams and the maritime monitoring domain. As a starting point, we investigate how unsupervised and semi-supervised change detection methods may be employed for identifying shifts in vessel behavior, aiming to detect and label unusual events.

This study suggests a new approach to EEG data classification by exploring the idea of using evolutionary computation to both select useful discriminative EEG features and optimise the topology of Artificial Neural Networks. An evolutionary algorithm is applied to select the most informative features from an initial set of 2550 EEG statistical features. Optimisation of a Multilayer Perceptron (MLP) is performed with an evolutionary approach before classification to estimate the best hyperparameters of the network. Deep learning and tuning with Long Short-Term Memory (LSTM) are also explored, and Adaptive Boosting of the two types of models is tested for each problem. Three experiments are provided for comparison using different classifiers: one for attention state classification, one for emotional sentiment classification, and a third experiment in which the goal is to guess the number a subject is thinking of. The obtained results show that an Adaptive Boosted LSTM can achieve an accuracy of 84.44%, 97.06%, and 9.94% on the attentional, emotional, and number datasets, respectively. An evolutionary-optimised MLP achieves results close to the Adaptive Boosted LSTM for the two first experiments and significantly higher for the number-guessing experiment with an Adaptive Boosted DEvo MLP reaching 31.35%, while being significantly quicker to train and classify. In particular, the accuracy of the nonboosted DEvo MLP was of 79.81%, 96.11%, and 27.07% in the same benchmarks. Two datasets for the experiments were gathered using a Muse EEG headband with four electrodes corresponding to TP9, AF7, AF8, and TP10 locations of the international EEG placement standard. The EEG MindBigData digits dataset was gathered from the TP9, FP1, FP2, and TP10 locations.

Natural language understanding (NLU) of text is a fundamental challenge in AI, and it has received significant attention throughout the history of NLP research. This primary goal has been studied under different tasks, such as Question Answering (QA) and Textual Entailment (TE). In this thesis, we investigate the NLU problem through the QA task and focus on the aspects that make it a challenge for the current state-of-the-art technology. This thesis is organized into three main parts: In the first part, we explore multiple formalisms to improve existing machine comprehension systems. We propose a formulation for abductive reasoning in natural language and show its effectiveness, especially in domains with limited training data. Additionally, to help reasoning systems cope with irrelevant or redundant information, we create a supervised approach to learn and detect the essential terms in questions. In the second part, we propose two new challenge datasets. In particular, we create two datasets of natural language questions where (i) the first one requires reasoning over multiple sentences; (ii) the second one requires temporal common sense reasoning. We hope that the two proposed datasets will motivate the field to address more complex problems. In the final part, we present the first formal framework for multi-step reasoning algorithms, in the presence of a few important properties of language use, such as incompleteness, ambiguity, etc. We apply this framework to prove fundamental limitations for reasoning algorithms. These theoretical results provide extra intuition into the existing empirical evidence in the field.

On a tower in the Brazilian rain forest, a sentinel scans the horizon for the first signs of fire. They don't blink or take breaks, and guided by artificial intelligence they can tell the difference between a dust cloud, an insect swarm and a plume of smoke that demands quick attention. In Brazil, the devices help keep mining giant Vale SA working, and protect trees for pulp and paper producer Suzano SA. In the future, it's a system that may be put to work in California, where deadly wildfires abound. The equipment includes optical and thermal cameras, as well as spectrometric systems that identify the chemical makeup of substances.

Building a Massive Corpus for Named Entity Recognition using Free Open Data Sources Daniel Specht Menezes Departamento de Inform atica PUC-Rio Rio de Janeiro, Brazil danielssmenezes@gmail.com Abstract --With the recent progress in machine learning, boosted by techniques such as deep learning, many tasks can be successfully solved once a large enough dataset is available for training. Nonetheless, human-annotated datasets are often expensive to produce, especially when labels are fine-grained, as is the case of Named Entity Recognition (NER), a task that operates with labels on a word-level. In this paper, we propose a method to automatically generate labeled datasets for NER from public data sources by exploiting links and structured data from DBpedia and Wikipedia. Due to the massive size of these data sources, the resulting dataset - SESAME 1 - is composed of millions of labeled sentences. We detail the method to generate the dataset, report relevant statistics, and design a baseline using a neural network, showing that our dataset helps building better NER predictors.

Deep Reinforcement Learning has made significant progress in multi-agent systems in recent years. In this review article, we have mostly focused on recent papers on Multi-Agent Reinforcement Learning (MARL) than the older papers, unless it was necessary. Several ideas and papers are proposed with different notations, and we tried our best to unify them with a single notation and categorize them by their relevance. In particular, we have focused on five common approaches on modeling and solving multi-agent reinforcement learning problems: (I) independent-learners, (II) fully observable critic, (III) value function decomposition, (IV) consensus, (IV) learn to communicate. Moreover, we discuss some new emerging research areas in MARL along with the relevant recent papers. In addition, some of the recent applications of MARL in real world are discussed. Finally, a list of available environments for MARL research are provided and the paper is concluded with proposals on the possible research directions.

Abstract: Sepsis, a dysregulated immune system response to infection, is among the leading causes of morbidity, mortality, and cost overruns in the Intensive Care Unit (ICU). Ear ly prediction of sepsis can improve situational awareness amongst clinicians and facilitate timely, protective interventions. While the application of predictive analytics in ICU patients has shown early promising results, much of the work has been encumbe red by high false - alarm rates. Efforts to improve specificity have been limited by several factors, most notably the difficulty of labeling sepsis onset time and the low prevalence of septic - events in the ICU. We show that by coupling a clinical criterion for defining sepsis onset time with a treatment policy (e.g., initiation of antibiotics within one hour of meeting the criterion), one may rank the relative utility of various criteria through offline policy evaluation. Given the optimal criterion, DeepAISE automatically learns predictive features related to higher - order interactions and temporal patterns among clinic al risk factors that maximize the data likelihood of observed time to septic events. DeepAISE has been incorporated into a clinical workflow, which provides real - time hourly sepsis risk scores. A comparative study of four baseline models indicates that Dee pAISE produces the most accurate predictions (AUC 0.90 and 0.87) and the lowest false alarm rates (FAR 0.20 and 0.26) in two separate cohorts (internal and external, respectively), while simultaneously producing interpretable representations of the clinica l time series and risk factors. Introduction Sepsis is a syndromic, life - threatening condition that arises when the body's response to infection injures its own internal organs (1) . Though the condition lacks the same public notoriety as other conditions like heart attacks, 6% of all hospitalized patients in the U nited S tates carry a primary diagnosis of sepsis as compared to 2.5% for the latter (2) . When all hospital deaths are ultimately considered, nearly 35% are attributable to sepsis (2) . This condition stands in stark contrast to heart attacks which have a mortality rate of 2.7 - 9.6% and only cost the US $12.1 billion ann ually, roughly half of the cost of sepsis (3) .

What is it exactly that makes humans so smart? In his seminal 1950 paper, "Computer Machinery and Intelligence," Alan Turing argued human intelligence was the result of complex symbolic reasoning. Philosopher Marvin Minsky, cofounder of the artificial intelligence lab at the Massachusetts Institute of Technology, also maintained that reasoning--the ability to think in a multiplicity of ways that are hierarchical--was what made humans human. Patrick Henry Winston begged to differ. "I think Turing and Minsky were wrong," he told me in 2017. "We forgive them because they were smart and mathematicians, but like most mathematicians, they thought reasoning is the key, not the byproduct." Winston, a professor of computer science at MIT, and a former director of its AI lab, was convinced the key to human intelligence was storytelling. "My belief is the distinguishing characteristic of humanity is this keystone ability to have descriptions with which we construct stories. I think stories are what make us different from chimpanzees and Neanderthals. And if story-understanding is really where it's at, we can't understand our intelligence until we understand that aspect of it."