Artificial intelligence and all its supporting tools, e.g. machine and deep learning in computational intelligence-based systems, are rebuilding our society (economy, education, life-style, etc.) and promising a new era for the social welfare state. In this paper we summarize recent advances in data science and artificial intelligence within the interplay between natural and artificial computation. A review of recent works published in the latter field and the state the art are summarized in a comprehensive and self-contained way to provide a baseline framework for the international community in artificial intelligence. Moreover, this paper aims to provide a complete analysis and some relevant discussions of the current trends and insights within several theoretical and application fields covered in the essay, from theoretical models in
Several research programs are tackling the use of Wireless Sensor Networks (WSN) at specific fields, such as e-Health, e-Inclusion or e-Sport. This is the case of the project “Ambient Intelligence Systems Support for Athletes with Specific Profiles”, which intends to assist athletes in their training. In this paper, the main developments and outcomes from this project are described. The architecture of the system comprises a WSN deployed in the training area which provides communication with athletes’ mobile equipments, performs location tasks, and harvests environmental data (wind speed, temperature, etc.). Athletes are equipped with a monitoring unit which obtains data from their training (pulse, speed, etc.). Besides, a decision engine combines these real-time data together with static information about the training field, and from the athlete, to direct athletes’ training to fulfill some specific goal. A prototype is presented in this work for a cross country running scenario, where the objective is to maintain the heart rate (HR) of the runner in a target range. For each track, the environmental conditions (temperature of the next track), the current athlete condition (HR), and the intrinsic difficulty of the track (slopes) influence the performance of the athlete. The decision engine, implemented by means of (m, s)-splines interpolation, estimates the future HR and selects the best track in each fork of the circuit. This method achieves a success ratio in the order of 80%. Indeed, results demonstrate that if environmental information is not take into account to derive training orders, the success ratio is reduced notably.
Reinforcement learning (RL) aims at building a policy that maximizes a task-related reward within a given domain. When the domain is known, i.e., when its states, actions and reward are defined, Markov Decision Processes (MDPs) provide a convenient theoretical framework to formalize RL. But in an open-ended learning process, an agent or robot must solve an unbounded sequence of tasks that are not known in advance and the corresponding MDPs cannot be built at design time. This defines the main challenges of open-ended learning: how can the agent learn how to behave appropriately when the adequate states, actions and rewards representations are not given? In this paper, we propose a conceptual framework to address this question. We assume an agent endowed with low-level perception and action capabilities. This agent receives an external reward when it faces a task. It must discover the state and action representations that will let it cast the tasks as MDPs in order to solve them by RL. The relevance of the action or state representation is critical for the agent to learn efficiently. Considering that the agent starts with a low level, task-agnostic state and action spaces based on its low-level perception and action capabilities, we describe open-ended learning as the challenge of building the adequate representation of states and actions, i.e., of redescribing available representations. We suggest an iterative approach to this problem based on several successive Representational Redescription processes, and highlight the corresponding challenges in which intrinsic motivations play a key role.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.