Explore the vast range of titles available.

[...]this convention requires multiple times to retrain the data. The round-off error will accumulate depending on the number of updating data. [...]The error in the data update process has to be determined to reduce the OS-ELM generalization [9]. [...]a learning technique must be adapted to this situation [9]. [...]in (8) can be solved in the triangular system [17].

This case study focused on the robotics learning process of Mark (a pseudonym), a Latino-American second grader diagnosed with autism spectrum disorder. Drawing on Polanyi’s (Personal knowledge: towards a post-critical philosophy [Kindle version], 1958/2015) notion of “tacit knowing” and “dwelling in tools,” we attempted to understand Mark’s unique processes and ways of engaging in learning about a Light Sensor by pursuing two research questions: (a) How does Mark, with his unique behavioral and socio-emotional characteristics, engage in the robotics class? (b) What insights can we gain from his inquiry as we develop responsive robotics education? Findings revealed that Mark used a non-sequential inquiry process filled with repetitive free explorations and unexpected expanded inquiries about the Light Sensor. This non-sequential inquiry process highlighted that dwelling with robotic manipulatives was Mark’s distinct ways of exploring the Light Sensor. His non-sequential inquiry process emerged from his tacit engagement and expanded to his sophisticated and holistic understanding of the Light Sensor. We discuss implications for a robotics education program that is responsive to young children with diverse needs and characteristics.

The linear parameter-varying (LPV) model is widely used in aero engine control system design. The conventional local modeling method is inaccurate and inefficient in the full flying envelope. Hence, a novel online data-driven LPV modeling method based on the online sequential extreme learning machine (OS-ELM) with an additional multiplying layer (MLOS-ELM) was proposed. An extra multiplying layer was inserted between the hidden layer and the output layer, where the hidden layer outputs were multiplied by the input variables and state variables of the LPV model. Additionally, the input layer was set to the LPV model’s scheduling parameter. With the multiplying layer added, the state space equation matrices of the LPV model could be easily calculated using online gathered data. Simulation results showed that the outputs of the MLOS-ELM matched that of the component level model of a turbo-shaft engine precisely. The maximum approximation error was less than 0.18%. The predictive outputs of the proposed online data-driven LPV model after five samples also matched that of the component level model well, and the maximum predictive error within a large flight envelope was less than 1.1% with measurement noise considered. Thus, the efficiency and accuracy of the proposed method were validated.

Reinforcement learning algorithms describe how an agent can learn an optimal action policy in a sequential decision process, through repeated experience. In a given environment, the agent policy provides him some running and terminal rewards. As in online learning, the agent learns sequentially. As in multi-armed bandit problems, when an agent picks an action, he can not infer ex-post the rewards induced by other action choices. In reinforcement learning, his actions have consequences: they influence not only rewards, but also future states of the world. The goal of reinforcement learning is to find an optimal policy – a mapping from the states of the world to the set of actions, in order to maximize cumulative reward, which is a long term strategy. Exploring might be sub-optimal on a short-term horizon but could lead to optimal long-term ones. Many problems of optimal control, popular in economics for more than forty years, can be expressed in the reinforcement learning framework, and recent advances in computational science, provided in particular by deep learning algorithms, can be used by economists in order to solve complex behavioral problems. In this article, we propose a state-of-the-art of reinforcement learning techniques, and present applications in economics, game theory, operation research and finance.

State space models (SSMs) are important for multi-variable performance analysis and controller design of aero-engines. In order to solve the problems of the traditional state space modeling methods that rely on component-level models (CLMs) and cannot be carried out in real time, an aero-engine state space modeling method based on adaptive forgetting factor online sequential extreme learning machine (AFOS-ELM) is proposed in this paper. The structure of the extreme learning machine (ELM) is determined according to the form of the state space model, and the inverse-free ELM algorithm is used to automatically select the appropriate number of hidden nodes to improve the efficiency of offline initialization. The focus of the ELM on current operation performance is enhanced by the adaptive renewed forgetting factor, which reduces the impact of aero-engine history and deviated data on the current output and improves the accuracy of the model. Then, according to the analytical equation of the ELM model, the state space model of an aero-engine at each sampling time is obtained by using the partial derivative method. The simulation results based on engine test data show that the real-time performance and accuracy of the state space model established online in this paper can meet the needs of aero-engine control system requirement.

We study the (perfect Bayesian) equilibrium of a sequential learning model over a general social network. Each individual receives a signal about the underlying state of the world, observes the past actions of a stochastically generated neighbourhood of individuals, and chooses one of two possible actions. The stochastic process generating the neighbourhoods defines the network topology. We characterize pure strategy equilibria for arbitrary stochastic and deterministic social networks and characterize the conditions under which there will be asymptotic learning—convergence (in probability) to the right action as the social network becomes large. We show that when private beliefs are unbounded (meaning that the implied likelihood ratios are unbounded), there will be asymptotic learning as long as there is some minimal amount of \"expansion in observations\". We also characterize conditions under which there will be asymptotic learning when private beliefs are bounded.

The paper develops a simulation-based approach to sequential parameter learning and filtering in general state space models. Our approach is based on approximating the target posterior by a mixture of fixed lag smoothing distributions. Parameter inference exploits a sufficient statistic structure and the methodology can be easily implemented by modifying state space smoothing algorithms. We avoid reweighting particles and hence sample degeneracy problems that plague particle filters that use sequential importance sampling. The method is illustrated by using two examples: a benchmark auto-regressive model with observation error and a high dimensional dynamic spatiotemporal model. We show that the method provides accurate inference in the presence of outliers, model misspecification and high dimensionality.

Computational intelligence techniques have been used in wide applications. Out of numerous computational intelligence techniques, neural networks and support vector machines (SVMs) have been playing the dominant roles. However, it is known that both neural networks and SVMs face some challenging issues such as: (1) slow learning speed, (2) trivial human intervene, and/or (3) poor computational scalability. Extreme learning machine (ELM) as emergent technology which overcomes some challenges faced by other techniques has recently attracted the attention from more and more researchers. ELM works for generalized single-hidden layer feedforward networks (SLFNs). The essence of ELM is that the hidden layer of SLFNs need not be tuned. Compared with those traditional computational intelligence techniques, ELM provides better generalization performance at a much faster learning speed and with least human intervene. This paper gives a survey on ELM and its variants, especially on (1) batch learning mode of ELM, (2) fully complex ELM, (3) online sequential ELM, (4) incremental ELM, and (5) ensemble of ELM.

Brain-computer interfaces (BCIs) have the potential in providing neurofeedback for stroke patients to improve motor rehabilitation. However, current BCIs often only detect general motor intentions and lack the precise information needed for complex movement execution, mainly due to insufficient movement execution features in EEG signals. This paper presents a sequential learning model incorporating a Graph Isomorphic Network (GIN) that processes a sequence of graph-structured data derived from EEG and EMG signals. Movement data are divided into sub-actions and predicted separately by the model, generating a sequential motor encoding that reflects the sequential features of the movements. Through time-based ensemble learning, the proposed method achieves more accurate prediction results and execution quality scores for each movement. A classification accuracy of 88.89% is achieved on an EEG-EMG synchronized dataset for push and pull movements, significantly outperforming the benchmark method's performance of 73.23%. This approach can be used to develop a hybrid EEG-EMG brain-computer interface to provide patients with more accurate neural feedback to aid their recovery.

Sound is inherently a temporal and sequential signal. Experience with sound therefore may help bootstrap—that is, provide a kind of \"scaffolding\" for—the development of general cognitive abilities related to representing temporal or sequential patterns. Accordingly, the absence of sound early in development may result in disturbances to these sequencing skills. In support of this hypothesis, we present two types of findings. First, normal-hearing adults do best on sequencing tasks when the sense of hearing, rather than sight, can be used. Second, recent findings suggest that deaf children have disturbances on exactly these same kinds of tasks that involve learning and manipulation of serial-order information. We suggest that sound provides an \"auditory scaffolding\" for time and serial-order behavior, possibly mediated through neural connections between the temporal and frontal lobes of the brain. Under conditions of auditory deprivation, auditory scaffolding is absent, resulting in neural reorganization and a disturbance to cognitive sequencing abilities.