In this paper we present an incremental approach to learning generative models of object manipulation actions as HMMs over qualitative relations between two objects. We compare the incremental approach against a traditional batch training baseline and show that the resulting qualitative action models are capable of one-shot learning after just one seen example while displaying good generalizati...

In the inductive inference framework of learning in the limit, a variation of the bounded example memory (Bem) language learning model is considered. Intuitively, the new model constrains the learner’s memory not only in how much data may be retained, but also in how long that data may be retained. More specifically, the model requires that, if a learner commits an example x to memory in some s...

Unlike the conventional neural network theories and implementations, Huang et al. [Universal approximation using incremental constructive feedforward networks with random hidden nodes, IEEE Transactions on Neural Networks 17(4) (2006) 879–892] have recently proposed a new theory to show that single-hidden-layer feedforward networks (SLFNs) with randomly generated additive or radial basis functi...

Negative correlation learning (NCL) is a successful approach to constructing neural network ensembles. In batch learning mode, NCL outperforms many other ensemble learning approaches. Recently, NCL has also shown to be a potentially powerful approach to incremental learning, while the advantages of NCL have not yet been fully exploited. In this paper, we propose a selective NCL (SNCL) algorithm...

Classical supervised learning techniques are generally based on an inductive mechanism able to generalise a model from a set of positive examples, assuring its consistency with respect to a set of negative examples. In case of learning from positive evidence only, the problem of over-generalisation comes into account. This paper proposes a general technique for incremental multi-class learning ...

The real world is too complex and variable to directly program an autonomous ground robot’s control system to respond to the inputs from its environmental sensors such as LIDAR and video. The need for learning incrementally, discarding prior data, is important because of the vast amount of data that can be generated by these sensors. This is crucial because the system needs to generate and upda...

In this article, a new class of the epoch-incremental reinforcement learning algorithm is proposed. In the incremental mode, the fundamental TD(0) or TD(λ) algorithm is performed and an environment model is created. In the epoch mode, on the basis of the environment model, the distances of past-active states to the terminal state are computed. These distances and the reinforcement terminal stat...

As computers are widely used and computer-programming gets increasingly complicated, computer users and programmers demand more convenient human-computer interfaces and programming tools. Motivated by facilitating computer programming and human-computer interaction, this project explores teaching a computer to react properly to external stimuli through natural human-computer interaction. The lo...

We present a new algorithm for the construction of radial basis function (RBF) networks. The method uses accumulated error information to determine where to insert new units. The diameter of the localized units is chosen based on the mutual distances of the units. To have the distance information always available, it is held up-to-date by a Hebbian learning rule adapted from the "Neural Gas" al...

Most existing tracking algorithms construct a representation of a target object prior to the tracking task starts, and utilize invariant features to handle appearance variation of the target caused by lighting, pose, and view angle change. In this paper, we present an efficient and effective online algorithm that incrementally learns and adapts a low dimensional eigenspace representation to ref...