Recent advances in AutoML have led to automated tools that can compete with machine learning experts on supervised learning tasks. However, current AutoML tools do not yet support modern neural networks effectively. In this work, we present a first version of Auto-Net, which provides automatically-tuned feed-forward neural networks without any human intervention. We report results on datasets f...

The architecture of a neural network with its links and weights can be viewed as a knowledge representation. To overcome the black{box problem of not knowing what knowledge is hidden in a neural architecture, we present a strictly logically operating network. Each neuron represents either a disjunc-tion or conjunction of its inputs and the net thus performs the function of a logic formula. This...

A neural net model for forecasting the prices of Venezuelan crude oil is proposed. The inputs of the neural net are selected by reference to a dynamic system model of oil prices by Mashayekhi (1995, 2001) and its performance is evaluated using two criteria: the Excess Profitability test by Anatoliev and Gerko (2005) and the characteristics of the equity curve generated by a trading strategy bas...

Attraction models are very popular in marketing research for studying the e ects of marketing instruments on market shares. However, so far the marketing literature only considers attraction models with certain functional forms that exclude threshold or saturation e ects on attraction values. We can achieve greater exibility by using the neural net based approach introduced here. This approach ...

This paper presents an application of an artificial neural net to the implementation of decision class analysis (DCA), together with the generation of a decision model, influence diagram. The diagram is well-known as a good tool for knowledge representation of complex decision problems. Generating influence diagram is known to in practice require much time and effort, and the resulting model ca...

In this paper we study how the framework of Petri nets can be extended and applied to study recurrent events. We use possibility theory to realistically model temporal properties of the recurrent processes being modeled by an extended Petri net. Such temporal properties include timestamps stored in tokens and durations of firing the transitions. We apply our method to model the recurrent behavi...

BP neural network as a kind of intelligent method is widely used in fault diagnosis, due to the single BP neural network’s error is big, GA algorithm is often used in optimizing BP neural network, but the standard GA algorithm’s searching efficiency is low and it is easy to fall into local convergence. According to the characters of Accord car ignition diagnosis and BP neural network, this arti...

Several neural-net based PID controllers have been proposed for nonlinear process systems. However, they have been not so widely used in process industries due to the considerably computational cost. This paper presents a new intelligent PID tuning scheme, whose PID tuner is constructed by the fusional structure of a cerebellar model articulation controller and a neural network. This PID tuner ...

The paper considers the development of a new type of artificial neural network and its applicability to non-linear system identification. This is the functional-link neural network with internal dynamic elements. The net consists of a single layer where the nonlinearity is firstly introduced by enhancing the input pattern with a functional expansion. The internal dynamic elements are auto-regre...