The combination of feedforward control and programmable tooling has emerged as a promising method to reduce product variation in multistage manufacturing systems. Feedforward control allows compensation of deviations on a part-by-part basis using programmable tooling. This paper addresses the problem of designing an optimal feedforward control law that improves quality. The controller design in...

For uncertain systems described in the standard LFT form, we consider the problem of designing robust L2-gain disturbance feedforward controllers if the uncertain blocks are described by integral quadratic constraints (IQCs). For technical reasons related to the feedforward problem we work with the duals of the constraints involved in robustness analysis using IQCs. Based on an elimination of t...

This paper examines the function approximation properties of the "random neural-network model" or GNN. The output of the GNN can be computed from the firing probabilities of selected neurons. We consider a feedforward Bipolar GNN (BGNN) model which has both "positive and negative neurons" in the output layer, and prove that the BGNN is a universal function approximator. Specifically, for any f ...

We discuss a model of consistent learning with an additional restriction on the probability distribution of training samples, the target concept and hypothesis class. We show that the model provides a significant improvement on the upper bounds of sample complexity, i.e. the minimal number of random training samples allowing a selection of the hypothesis with a predefined accuracy and confidenc...

Although feedforward neural networks are well suited to function approximation , in some applications networks experience problems when learning a desired function. One problem is interference which occurs when learning in one area of the input space causes unlearning in another area. Networks that are less susceptible to interference are referred to as spatially local networks. To understand t...

For many practical problem domains the use of neural networks has led to very satisfactory results. Nevertheless the choice of an appropriate, problem specific network architecture still remains a very poorly understood task. Given an actual problem, one can choose a few different architectures, train the chosen architectures a few times and finally select the architecturewith the best behaviou...

A feedforward network is proposed which lends itself to cost-effective implementations in digital hardware and has a fast forward-pass capability. It differs from the conventional model in restricting its synapses to the set {−1, 0, 1} while allowing unrestricted offsets. Simulation results on the ‘onset of diabetes’ data set and a handwritten numeral recognition database indicate that the new ...

Spike propagation for spatially correlated inputs in layered neural networks has been investigated with the use of a semi-analytical dynamical mean-field approximation (DMA) theory recently proposed by the author [H. Hasegawa, Phys. Rev. E 67, 041903 (2003)]. Each layer of the network is assumed to consist of FitzHugh-Nagumo neurons which are coupled by feedforward couplings. Applying an single...

The hypothalamo-pituitary-adrenal axis is a stress-adaptive neuroendocrine ensemble, in which adrenocorticotropin (ACTH) drives cortisol secretion (feedforward) and cortisol restrains ACTH outflow (feedback). Quantifying direction- and pathway-specific adjustments within this and other interlinked systems by noninvasive means remains difficult. The present study tests the hypothesis that forwar...

Local inhibition by GABA-releasing neurons is important for the operation of sensory cortices, but the details of these inhibitory circuits remain unclear. We addressed this question in the olfactory system by making targeted recordings from identified classes of inhibitory and glutamatergic neurons in the piriform cortex (PC) of mice. First, we looked for feedforward synaptic inhibition provid...