The relationship between the number of hidden nodes in a neural network, the complexity of a multiclass discrimination problem, and the number of samples needed for effect learning are discussed. Bounds for the number of samples needed for effect learning are given. It is shown that Omega(min (d,n) M) boundary samples are required for successful classification of M clusters of samples using a t...

The internal representation of the training patterns of multi-layer perceptrons was examined and we demonstrated that the connection weights between layers are effectively transforming the representation format of the information from one layer to another one in a meaningful way. The internal code, which can be in analog or binary form, is found to be dependent on a number of factors, including...

We propose an algorithm for training Multi Layer Preceptrons for classification problems, that we named Hidden Layer Learning Vector Quantization (H-LVQ). It consists of applying Learning Vector Quantization to the last hidden layer of a MLP and it gave very successful results on problems containing a large number of correlated inputs. It was applied with excellent results on classification of ...

Community detection, also known as graph clustering, in multi-layer networks has been extensively studied the literature. The goal of community detection is to partition vertices a network into densely connected components so called communities. Networks contain set strong, dominant communities, which may interfere with weak, natural structure. When most members weak communities belong stronger...

Accurate pore pressure prediction is a necessary requirement to well structure optimizing, drilling difficulty minimizing, drilling accidents preventing. It plays a very important role in the economically and efficiently well operating. Previous methods for pore prediction have their own hypothesizes and cannot take into consideration factors that indicate or influence the pore pressure, so the...

While the network loading problem for 2-layer threshold nets is NP-hard when learning from examples alone (as with backpropagation), (Baum, 91) has now proved that a learner can employ queries to evade the hidden unit credit assignment problem and PAC-load nets with up to four hidden units in polynomial time. Empirical tests show that the method can also learn far more complicated functions suc...

Introduction: The possibility of depression is common in the elderly. Novel technologies allow us to monitor people related to depression. Hence, a model was provided to detect depression in elderly based on artificial neural network (ANN). Methods: The present study is an applied descriptive-survey research. Forty elderly people were randomly selected from the Elderly Care Center in Gonbad Ka...

Our living creatures represent global information in their brain by integrating local sensory signals such as visual sensory signals. In this paper, the state of hidden layer in a layered neural network with local inputs after learning was observed for some cases. Some characters became clear as follows. (1)If the training signal changes gradually in space, the hidden layer becomes to represent...

A simultaneous perturbation approach for cascade learning of single hidden layer neural network is presented. A sigmoidal hidden neuron is added to the single layer of hidden neurons after training until the error has stopped decreasing after a certain limit. Then, the cascaded network is again trained using simultaneous perturbation. Perturbation employed on the weights connecting to hidden ne...

In this paper, we introduce transformations of deep rectifier networks, enabling the conversion of deep rectifier networks into shallow rectifier networks. We subsequently prove that any rectifier net of any depth can be represented by a maximum of a number of functions that can be realized by a shallow network with a single hidden layer. The transformations of both deep rectifier nets and deep...