There exist a number of negative results ([J), [BR), [KV]) about learning on neural nets in Valiant's model [V) for probably approximately correct learning ("PAC-learning"). These negative results are based on an asymptotic analysis where one lets the number of nodes in the neural net go to infinit.y. Hence this analysis is less adequate for the investigation of learning on a small fixed neural...

In this paper, we propose a model using generative adversarial net (GAN) to generate realistic text. Instead of using standard GAN, we combine variational autoencoder (VAE) with generative adversarial net. The use of high-level latent random variables is helpful to learn the data distribution and solve the problem that generative adversarial net always emits the similar data. We propose the VGA...

This paper presents a novel feature selection approach for backpropagation neural networks (NNs). Previously, a feature selection technique known as the wrapper model was shown effective for decision trees induction. However, it is prohibitively expensive when applied to real-world neural net training characterized by large volumes of data and many feature choices. Our approach incorporates a w...

Neural networks are a powerful method for solving complex, "real world", modeling problems when traditional algorithms cannot be formulated. Most neural networks are implemented in programming languages that can represent data structures well such as C/C++, Java or Visual Basic. SAS is very good at processing longititudinal data. This paper will offer techniques and methods through implementati...

This study aimed to evaluate the efficiency of energy consumption and economic analysis of different watermelon cultivation systems in Fars Province of Iran. Watermelon production systems were classified into five systems, namely, custom tillage (group 1), conservation tillage (group 2), traditional planting (group3), semi mechanized planting (group 4), and mechanized planting (group 5). Data w...

Recently, there has been considerable interest in deriving and applying knowledge-based, empirical potential functions for proteins. These empirical potentials have been derived from the statistics of interacting, spatially neighboring residues, as may be obtained from databases of known protein crystal structures. In this paper we employ neural networks to redefine empirical potential function...

We describe a CMOS neural net chip with a reconfigurable network architecture. It contains 32,768 binary, programmable connections arranged in 256 'building block' neurons. Several 'building blocks' can be connected to form long neurons with up to 1024 binary connections or to form neurons with analog connections. Singleor multi-layer networks can be implemented with this chip. We have integrat...

This paper p r e s e n t s a new n o i s e c a n c e l l a t i o n with an Neural Network. The network feedforward one with t h r e e method for A r t i f i c i a l used is a l a y e r s . The backpropagati on and s tas ti cal Cauchy’ s 1 ear n i ng a1 gor i t hms are empl oyed for a d a p t a t i o n of t h e i n t e r n a l parameters of t h e network. The c o n s t r a i n e d tangent hyperb...

Deep neural networks are surprisingly efficient at solving practical tasks, but the theory behind this phenomenon is only starting to catch up with the practice. Numerous works show that depth is the key to this efficiency. A certain class of deep convolutional networks – namely those that correspond to the Hierarchical Tucker (HT) tensor decomposition – has been proven to have exponentially hi...

Since 1997, the rupiah currency has a tendency to change at any time since the economic crisis that hit Indonesia. One of the currencies of the most widely traded on international exchange market is the U.S. dollar. This paper will forecast the exchange rate by using back propagation neural networks. Variables that affecting currency exchange rates is inflation, gross national product and inter...