The success of sentence classification often depends on understanding both the syntactic and semantic properties of wordphrases. Recent progress on this task has been based on exploiting the grammatical structure of sentences but often this structure is difficult to parse and noisy. In this paper, we propose a structureindependent ‘Gated Representation Alignment’ (GRA) model that blends a phras...

In the present study Iran’s rice imports trend is forecasted, using artificial neural networks and econometric methods, during 2009 to 2013, and their results are compared. The results showed that feet forward neural network leading with less forecast error and had better performance in comparison to econometric techniques and also, other methods of neural networks, such as Recurrent networks a...

In this paper, we propose the new fixedsize ordinally-forgetting encoding (FOFE) method, which can almost uniquely encode any variable-length sequence of words into a fixed-size representation. FOFE can model the word order in a sequence using a simple ordinally-forgetting mechanism according to the positions of words. In this work, we have applied FOFE to feedforward neural network language mo...

This paper presents a neural network able to control saccadic movements. The input to the network is a specification of a stimulation site on the collicular motor map. The output is the time course of the eye position in the orbit (horizontal and vertical angles). The units in the network exhibit a one-to-one correspondance with neurons in the intermediate layer of the superior colliculus (coll...

In this paper, we implement a biologically inspired approach for the generation of real-time navigation of a real omnidirectional robot. The approach is based on a so-called neural fields, which are equivalent to continuous recurrent neural networks. Due to its dynamical properties, a neural field produces only one localized peak that indicates the optimum movement direction of the robot. Exper...

This paper describes iUBC, a neural network based approach that achieves competitive results on the interpretable STS task (iSTS 2016). Actually, it achieves top performance in one of the three datasets. iUBC makes use of a jointly trained classifier and regressor, and both models work on top of a recurrent neural network. Through the paper we provide detailed description of the approach, as we...

In this paper, a neural network based on the projection and contraction method is employed to compute the minimum in nity-norm joint torques of redundant manipulators, which explicitly takes into account the joint torque limits. While the desired accelerations of the end-e ector for a speci ed task are fed into the network, a driving joint torque vector which has the maximum component in magnit...

Recent research has revealed that hierarchical linguistic structures can emerge in a recurrent neural network with a sufficient number of delayed context layers. As a representative of this type of network the Multiple Timescale Recurrent Neural Network (MTRNN) has been proposed for recognising and generating known as well as unknown linguistic utterances. However the training of utterances per...

Complex neural dynamics produced by the recurrent architecture of neocortical circuits is critical to the cortex's computational power. However, the synaptic learning rules underlying the creation of stable propagation and reproducible neural trajectories within recurrent networks are not understood. Here, we examined synaptic learning rules with the goal of creating recurrent networks in which...