25 Here we address how dynamics of glutamatergic and GABAergic synaptic input to CA3 26 pyramidal cells contribute to spontaneous emergence and evolution of recurrent seizure-like 27 events (SLEs) in juvenile (P10-13) rat hippocampal slices bathed in low-[Mg] artificial 28 cerebrospinal fluid. In field potential recordings from CA3 pyramidal layer a short epoch of 29 high frequency oscillation ...

We developed a method called Time-Slicing [1] for the analysis of the speech signal. It enables a neural network to recognize connected speech as it comes, without having to fit the input signal into a fixed time-format, nor label or segment it phoneme by phoneme. The neural network produces an immediate hypothesis of the recognized phoneme and its size is small enough to run even on a PC. To i...

How should one apply deep learning to tasks such as morphological reinflection, which stochastically edit one string to get another? A recent approach to such sequence-to-sequence tasks is to compress the input string into a vector that is then used to generate the output string, using recurrent neural networks. In contrast, we propose to keep the traditional architecture, which uses a finite-s...

TRAINREC is a system for training feedforward and recurrent neural networks that incorporates several ideas. It uses the conjugate-gradient method which is demonstrably more efficient than traditional backward error propagation. We assume epoch-based training and derive a new error function having several desirable properties absent from the traditional sum-of-squares-error function. We argue f...

Models of the cerebellar microcircuit often assume that input signals from the mossy-fibers are expanded and recoded to provide a foundation from which the Purkinje cells can synthesize output filters to implement specific input-signal transformations. Details of this process are however unclear. While previous work has shown that recurrent granule cell inhibition could in principle generate a ...

Abstractive Sentence Summarization generates a shorter version of a given sentence while attempting to preserve its meaning. We introduce a conditional recurrent neural network (RNN) which generates a summary of an input sentence. The conditioning is provided by a novel convolutional attention-based encoder which ensures that the decoder focuses on the appropriate input words at each step of ge...

We investigate a form of modular neural network for classification with (a) pre-separated input vectors entering its specialist (expert) networks, (b) specialist networks which are selforganized (radial-basis function or self-targeted feedforward type) and (c) which fuses (or integrates) the specialists with a single-layer net. When the modular architecture is applied to spatiotemporal sequence...

Second order properties of cost functions for recurrent networks are investigated. We analyze a layered fully recurrent architecture, the virtue of this architecture is that it features the conventional feedforward architecture as a special case. A detailed description of recursive computation of the full Hessian of the network cost function is provided. We discuss the possibility of invoking s...

A major source of random variability in cortical networks is the quasi-random arrival of presynaptic action potentials from many other cells. In network studies as well as in the study of the response properties of single cells embedded in a network, synaptic background input is often approximated by Poissonian spike trains. However, the output statistics of the cells is in most cases far from ...

In this paper, a TSK-type recurrent fuzzy network (TRFN) structure is proposed. The proposal calls for a design of TRFN by either neural network or genetic algorithms depending on the learning environment. Set forth first is a recurrent fuzzy network which develops from a series of recurrent fuzzy if–then rules with TSK-type consequent parts. The recurrent property comes from feeding the intern...