Int J Neural Syst - The super-Turing computational power of plastic recurrent neural networks.

Tópicos

{ network(2748) neural(1063) input(814) }
{ algorithm(1844) comput(1787) effici(935) }
{ general(901) number(790) one(736) }
{ method(1557) propos(1049) approach(1037) }
{ gene(2352) biolog(1181) express(1162) }
{ model(2220) cell(1177) simul(1124) }
{ chang(1828) time(1643) increas(1301) }
{ signal(2180) analysi(812) frequenc(800) }
{ estim(2440) model(1874) function(577) }
{ inform(2794) health(2639) internet(1427) }
{ measur(2081) correl(1212) valu(896) }
{ perform(1367) use(1326) method(1137) }
{ imag(2830) propos(1344) filter(1198) }
{ extract(1171) text(1153) clinic(932) }
{ use(2086) technolog(871) perceiv(783) }
{ model(3404) distribut(989) bayesian(671) }
{ can(774) often(719) complex(702) }
{ problem(2511) optim(1539) algorithm(950) }
{ concept(1167) ontolog(924) domain(897) }
{ clinic(1479) use(1117) guidelin(835) }
{ care(1570) inform(1187) nurs(1089) }
{ research(1085) discuss(1038) issu(1018) }
{ monitor(1329) mobil(1314) devic(1160) }
{ patient(2837) hospit(1953) medic(668) }
{ structur(1116) can(940) graph(676) }
{ implement(1333) system(1263) develop(1122) }
{ decis(3086) make(1611) patient(1517) }
{ detect(2391) sensit(1101) algorithm(908) }
{ imag(1947) propos(1133) code(1026) }
{ data(1737) use(1416) pattern(1282) }
{ system(1976) rule(880) can(841) }
{ imag(1057) registr(996) error(939) }
{ bind(1733) structur(1185) ligand(1036) }
{ sequenc(1873) structur(1644) protein(1328) }
{ method(1219) similar(1157) match(930) }
{ featur(3375) classif(2383) classifi(1994) }
{ imag(2675) segment(2577) method(1081) }
{ patient(2315) diseas(1263) diabet(1191) }
{ take(945) account(800) differ(722) }
{ studi(2440) review(1878) systemat(933) }
{ motion(1329) object(1292) video(1091) }
{ assess(1506) score(1403) qualiti(1306) }
{ treatment(1704) effect(941) patient(846) }
{ surgeri(1148) surgic(1085) robot(1054) }
{ framework(1458) process(801) describ(734) }
{ error(1145) method(1030) estim(1020) }
{ learn(2355) train(1041) set(1003) }
{ data(1714) softwar(1251) tool(1186) }
{ design(1359) user(1324) use(1319) }
{ control(1307) perform(991) simul(935) }
{ method(984) reconstruct(947) comput(926) }
{ search(2224) databas(1162) retriev(909) }
{ featur(1941) imag(1645) propos(1176) }
{ case(1353) use(1143) diagnosi(1136) }
{ howev(809) still(633) remain(590) }
{ data(3963) clinic(1234) research(1004) }
{ studi(1410) differ(1259) use(1210) }
{ risk(3053) factor(974) diseas(938) }
{ perform(999) metric(946) measur(919) }
{ system(1050) medic(1026) inform(1018) }
{ import(1318) role(1303) understand(862) }
{ model(2341) predict(2261) use(1141) }
{ visual(1396) interact(850) tool(830) }
{ compound(1573) activ(1297) structur(1058) }
{ studi(1119) effect(1106) posit(819) }
{ blood(1257) pressur(1144) flow(957) }
{ spatial(1525) area(1432) region(1030) }
{ record(1888) medic(1808) patient(1693) }
{ health(3367) inform(1360) care(1135) }
{ model(3480) simul(1196) paramet(876) }
{ ehr(2073) health(1662) electron(1139) }
{ state(1844) use(1261) util(961) }
{ research(1218) medic(880) student(794) }
{ model(2656) set(1616) predict(1553) }
{ data(2317) use(1299) case(1017) }
{ age(1611) year(1155) adult(843) }
{ medic(1828) order(1363) alert(1069) }
{ cost(1906) reduc(1198) effect(832) }
{ group(2977) signific(1463) compar(1072) }
{ sampl(1606) size(1419) use(1276) }
{ data(3008) multipl(1320) sourc(1022) }
{ first(2504) two(1366) second(1323) }
{ intervent(3218) particip(2042) group(1664) }
{ activ(1138) subject(705) human(624) }
{ time(1939) patient(1703) rate(768) }
{ patient(1821) servic(1111) care(1106) }
{ can(981) present(881) function(850) }
{ analysi(2126) use(1163) compon(1037) }
{ health(1844) social(1437) communiti(874) }
{ high(1669) rate(1365) level(1280) }
{ cancer(2502) breast(956) screen(824) }
{ use(976) code(926) identifi(902) }
{ use(1733) differ(960) four(931) }
{ drug(1928) target(777) effect(648) }
{ result(1111) use(1088) new(759) }
{ survey(1388) particip(1329) question(1065) }
{ process(1125) use(805) approach(778) }
{ activ(1452) weight(1219) physic(1104) }
{ method(1969) cluster(1462) data(1082) }
{ method(2212) result(1239) propos(1039) }

Resumo

We study the computational capabilities of a biologically inspired neural model where the synaptic weights, the connectivity pattern, and the number of neurons can evolve over time rather than stay static. Our study focuses on the mere concept of plasticity of the model so that the nature of the updates is assumed to be not constrained. In this context, we show that the so-called plastic recurrent neural networks (RNNs) are capable of the precise super-Turing computational power--as the static analog neural networks--irrespective of whether their synaptic weights are modeled by rational or real numbers, and moreover, irrespective of whether their patterns of plasticity are restricted to bi-valued updates or expressed by any other more general form of updating. Consequently, the incorporation of only bi-valued plastic capabilities in a basic model of RNNs suffices to break the Turing barrier and achieve the super-Turing level of computation. The consideration of more general mechanisms of architectural plasticity or of real synaptic weights does not further increase the capabilities of the networks. These results support the claim that the general mechanism of plasticity is crucially involved in the computational and dynamical capabilities of biological neural networks. They further show that the super-Turing level of computation reflects in a suitable way the capabilities of brain-like models of computation.

Resumo Limpo

studi comput capabl biolog inspir neural model synapt weight connect pattern number neuron can evolv time rather stay static studi focus mere concept plastic model natur updat assum constrain context show socal plastic recurr neural network rnns capabl precis supertur comput powera static analog neural networksirrespect whether synapt weight model ration real number moreov irrespect whether pattern plastic restrict bivalu updat express general form updat consequ incorpor bivalu plastic capabl basic model rnns suffic break ture barrier achiev supertur level comput consider general mechan architectur plastic real synapt weight increas capabl network result support claim general mechan plastic crucial involv comput dynam capabl biolog neural network show supertur level comput reflect suitabl way capabl brainlik model comput

Resumos Similares

Neural Comput - A framework for simulating and estimating the state and functional topology of complex dynamic geometric networks. ( 0,723250253836986 )
Neural Comput - Influence of external inputs and asymmetry of connections on information-geometric measures involving up to ten neuronal interactions. ( 0,670175696435759 )
IEEE Trans Neural Netw Learn Syst - Complex-Valued Recurrent Correlation Neural Networks. ( 0,650281406481894 )
Neural Comput - Facilitation of neuronal responses by intrinsic default mode network activity. ( 0,64443485690973 )
Neural Comput - Noise tolerance of attractor and feedforward memory models. ( 0,639979133800512 )
Comput. Biol. Med. - Machine learning on-a-chip: a high-performance low-power reusable neuron architecture for artificial neural networks in ECG classifications. ( 0,636220691254037 )
Neural Comput - Echo state property linked to an input: exploring a fundamental characteristic of recurrent neural networks. ( 0,63507251961778 )
Neural Comput - Model-based decoding, information estimation, and change-point detection techniques for multineuron spike trains. ( 0,630158982820342 )
Neural Comput - Self-organization of topographic bilinear networks for invariant recognition. ( 0,629686680316843 )
Comput. Biol. Med. - Discontinuous Galerkin finite element method for solving population density functions of cortical pyramidal and thalamic neuronal populations. ( 0,628299999546713 )
Comput Math Methods Med - Multiobjective optimization design of spinal pedicle screws using neural networks and genetic algorithm: mathematical models and mechanical validation. ( 0,626254322962057 )
Neural Comput - Dynamical synapses enhance neural information processing: gracefulness, accuracy, and mobility. ( 0,619946653801671 )
Comput Math Methods Med - A signal-processing-based approach to time-varying graph analysis for dynamic brain network identification. ( 0,619209879378934 )
Neural Comput - Synchronization and redundancy: implications for robustness of neural learning and decision making. ( 0,614136938397682 )
Neural Comput - How to compress sequential memory patterns into periodic oscillations: general reduction rules. ( 0,613340475747981 )
Int J Neural Syst - Effects of extremely low-frequency magnetic fields on the response of a conductance-based neuron model. ( 0,613052873501095 )
Neural Comput - Exact event-driven implementation for recurrent networks of stochastic perfect integrate-and-fire neurons. ( 0,612741326239852 )
IEEE Trans Neural Netw Learn Syst - A Spiking Neural Simulator Integrating Event-Driven and Time-Driven Computation Schemes Using Parallel CPU-GPU Co-Processing: A Case Study. ( 0,61220105360293 )
Brief. Bioinformatics - Estimating the divisibility of complex biological networks by sparseness indices. ( 0,610408992855199 )
Neural Comput - Neuronal responses below firing threshold for subthreshold cross-modal enhancement. ( 0,608688623484337 )
Int J Neural Syst - Modeling fluctuations in default-mode brain network using a spiking neural network. ( 0,607238642385431 )
Neural Comput - Supervised learning in multilayer spiking neural networks. ( 0,607162129685384 )
Neural Comput - Fragility in dynamic networks: application to neural networks in the epileptic cortex. ( 0,603542870696536 )
Int J Neural Syst - Adaptation-dependent synchronization transitions and burst generations in electrically coupled neural networks. ( 0,602120832898933 )
Neural Comput - Subthreshold membrane depolarization as memory trace for perceptual learning. ( 0,600819081823763 )
IEEE Trans Neural Netw Learn Syst - Phase Oscillatory Network and Visual Pattern Recognition. ( 0,60053221740885 )
Neural Comput - The hippocampus as a stable memory allocator for cortex. ( 0,600284225501493 )
Neural Comput - Computing with a canonical neural circuits model with pool normalization and modulating feedback. ( 0,599255139342962 )
Neural Comput - Tonically balancing intracortical excitation and inhibition by GABAergic gliotransmission. ( 0,598507408220344 )
Neural Comput - Frequency selectivity emerging from spike-timing-dependent plasticity. ( 0,597449337282284 )
Comput Math Methods Med - Voxel scale complex networks of functional connectivity in the rat brain: neurochemical state dependence of global and local topological properties. ( 0,595613264282394 )
IEEE Trans Neural Netw Learn Syst - A two-layer recurrent neural network for nonsmooth convex optimization problems. ( 0,594175476174438 )
Neural Comput - Information-geometric measures for estimation of connection weight under correlated inputs. ( 0,592385877050024 )
Neural Comput - Collective stability of networks of winner-take-all circuits. ( 0,5910811859374 )
Neural Comput - Traveling bumps and their collisions in a two-dimensional neural field. ( 0,590729494534719 )
Neural Comput - A new supervised learning algorithm for spiking neurons. ( 0,590377485388695 )
Brief. Bioinformatics - BioFNet: biological functional network database for analysis and synthesis of biological systems. ( 0,58915889958077 )
Neural Comput - Insights from a simple expression for linear fisher information in a recurrently connected population of spiking neurons. ( 0,58636507439618 )
J. Comput. Biol. - Node fingerprinting: an efficient heuristic for aligning biological networks. ( 0,586039706493932 )
J Chem Inf Model - New Markov-autocorrelation indices for re-evaluation of links in chemical and biological complex networks used in metabolomics, parasitology, neurosciences, and epidemiology. ( 0,585015864082143 )
J Biomed Inform - FALCON or how to compute measures time efficiently on dynamically evolving dense complex networks? ( 0,584684860648373 )
Neural Comput - Discovering functional neuronal connectivity from serial patterns in spike train data. ( 0,584155254687656 )
Neural Comput - Spike-timing-dependent construction. ( 0,583412750093592 )
IEEE Trans Neural Netw Learn Syst - Output-feedback adaptive neural control for stochastic nonlinear time-varying delay systems with unknown control directions. ( 0,583302803985789 )
Comput Math Methods Med - Results on a binding neuron model and their implications for modified hourglass model for neuronal network. ( 0,582512213051 )
Neural Comput - Mechanisms that modulate the transfer of spiking correlations. ( 0,581549382946784 )
Neural Comput - Neutral stability, rate propagation, and critical branching in feedforward networks. ( 0,5811231561997 )
Neural Comput - Natural gradient learning algorithms for RBF networks. ( 0,580011499289362 )
Neural Comput - Short-term memory capacity in networks via the restricted isometry property. ( 0,57742014046181 )
Wiley Interdiscip Rev Syst Biol Med - Adaptation of cells to new environments. ( 0,572667256109345 )
Neural Comput - Likelihood methods for point processes with refractoriness. ( 0,572106794904815 )
Brief. Bioinformatics - Inference of dynamic networks using time-course data. ( 0,572045453131902 )
Comput Methods Programs Biomed - In quest of the missing neuron: spike sorting based on dominant-sets clustering. ( 0,571444249126461 )
Neural Comput - A biological gradient descent for prediction through a combination of STDP and homeostatic plasticity. ( 0,571367910904225 )
Comput Methods Programs Biomed - Introducing treatment strategy for cerebellar ataxia in mutant med mice: combination of acetazolamide and 4-aminopyridine. ( 0,57099406998077 )
Neural Comput - Decorrelation by recurrent inhibition in heterogeneous neural circuits. ( 0,570311602782236 )
Comput Math Methods Med - Computational models of neuron-astrocyte interactions lead to improved efficacy in the performance of neural networks. ( 0,570113938393943 )
Int J Neural Syst - Relationship between applicability of current-based synapses and uniformity of firing patterns. ( 0,569767339909432 )
Neural Comput - The competing benefits of noise and heterogeneity in neural coding. ( 0,569253683772917 )
Neural Comput - Interactions of excitatory and inhibitory feedback topologies in facilitating pattern separation and retrieval. ( 0,567741680751974 )
Neural Comput - The rise and fall of memory in a model of synaptic integration. ( 0,567695739662112 )
Int J Neural Syst - A neuron-based time-optimal controller of horizontal saccadic eye movements. ( 0,567635281333824 )
Int J Neural Syst - Optimal sparse approximation with integrate and fire neurons. ( 0,567429229517161 )
Neural Comput - Signal-tuned Gabor functions as models for stimulus-dependent cortical receptive fields. ( 0,567285988658636 )
Int J Neural Syst - Perceptual suppression revealed by adaptive multi-scale entropy analysis of local field potential in monkey visual cortex. ( 0,566323204131405 )
Neural Comput - Projective clustering using neural networks with adaptive delay and signal transmission loss. ( 0,566024985194783 )
Neural Comput - Nearly extensive sequential memory lifetime achieved by coupled nonlinear neurons. ( 0,565028030614257 )
Neural Comput - Decorrelation of spiking variability and improved information transfer through feedforward divisive normalization. ( 0,563272571133216 )
Int J Neural Syst - Unorganized machines for seasonal streamflow series forecasting. ( 0,562699857885148 )
Neural Comput - Learning quadratic receptive fields from neural responses to natural stimuli. ( 0,561523424233976 )
Neural Comput - Motor cortex microcircuit simulation based on brain activity mapping. ( 0,561472075630773 )
Int J Neural Syst - Real-time EEG-based detection of fatigue driving danger for accident prediction. ( 0,560831645137985 )
Med Biol Eng Comput - An EEG-based real-time cortical functional connectivity imaging system. ( 0,560563882676958 )
IEEE Trans Neural Netw Learn Syst - Passivity and Passification of Memristor-Based Recurrent Neural Networks With Additive Time-Varying Delays. ( 0,560393411853599 )
Neural Comput - A bayesian model of polychronicity. ( 0,56035829739918 )
Neural Comput - Chaotic exploration and learning of locomotion behaviors. ( 0,560159439231981 )
J Chem Inf Model - Modeling complex metabolic reactions, ecological systems, and financial and legal networks with MIANN models based on Markov-Wiener node descriptors. ( 0,560151057796937 )
Neural Comput - Randomly connected networks have short temporal memory. ( 0,559962730120983 )
Comput Methods Programs Biomed - Optimization of microorganisms growth processes. ( 0,55972684660498 )
Neural Comput - Synaptic scaling stabilizes persistent activity driven by asynchronous neurotransmitter release. ( 0,559684512244848 )
Comput. Biol. Med. - Radial basis function neural networks applied to efficient QRST cancellation in atrial fibrillation. ( 0,55902437798745 )
Neural Comput - Computer modeling of mild axonal injury: implications for axonal signal transmission. ( 0,558252990317687 )
Neural Comput - Regulation of ambient GABA levels by neuron-glia signaling for reliable perception of multisensory events. ( 0,557819544590479 )
Neural Comput - Estimating parameters of generalized integrate-and-fire neurons from the maximum likelihood of spike trains. ( 0,557734950006991 )
Neural Comput - Intrinsic adaptation in autonomous recurrent neural networks. ( 0,557295959629742 )
Neural Comput - Analysis of the stabilized supralinear network. ( 0,556035855634978 )
J Chem Inf Model - Social network of isomers based on bond count distance: algorithms. ( 0,554512567670862 )
Neural Comput - Efficient calculation of the Gauss-Newton approximation of the Hessian matrix in neural networks. ( 0,554276671093192 )
Neural Comput - Broken symmetries in a location-invariant word recognition network. ( 0,552671295897571 )
IEEE Trans Vis Comput Graph - A Modular Degree-of-Interest Specification for the Visual Analysis of Large Dynamic Networks. ( 0,550798020485024 )
Neural Comput - Neural associative memory with optimal Bayesian learning. ( 0,549972726322083 )
Comput Math Methods Med - Analysis of epileptic seizures with complex network. ( 0,549914230272286 )
Neural Comput - Replicating receptive fields of simple and complex cells in primary visual cortex in a neuronal network model with temporal and population sparseness and reliability. ( 0,549746262063693 )
Neural Comput - Anatomical constraints on lateral competition in columnar cortical architectures. ( 0,546688763276491 )
Int J Neural Syst - Understanding Networks of Computing Chemical Droplet Neurons Based on Information Flow. ( 0,545345234078024 )
Neural Comput - A theoretical basis for emergent pattern discrimination in neural systems through slow feature extraction. ( 0,545206595231063 )
Neural Comput - New supervised learning theory applied to cerebellar modeling for suppression of variability of saccade end points. ( 0,544933851662998 )
Neural Comput - Noise facilitation in associative memories of exponential capacity. ( 0,544739647767023 )
Neural Comput - Multiplicative gain modulation arises through unsupervised learning in a predictive coding model of cortical function. ( 0,544666769332549 )
Neural Comput - Characterizing responses of translation-invariant neurons to natural stimuli: maximally informative invariant dimensions. ( 0,544303024764519 )