Abstract:
:Particular levels of partial fault tolerance (PFT) in feedforward artificial neural networks of a given size can be obtained by redundancy (replicating a smaller normally trained network), by design (training specifically to increase PFT), and by a combination of the two (replicating a smaller PFT-trained network). This letter investigates the method of achieving the highest PFT per network size (total number of units and connections) for classification problems. It concludes that for non-toy problems, there exists a normally trained network of optimal size that produces the smallest fully fault-tolerant network when replicated. In addition, it shows that for particular network sizes, the best level of PFT is achieved by training a network of that size for fault tolerance. The results and discussion demonstrate how the outcome depends on the levels of saturation of the network nodes when classifying data points. With simple training tasks, where the complexity of the problem and the size of the network are well within the ability of the training method, the hidden-layer nodes operate close to their saturation points, and classification is clean. Under such circumstances, replicating the smallest normally trained correct network yields the highest PFT for any given network size. For hard training tasks (difficult classification problems or network sizes close to the minimum), normal training obtains networks that do not operate close to their saturation points, and outputs are not as close to their targets. In this case, training a larger network for fault tolerance yields better PFT than replicating a smaller, normally trained network. However, since fault-tolerant training on its own produces networks that operate closer to their linear areas than normal training, replicating normally trained networks ultimately leads to better PFT than replicating fault-tolerant networks of the same initial size.
journal_name
Neural Computjournal_title
Neural computationauthors
Tchernev EB,Mulvaney RG,Phatak DSdoi
10.1162/0899766053723096subject
Has Abstractpub_date
2005-07-01 00:00:00pages
1646-64issue
7eissn
0899-7667issn
1530-888Xjournal_volume
17pub_type
杂志文章abstract::In a previous article, we considered game trees as graphical models. Adopting an evaluation function that returned a probability distribution over values likely to be taken at a given position, we described how to build a model of uncertainty and use it for utility-directed growth of the search tree and for deciding o...
journal_title:Neural computation
pub_type: 杂志文章
doi:10.1162/089976699300016881
更新日期:1999-01-01 00:00:00
abstract::We present a new supervised learning procedure for ensemble machines, in which outputs of predictors, trained on different distributions, are combined by a dynamic classifier combination model. This procedure may be viewed as either a version of mixture of experts (Jacobs, Jordan, Nowlan, & Hintnon, 1991), applied to ...
journal_title:Neural computation
pub_type: 杂志文章
doi:10.1162/089976699300016737
更新日期:1999-02-15 00:00:00
abstract::A fast and accurate computational scheme for simulating nonlinear dynamic systems is presented. The scheme assumes that the system can be represented by a combination of components of only two different types: first-order low-pass filters and static nonlinearities. The parameters of these filters and nonlinearities ma...
journal_title:Neural computation
pub_type: 信件
doi:10.1162/neco.2008.04-07-506
更新日期:2008-07-01 00:00:00
abstract::In this letter, we develop a gaussian process model for clustering. The variances of predictive values in gaussian processes learned from a training data are shown to comprise an estimate of the support of a probability density function. The constructed variance function is then applied to construct a set of contours ...
journal_title:Neural computation
pub_type: 杂志文章
doi:10.1162/neco.2007.19.11.3088
更新日期:2007-11-01 00:00:00
abstract::A mathematical model, of general character for the dynamic description of coupled neural oscillators is presented. The population approach that is employed applies equally to coupled cells as to populations of such coupled cells. The formulation includes stochasticity and preserves details of precisely firing neurons....
journal_title:Neural computation
pub_type: 杂志文章
doi:10.1162/neco.2007.03-07-482
更新日期:2008-05-01 00:00:00
abstract::In this work, we discuss practical methods for the assessment, comparison, and selection of complex hierarchical Bayesian models. A natural way to assess the goodness of the model is to estimate its future predictive capability by estimating expected utilities. Instead of just making a point estimate, it is important ...
journal_title:Neural computation
pub_type: 杂志文章
doi:10.1162/08997660260293292
更新日期:2002-10-01 00:00:00
abstract::In a pioneering classic, Warren McCulloch and Walter Pitts proposed a model of the central nervous system. Motivated by EEG recordings of normal brain activity, Chvátal and Goldsmith asked whether these dynamical systems can be engineered to produce trajectories that are irregular, disorderly, and apparently unpredict...
journal_title:Neural computation
pub_type: 杂志文章
doi:10.1162/NECO_a_00841
更新日期:2016-06-01 00:00:00
abstract::Controlling for multiple hypothesis tests using standard spike resampling techniques often requires prohibitive amounts of computation. Importance sampling techniques can be used to accelerate the computation. The general theory is presented, along with specific examples for testing differences across conditions using...
journal_title:Neural computation
pub_type: 杂志文章
doi:10.1162/NECO_a_00399
更新日期:2013-02-01 00:00:00
abstract::Calculation of the total conductance change induced by multiple synapses at a given membrane compartment remains one of the most time-consuming processes in biophysically realistic neural network simulations. Here we show that this calculation can be achieved in a highly efficient way even for multiply converging syna...
journal_title:Neural computation
pub_type: 杂志文章
doi:10.1162/089976698300017061
更新日期:1998-10-01 00:00:00
abstract::Neural associative memories are perceptron-like single-layer networks with fast synaptic learning typically storing discrete associations between pairs of neural activity patterns. Previous work optimized the memory capacity for various models of synaptic learning: linear Hopfield-type rules, the Willshaw model employ...
journal_title:Neural computation
pub_type: 杂志文章
doi:10.1162/NECO_a_00127
更新日期:2011-06-01 00:00:00
abstract::Reservoir computing is a biologically inspired class of learning algorithms in which the intrinsic dynamics of a recurrent neural network are mined to produce target time series. Most existing reservoir computing algorithms rely on fully supervised learning rules, which require access to an exact copy of the target re...
journal_title:Neural computation
pub_type: 杂志文章
doi:10.1162/neco_a_01198
更新日期:2019-07-01 00:00:00
abstract::Synchronized firings in the networks of class 1 excitable neurons with excitatory and inhibitory connections are investigated, and their dependences on the forms of interactions are analyzed. As the forms of interactions, we treat the double exponential coupling and the interactions derived from it: pulse coupling, ex...
journal_title:Neural computation
pub_type: 杂志文章
doi:10.1162/0899766053630387
更新日期:2005-06-01 00:00:00
abstract::Disparity tuning of visual cells in the brain depends on the structure of their binocular receptive fields (RFs). Freeman and coworkers have found that binocular RFs of a typical simple cell can be quantitatively described by two Gabor functions with the same gaussian envelope but different phase parameters in the sin...
journal_title:Neural computation
pub_type: 杂志文章
doi:10.1162/neco.1996.8.8.1611
更新日期:1996-11-15 00:00:00
abstract::A necessary ingredient for a quantitative theory of neural coding is appropriate "spike kinematics": a precise description of spike trains. While summarizing experiments by complete spike time collections is clearly inefficient and probably unnecessary, the most common probabilistic model used in neurophysiology, the ...
journal_title:Neural computation
pub_type: 杂志文章
doi:10.1162/neco.2009.07-08-828
更新日期:2009-08-01 00:00:00
abstract::We extend the neural Turing machine (NTM) model into a dynamic neural Turing machine (D-NTM) by introducing trainable address vectors. This addressing scheme maintains for each memory cell two separate vectors, content and address vectors. This allows the D-NTM to learn a wide variety of location-based addressing stra...
journal_title:Neural computation
pub_type: 杂志文章
doi:10.1162/neco_a_01060
更新日期:2018-04-01 00:00:00
abstract::We study active learning (AL) based on gaussian processes (GPs) for efficiently enumerating all of the local minimum solutions of a black-box function. This problem is challenging because local solutions are characterized by their zero gradient and positive-definite Hessian properties, but those derivatives cannot be ...
journal_title:Neural computation
pub_type: 杂志文章
doi:10.1162/neco_a_01307
更新日期:2020-10-01 00:00:00
abstract::Durbin and Willshaw's elastic net algorithm can find good solutions to the TSP. The purpose of this paper is to point out that for certain ranges of parameter values, the algorithm converges into local minima that do not correspond to valid tours. The key parameter is the ratio governing the relative strengths of the ...
journal_title:Neural computation
pub_type: 杂志文章
doi:10.1162/neco.1991.3.3.363
更新日期:1991-10-01 00:00:00
abstract::We show that Langevin Markov chain Monte Carlo inference in an energy-based model with latent variables has the property that the early steps of inference, starting from a stationary point, correspond to propagating error gradients into internal layers, similar to backpropagation. The backpropagated error is with resp...
journal_title:Neural computation
pub_type: 杂志文章
doi:10.1162/NECO_a_00934
更新日期:2017-03-01 00:00:00
abstract::The important task of generating the minimum number of sequential triangle strips (tristrips) for a given triangulated surface model is motivated by applications in computer graphics. This hard combinatorial optimization problem is reduced to the minimum energy problem in Hopfield nets by a linear-size construction. I...
journal_title:Neural computation
pub_type: 杂志文章
doi:10.1162/neco.2008.10-07-623
更新日期:2009-02-01 00:00:00
abstract::One standard interpretation of networks of cortical neurons is that they form dynamical attractors. Computations such as stimulus estimation are performed by mapping inputs to points on the networks' attractive manifolds. These points represent population codes for the stimulus values. However, this standard interpret...
journal_title:Neural computation
pub_type: 杂志文章
doi:10.1162/NECO_a_00051
更新日期:2010-12-01 00:00:00
abstract::We show how a Hopfield network with modifiable recurrent connections undergoing slow Hebbian learning can extract the underlying geometry of an input space. First, we use a slow and fast analysis to derive an averaged system whose dynamics derives from an energy function and therefore always converges to equilibrium p...
journal_title:Neural computation
pub_type: 杂志文章
doi:10.1162/NECO_a_00322
更新日期:2012-09-01 00:00:00
abstract::We derive a synaptic weight update rule for learning temporally precise spike train-to-spike train transformations in multilayer feedforward networks of spiking neurons. The framework, aimed at seamlessly generalizing error backpropagation to the deterministic spiking neuron setting, is based strictly on spike timing ...
journal_title:Neural computation
pub_type: 杂志文章
doi:10.1162/NECO_a_00829
更新日期:2016-05-01 00:00:00
abstract::Independent component analysis (ICA) finds a linear transformation to variables that are maximally statistically independent. We examine ICA and algorithms for finding the best transformation from the point of view of maximizing the likelihood of the data. In particular, we discuss the way in which scaling of the unmi...
journal_title:Neural computation
pub_type: 杂志文章
doi:10.1162/089976699300016043
更新日期:1999-11-15 00:00:00
abstract::We have created a network that allocates a new computational unit whenever an unusual pattern is presented to the network. This network forms compact representations, yet learns easily and rapidly. The network can be used at any time in the learning process and the learning patterns do not have to be repeated. The uni...
journal_title:Neural computation
pub_type: 杂志文章
doi:10.1162/neco.1991.3.2.213
更新日期:1991-07-01 00:00:00
abstract::We present formal specification and verification of a robot moving in a complex network, using temporal sequence learning to avoid obstacles. Our aim is to demonstrate the benefit of using a formal approach to analyze such a system as a complementary approach to simulation. We first describe a classical closed-loop si...
journal_title:Neural computation
pub_type: 杂志文章
doi:10.1162/NECO_a_00493
更新日期:2013-11-01 00:00:00
abstract::Primary visual cortical complex cells are thought to serve as invariant feature detectors and to provide input to higher cortical areas. We propose a single model for learning the connectivity required by complex cells that integrates two factors that have been hypothesized to play a role in the development of invaria...
journal_title:Neural computation
pub_type: 杂志文章
doi:10.1162/NECO_a_00743
更新日期:2015-07-01 00:00:00
abstract::The visual systems of many mammals, including humans, are able to integrate the geometric information of visual stimuli and perform cognitive tasks at the first stages of the cortical processing. This is thought to be the result of a combination of mechanisms, which include feature extraction at the single cell level ...
journal_title:Neural computation
pub_type: 杂志文章
doi:10.1162/NECO_a_00738
更新日期:2015-06-01 00:00:00
abstract::In this review, we compare methods for temporal sequence learning (TSL) across the disciplines machine-control, classical conditioning, neuronal models for TSL as well as spike-timing-dependent plasticity (STDP). This review introduces the most influential models and focuses on two questions: To what degree are reward...
journal_title:Neural computation
pub_type: 杂志文章,评审
doi:10.1162/0899766053011555
更新日期:2005-02-01 00:00:00
abstract::Different analytical expressions for the membrane potential distribution of membranes subject to synaptic noise have been proposed and can be very helpful in analyzing experimental data. However, all of these expressions are either approximations or limit cases, and it is not clear how they compare and which expressio...
journal_title:Neural computation
pub_type: 杂志文章
doi:10.1162/neco.2006.18.12.2917
更新日期:2006-12-01 00:00:00
abstract::Previous studies have combined analytical models of stochastic neural responses with signal detection theory (SDT) to predict psychophysical performance limits; however, these studies have typically been limited to simple models and simple psychophysical tasks. A companion article in this issue ("Evaluating Auditory P...
journal_title:Neural computation
pub_type: 杂志文章
doi:10.1162/089976601750541813
更新日期:2001-10-01 00:00:00