Abstract Missing

We describe a neuromorphic chip that uses binary synapses with spike timing-dependent plasticity (STDP) to learn stimulated patterns of activity andto compensate for variability in excitability. Specifically, STDP preferentially potentiates (turns on) synapses that project from excitable neurons, which spike early, to lethargic neurons, which spike late. The additional excitatory synaptic current makes lethargic neurons spike earlier, therebycausing neurons that belong to the same pattern to spike in synchrony. Once learned, an entire pattern can be recalled by stimulating a subset.

Abstract Missing

Consider the problem of joint parameter estimation and prediction in a Markov random field: i.e., the model parameters are estimated on the basis of an initial setof data, and then the fitted model is used to perform prediction (e.g., smoothing, denoising, interpolation) on a new noisy observation. Working in the computation-limited setting, we analyze a joint method in which the same convex variational relaxation is used to construct an M-estimator for fitting parameters, and to perform approximate marginalization for the prediction step. The key result ofthis paper is that in the computation-limited setting, using an inconsistent parameter estimator (i.e., an estimator that returns the "wrong" model even in the infinite data limit) is provably beneficial, since the resulting errors can partially compensatefor errors made by using an approximate prediction technique. En route to this result, we analyze the asymptotic properties of M-estimators based on convex variational relaxations, and establish a Lipschitz stability property thatholds for a broad class of variational methods. We show that joint estimation/prediction basedon the reweighted sum-product algorithm substantially outperforms a commonly used heuristic based on ordinary sum-product.

We address the problem of robust, computationally-efficient design of biological experiments.

This paper provides a system-level analysis of a scalable distributed sensing modelfor networked sensors. In our system model, a data center acquires datafrom a bunch of L sensors which each independently encode their noisy observations of an original binary sequence, and transmit their encoded data sequences to the data center at a combined rate R, which is limited. Supposing that the sensors use independent LDGM rate distortion codes,we show that the system performance can be evaluated for any given finite R when the number of sensors L goes to infinity. The analysis shows how the optimal strategy for the distributed sensing problem changesat critical values of the data rate R or the noise level.

Images represent an important and abundant source of data. Understanding theirstatistical structure has important applications such as image compression and restoration. In this paper we propose a particular kind of probabilistic model, dubbed the "products of edge-perts model" to describe thestructure of wavelet transformed images. We develop a practical denoising algorithm based on a single edge-pert and show state-ofthe-art denoisingperformance on benchmark images.

We propose a new Bayesian method for spatial cluster detection, the "Bayesian spatial scan statistic," and compare this method to the standard (frequentist) scan statistic approach. We demonstrate that the Bayesian statistic has several advantages over the frequentist approach, including increased power to detect clusters and (since randomization testing is unnecessary) much faster runtime. We evaluate the Bayesian and frequentist methodson the task of prospective disease surveillance: detecting spatial clusters of disease cases resulting from emerging disease outbreaks. Wedemonstrate that our Bayesian methods are successful in rapidly detecting outbreaks while keeping number of false positives low.

Given a redundant dictionary of basis vectors (or atoms), our goal is to find maximally sparse representations of signals. Previously, we have argued that a sparse Bayesian learning (SBL) framework is particularly well-suited for this task, showing that it has far fewer local minima than other Bayesian-inspired strategies. In this paper, we provide further evidence forthis claim by proving a restricted equivalence condition, based on the distribution of the nonzero generating model weights, whereby the SBL solution will equal the maximally sparse representation. We also prove that if these nonzero weights are drawn from an approximate Jeffreys prior,then with probability approaching one, our equivalence condition issatisfied.

MRF/CRF models focus on pixel-level labeling, requiring inferences over millions of pixels.