Author name cluster

Virginia de

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

1 author row

NeurIPS Conference 1997 Conference Paper

Using Helmholtz Machines to Analyze Multi-channel Neuronal Recordings

Virginia de
R. DeCharms
Michael Merzenich

One of the current challenges to understanding neural information processing in biological systems is to decipher the "code" carried by large populations of neurons acting in parallel. We present an algorithm for automated discovery of stochastic firing patterns in large ensembles of neurons. The algorithm, from the "Helmholtz Machine" family, attempts to predict the observed spike patterns in the data. The model consists of an observable layer which is directly activated by the input spike patterns, and hidden units that are ac(cid: 173) tivated through ascending connections from the input layer. The hidden unit activity can be propagated down to the observable layer to create a prediction of the data pattern that produced it. Hidden units are added incrementally and their weights are adjusted to im(cid: 173) prove the fit between the predictions and data, that is, to increase a bound on the probability of the data given the model. This greedy strategy is not globally optimal but is computationally tractable for large populations of neurons. We show benchmark data on artifi(cid: 173) cially constructed spike trains and promising early results on neuro(cid: 173) physiological data collected from our chronic multi-electrode cortical implant.

PDF Details

NeurIPS Conference 1996 Conference Paper

Promoting Poor Features to Supervisors: Some Inputs Work Better as Outputs

Rich Caruana
Virginia de

In supervised learning there is usually a clear distinction between inputs and outputs - inputs are what you will measure, outputs are what you will predict from those measurements. This paper shows that the distinction between inputs and outputs is not this simple. Some features are more useful as extra outputs than as inputs. By using a feature as an output we get more than just the case values but can. learn a mapping from the other inputs to that feature. For many features this mapping may be more useful than the feature value itself. We present two regression problems and one classification problem where performance improves if features that could have been used as inputs are used as extra outputs instead. This result is surprising since a feature used as an output is not used during testing.

PDF Details

NeurIPS Conference 1993 Conference Paper

Learning Classification with Unlabeled Data

Virginia de

One of the advantages of supervised learning is that the final error met(cid: 173) ric is available during training. For classifiers, the algorithm can directly reduce the number of misclassifications on the training set. Unfortu(cid: 173) nately, when modeling human learning or constructing classifiers for au(cid: 173) tonomous robots, supervisory labels are often not available or too ex(cid: 173) pensive. In this paper we show that we can substitute for the labels by making use of structure between the pattern distributions to different sen(cid: 173) sory modalities. We show that minimizing the disagreement between the outputs of networks processing patterns from these different modalities is a sensible approximation to minimizing the number of misclassifications in each modality, and leads to similar results. Using the Peterson-Barney vowel dataset we show that the algorithm performs well in finding ap(cid: 173) propriate placement for the codebook vectors particularly when the con(cid: 173) fuseable classes are different for the two modalities.

PDF Details

NeurIPS Conference 1992 Conference Paper

A Note on Learning Vector Quantization

Virginia de
Dana Ballard

Vector Quantization is useful for data compression. Competitive Learn(cid: 173) ing which minimizes reconstruction error is an appropriate algorithm for vector quantization of unlabelled data. Vector quantization of labelled data for classification has a different objective, to minimize the number of misclassifications, and a different algorithm is appropriate. We show that a variant of Kohonen's LVQ2. 1 algorithm can be seen as a multi(cid: 173) class extension of an algorithm which in a restricted 2 class case can be proven to converge to the Bayes optimal classification boundary. We compare the performance of the LVQ2. 1 algorithm to that of a modified version having a decreasing window and normalized step size, on a ten class vowel classification problem.

PDF Details