Bridging large-scale neuronal recordings and large-scale network models using dimensionality reduction

Puzzle Imaging: Using Large-Scale Dimensionality Reduction Algorithms for Localization

Current high-resolution imaging techniques require an intact sample that preserves spatial relationships. We here present a novel approach, "puzzle imaging," that allows imaging a spatially scrambled sample. This technique takes many spatially disordered samples, and then pieces them back together using local properties embedded within the sample. We show that puzzle imaging can efficiently pro...

The Effect of Dimensionality Reduction on Large Scale Hierarchical Classification

Many classification problems are related to a hierarchy of classes, that can be exploited in order to perform hierarchical classification of test objects. The most basic way of hierarchical classification is that of cascade classification, which greedily traverses the hierarchy from root to the predicted leaf. In order to perform cascade classification, a classifier must be trained for each nod...

Order reduction of large scale DAE models

A tool for the order reduction of differential algebraic equations (DAEs) is outlined in this report. Through the use of an equation dependency analysis and nonlinear function approximation, the algebraic equations can be divided into sets that require implicit or explicit solutions. If all of the algebraic variables can be solved or approximated explicitly, the DAE becomes a set of ordinary di...

Large - Scale Neuronal

Large Scale Hierarchical Neural Network Language Models

Feed-forward neural network language models (NNLMs) are known to improve both perplexity and word error rate performance for speech recognition compared with conventional ngram language models. We present experimental results showing how much the WER can be improved by increasing the scale of the NNLM, in terms of model size and training data. However, training time can become very long. We imp...