This work proposes a novel practical and general-purpose lossless compression algorithm named Neural Markovian Predictive Compression (NMPC), based on a novel combination of Bayesi...
: Recurrent neural networks possess interesting universal approximation capabilities, making them good candidates for time series modeling. Unfortunately, long term dependencies ar...
Learning to recognize or predict sequences using long-term context has many applications. However, practical and theoretical problems are found in training recurrent neural networ...
We consider the issue of how to read out the information from nonstationary spike train ensembles. Based on the theory of censored data in statistics, we propose a ‘censored’ m...
Background: Generally speaking, different classifiers tend to work well for certain types of data and conversely, it is usually not known a priori which algorithm will be optimal ...