21 citations
- University College LondonGB5 papers
- Google DeepMind (United Kingdom)GB2 papers
- Helsinki Institute for Information TechnologyFI2 papers
- Google (United States)US1 paper
- Nara Institute of Science and TechnologyJP1 paper
- RIKENJP1 paper
- RIKEN Center for Advanced Intelligence ProjectJP1 paper
- The University of TokyoJP1 paper
- Tokyo Institute of TechnologyJP1 paper
- Toyota Technological Institute at ChicagoUS1 paper
5 papers
Learning deep kernels for exponential family densities
Li Wenliang, Danica J. Sutherland, Heiko Strathmann +1
The kernel exponential family is a rich class of distributions, which can be fit efficiently and with statistical guarantees by score matching. Being required to choose a priori a…
A Unified Probabilistic Model for Learning Latent Factors and Their Connectivities from High-Dimensional Data
Ricardo Pio Monti, Aapo Hyvärinen
Connectivity estimation is challenging in the context of high-dimensional data. A useful preprocessing step is to group variables into clusters, however, it is not always clear how…
Fast Parametric Learning with Activation Memorization
Jack W Rae, Chris Dyer, Peter Dayan +1
Neural networks trained with backpropagation often struggle to identify classes that have been observed a small number of times. In applications where most class labels are rare, s…
Mode-Seeking Clustering and Density Ridge Estimation via Direct Estimation of Density-Derivative-Ratios
Hiroaki Sasaki, Takafumi Kanamori, Aapo Hyvärinen +2
Modes and ridges of the probability density function behind observed data are useful geometric features. Mode-seeking clustering assigns cluster labels by associating data samples…
A unifying framework for understanding state-dependent network dynamics in cortex
Alexander Lerchner, Peter E. Latham
Activity in neocortex exhibits a range of behaviors, from irregular to temporally precise, and from weakly to strongly correlated. So far there has been no single theoretical frame…