Search Results for author:
Found 11 papers, 8 papers with code
Deep Generative Models of Music Expectation
In prior work, this idea has been operationalized in the form of probabilistic models of music which allow for precise computation of song (or note-by-note) probabilities, conditioned on a 'training set' of prior musical or cultural experiences.
Flow Factorized Representation Learning
A prominent goal of representation learning research is to achieve representations which are factorized in a useful manner with respect to the ground truth factors of variation.
Traveling Waves Encode the Recent Past and Enhance Sequence Learning
Traveling waves of neural activity have been observed throughout the brain at a diversity of regions and scales; however, their precise computational role is still debated.
DUET: 2D Structured and Approximately Equivariant Representations
We propose 2D strUctured and EquivarianT representations (coined DUET), which are 2d representations organized in a matrix structure, and equivariant with respect to transformations acting on the input data.
Latent Traversals in Generative Models as Potential Flows
In this work, we instead propose to model latent structures with a learned dynamic potential landscape, thereby performing latent traversals as the flow of samples down the landscape's gradient.
Homomorphic Self-Supervised Learning
In this work, we observe that many existing self-supervised learning algorithms can be both unified and generalized when seen through the lens of equivariant representations.
Modeling Category-Selective Cortical Regions with Topographic Variational Autoencoders
Category-selectivity in the brain describes the observation that certain spatially localized areas of the cerebral cortex tend to respond robustly and selectively to stimuli from specific limited categories.
Topographic VAEs learn Equivariant Capsules
Finally, we demonstrate approximate equivariance to complex transformations, expanding upon the capabilities of existing group equivariant neural networks.
As easy as APC: overcoming missing data and class imbalance in time series with self-supervised learning
High levels of missing data and strong class imbalance are ubiquitous challenges that are often presented simultaneously in real-world time series data.
Ranked #1 on
Time Series Classification
on PhysioNet Challenge 2012
(AUPRC metric)
Self Normalizing Flows
Efficient gradient computation of the Jacobian determinant term is a core problem in many machine learning settings, and especially so in the normalizing flow framework.
Fast Weight Long Short-Term Memory
Associative memory using fast weights is a short-term memory mechanism that substantially improves the memory capacity and time scale of recurrent neural networks (RNNs).
