Timothy A. Keller
YOU?
Author Swipe
View article: Flow Equivariant Recurrent Neural Networks
Flow Equivariant Recurrent Neural Networks Open
Data arrives at our senses as a continuous stream, smoothly transforming from one instant to the next. These smooth transformations can be viewed as continuous symmetries of the environment that we inhabit, defining equivalence relations b…
View article: The neural and cognitive basis of expository text comprehension
The neural and cognitive basis of expository text comprehension Open
As science and technology rapidly progress, it becomes increasingly important to understand how individuals comprehend expository technical texts that explain these advances. This study examined differences in individual readers’ technical…
View article: Deep Generative Models of Music Expectation
Deep Generative Models of Music Expectation Open
A prominent theory of affective response to music revolves around the concepts of surprisal and expectation. In prior work, this idea has been operationalized in the form of probabilistic models of music which allow for precise computation…
View article: Flow Factorized Representation Learning
Flow Factorized Representation Learning Open
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. The fields of disentangled and equivariant representation lea…
View article: DNPLab/DNPLab: DNPLab 1.0.8
DNPLab/DNPLab: DNPLab 1.0.8 Open
Fix issue with importing winEPR parameters Removing HydrationGUI Adding polyfit function
View article: Modeling Category-Selective Cortical Regions with Topographic Variational Autoencoders
Modeling Category-Selective Cortical Regions with Topographic Variational Autoencoders Open
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. One of the most well known exam…
View article: Predictive Coding with Topographic Variational Autoencoders
Predictive Coding with Topographic Variational Autoencoders Open
Predictive coding is a model of visual processing which suggests that the brain is a generative model of input, with prediction error serving as a signal for both learning and attention. In this work, we show how the equivariant capsules l…
View article: DNPLab/DNPLab: 1.0.7
DNPLab/DNPLab: 1.0.7 Open
Updated Documentation Improvements to Alignment Function New lineshape functions added
View article: Topographic VAEs learn Equivariant Capsules
Topographic VAEs learn Equivariant Capsules Open
In this work we seek to bridge the concepts of topographic organization and equivariance in neural networks. To accomplish this, we introduce the Topographic VAE: a novel method for efficiently training deep generative models with topograp…
View article: DNPLab/DNPLab: DNPLab 1.0.5
DNPLab/DNPLab: DNPLab 1.0.5 Open
Bug fixes for topspin import New widgets for manual phasing and alignment of spectra
View article: Self Normalizing Flows
Self Normalizing Flows Open
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. Most proposed flow models therefore either restrict to a function cla…
View article: As easy as APC: overcoming missing data and class imbalance in time series with self-supervised learning
As easy as APC: overcoming missing data and class imbalance in time series with self-supervised learning Open
High levels of missing data and strong class imbalance are ubiquitous challenges that are often presented simultaneously in real-world time series data. Existing methods approach these problems separately, frequently making significant ass…
View article: As easy as APC: Leveraging self-supervised learning in the context of time series classification with varying levels of sparsity and severe class imbalance.
As easy as APC: Leveraging self-supervised learning in the context of time series classification with varying levels of sparsity and severe class imbalance. Open
High levels of sparsity and strong class imbalance are ubiquitous challenges that are often presented simultaneously in real-world time series data. While most methods tackle each problem separately, our proposed approach handles both in c…
View article: DNPLab/DNPLab: DNPLab 1.0.4
DNPLab/DNPLab: DNPLab 1.0.4 Open
Improved documentation Fixed issues with saving h5 files Improvements to Hydration GUI Improvements to importing data
View article: Self Normalizing Flows
Self Normalizing Flows Open
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. Most proposed flow models therefore either restrict to a function cla…
View article: Reduced White Matter Integrity and Deficits in Neuropsychological Functioning in Adults With Autism Spectrum Disorder
Reduced White Matter Integrity and Deficits in Neuropsychological Functioning in Adults With Autism Spectrum Disorder Open
Autism spectrum disorder (ASD) is currently viewed as a disorder of cortical systems connectivity, with a heavy emphasis being on the structural integrity of white matter tracts. However, the majority of the literature to date has focused …
View article: Fast Weight Long Short-Term Memory
Fast Weight Long Short-Term Memory Open
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). As recent studies introduced fast weights only to regular RNNs, it i…
View article: Attention-tonotopy stimulus for mapping attention across auditory cortex
Attention-tonotopy stimulus for mapping attention across auditory cortex Open
This audio file offers an example stimulus in which attention is first directed to a lower-frequency band with a higher-frequency distractor band. Listen for the repeat of the 4-tone mini-sequence. The voice directs attention to the lower-…
View article: Extensive Tonotopic Mapping across Auditory Cortex Is Recapitulated by Spectrally Directed Attention and Systematically Related to Cortical Myeloarchitecture
Extensive Tonotopic Mapping across Auditory Cortex Is Recapitulated by Spectrally Directed Attention and Systematically Related to Cortical Myeloarchitecture Open
Auditory selective attention is vital in natural soundscapes. But it is unclear how attentional focus on the primary dimension of auditory representation—acoustic frequency—might modulate basic auditory functional topography during active …
View article: Extensive tonotopic mapping across auditory cortex is recapitulated by spectrally-directed attention, and systematically related to cortical myeloarchitecture
Extensive tonotopic mapping across auditory cortex is recapitulated by spectrally-directed attention, and systematically related to cortical myeloarchitecture Open
Auditory selective attention is vital in natural soundscapes. But, it is unclear how attentional focus on the primary dimension of auditory representation - acoustic frequency - might modulate basic auditory functional topography during ac…