The methods are (1) easy to implement and (2) broadly applicable across clustering algorithms, which could make them highly impactful.
We show that self-supervised models are not as robust as expected based on their results in natural imaging benchmarks and can be outperformed by supervised learning with dropout.
Although distributed machine learning has opened up numerous frontiers of research, the separation of large models across different devices, nodes, and sites can invite significant communication overhead, making reliable training difficult.
Sensory input from multiple sources is crucial for robust and coherent human perception.
In this paper, we introduce a way to exhaustively consider multimodal architectures for contrastive self-supervised fusion of fMRI and MRI of AD patients and controls.
In this paper we present a novel self supervised training schema which reinforces whole sequence mutual information local to context (whole MILC).
In the last two decades, unsupervised latent variable models---blind source separation (BSS) especially---have enjoyed a strong reputation for the interpretable features they produce.
In this work, we propose a differentially private algorithm for performing ICA in a decentralized data setting.
In this paper, we present our approach to solve a physics-based reinforcement learning challenge "Learning to Run" with objective to train physiologically-based human model to navigate a complex obstacle course as quickly as possible.
We introduce a novel recurrent neural network (RNN) approach to account for temporal dynamics and dependencies in brain networks observed via functional magnetic resonance imaging (fMRI).
Independent component analysis (ICA), as an approach to the blind source-separation (BSS) problem, has become the de-facto standard in many medical imaging settings.
In this work we demonstrate our results (and feasible parameter ranges) in application of deep learning methods to structural and functional brain imaging data.
However, present algorithms designed for optimizing the mixed norm L$_1$/L$_2$ are slow and other formulations for sparse NMF have been proposed such as those based on L$_1$ and L$_0$ norms.