479 citations · 1.5k across the 53 of their papers we have counts for
8 papers · 1 filter
Continuous-Time Signal Decomposition: An Implicit Neural Generalization of PCA and ICA
Shayan K. Azmoodeh, Krishna Subramani, Paris Smaragdis
We generalize the low-rank decomposition problem, such as principal and independent component analysis (PCA, ICA) for continuous-time vector-valued signals and provide a model-agno…
Diagnosing Neural Convergence with Topological Alignment Spectra
Tiago F. Tavares, Fabio Ayres, Paris Smaragdis
Representational similarity in neural networks is inherently scale-dependent, yet widely used metrics such as Centered Kernel Alignment (CKA) and Procrustes analysis provide only g…
Two-Step Sound Source Separation: Training on Learned Latent Targets
Efthymios Tzinis, Shrikant Venkataramani, Zhepei Wang +2
In this paper, we propose a two-step training procedure for source separation via a deep neural network. In the first step we learn a transform (and it's inverse) to a latent space…
Continual Learning of New Sound Classes using Generative Replay
Zhepei Wang, Cem Subakan, Efthymios Tzinis +2
Continual learning consists in incrementally training a model on a sequence of datasets and testing on the union of all datasets. In this paper, we examine continual learning for t…
Unsupervised Deep Clustering for Source Separation: Direct Learning from Mixtures using Spatial Information
Efthymios Tzinis, Shrikant Venkataramani, Paris Smaragdis
We present a monophonic source separation system that is trained by only observing mixtures with no ground truth separation information. We use a deep clustering approach which tra…
Learning the Base Distribution in Implicit Generative Models
Cem Subakan, Oluwasanmi Koyejo, Paris Smaragdis
Popular generative model learning methods such as Generative Adversarial Networks (GANs), and Variational Autoencoders (VAE) enforce the latent representation to follow simple dist…
Bitwise Neural Networks
Minje Kim, Paris Smaragdis
Based on the assumption that there exists a neural network that efficiently represents a set of Boolean functions between all binary inputs and outputs, we propose a process for de…
A Dictionary Learning Approach for Factorial Gaussian Models
Y. Cem Subakan, Johannes Traa, Paris Smaragdis +1
In this paper, we develop a parameter estimation method for factorially parametrized models such as Factorial Gaussian Mixture Model and Factorial Hidden Markov Model. Our contribu…