Biologically-Plausible Determinant Maximization Neural Networks for Blind Separation of Correlated Sources
Nov 28, 2022
Speakers
Bariscan Bozkurt
Speaker · 0 followers
Cengiz Pehlevan
Speaker · 0 followers
Alper T. Erdogan
Speaker · 0 followers
About
Extraction of latent sources of complex stimuli is critical for making sense of the world. While the brain solves this blind source separation (BSS) problem continuously, its algorithms remain unknown. Previous work on biologically-plausible BSS algorithms assumed that observed signals are linear mixtures of statistically independent or uncorrelated sources, limiting the domain of applicability of these algorithms. To overcome this limitation, we propose novel biologically-plausible neural networks for the blind separation of potentially dependent/correlated sources. Differing from previous work, we assume some general geometric, not statistical, conditions on the source vectors allowing separation of potentially dependent/correlated sources. Concretely, we assume that the source vectors are sufficiently scattered in their domains which can be described by certain polytopes. Then, we consider recovery of these sources by the Det-Max criterion, which maximizes the determinant of the output correlation matrix to enforce a similar spread for the source estimates. Starting from this normative principle, and using a weighted similarity matching approach that enables arbitrary linear transformations adaptable by local learning rules, we derive two-layer biologically-plausible neural network algorithms that can separate mixtures into sources coming from a variety of source domains. We demonstrate that our algorithms outperform other biologically-plausible BSS algorithms on correlated source separation problems.Extraction of latent sources of complex stimuli is critical for making sense of the world. While the brain solves this blind source separation (BSS) problem continuously, its algorithms remain unknown. Previous work on biologically-plausible BSS algorithms assumed that observed signals are linear mixtures of statistically independent or uncorrelated sources, limiting the domain of applicability of these algorithms. To overcome this limitation, we propose novel biologically-plausible neural netwo…
Organizer
NeurIPS 2022
Account · 952 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
A Probabilistic Graph Coupling View of Dimension Reduction
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
DriveCLIP: Zero-shot transfer for distracted driving activity understanding using CLIP
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Adaptive Multi-stage Density Ratio Estimation for Learning Latent Space Energy-based Model
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Conditional Diffusion Process for Inverse Halftoning
Watch later
Hao Jiang, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
HorNet: Efficient High-Order Spatial Interactions with Recursive Gated Convolutions
Watch later
Yongming Rao, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Effectiveness of Vision Transformer for Fast and Accurate Single-Stage Pedestrian Detector
Watch later
Jing Yuan, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%