7 papers
How Data Augmentation Shapes Neural Representations
Tianxiao He, Alex H. Williams, Sarah E. Harvey
Data augmentation is widely recognized for improving generalization in deep networks, yet its impact on the geometry of learned representations remains poorly understood. In this w…
Modulating Cross-Modal Convergence with Single-Stimulus, Intra-Modal Dispersion
Eghbal A. Hosseini, Brian Cheung, Evelina Fedorenko +1
Neural networks exhibit a remarkable degree of representational convergence across diverse architectures, training objectives, and even data modalities. This convergence is predict…
Partial Soft-Matching Distance for Neural Representational Comparison with Partial Unit Correspondence
Chaitanya Kapoor, Alex H. Williams, Meenakshi Khosla
Representational similarity metrics typically force all units to be matched, making them susceptible to noise and outliers common in neural representations. We extend the soft-matc…
Quasi Monte Carlo methods enable extremely low-dimensional deep generative models
Miles Martinez, Alex H. Williams
This paper introduces quasi-Monte Carlo latent variable models (QLVMs): a class of deep generative models that are specialized for finding extremely low-dimensional and interpretab…
Modeling Neural Activity with Conditionally Linear Dynamical Systems
Victor Geadah, Amin Nejatbakhsh, David Lipshutz +2
Neural population activity exhibits complex, nonlinear dynamics, varying in time, over trials, and across experimental conditions. Here, we develop Conditionally Linear Dynamical S…
Discriminating image representations with principal distortions
Jenelle Feather, David Lipshutz, Sarah E. Harvey +2
Image representations (artificial or biological) are often compared in terms of their global geometric structure; however, representations with similar global structure can have st…