Search Results for author:
Found 15 papers, 3 papers with code
A separability-based approach to quantifying generalization: which layer is best?
Which layers of a network are likely to generalize best?
Learning dynamic representations of the functional connectome in neurobiological networks
We introduce an unsupervised approach to learn the dynamic affinities between neurons in live, behaving animals, and to reveal which communities form among neurons at different times.
Zero-shot generalization across architectures for visual classification
Generalization to unseen data is a key desideratum for deep networks, but its relation to classification accuracy is unclear.
Good continuation in 3D: the neurogeometry of stereo vision
Classical good continuation for image curves is based on $2D$ position and orientation.
IAN: Iterated Adaptive Neighborhoods for manifold learning and dimensionality estimation
Invoking the manifold assumption in machine learning requires knowledge of the manifold's geometry and dimension, and theory dictates how many samples are required.
On Qualitative Shape Inferences: a journey from geometry to topology
Shape inference is classically ill-posed, because it involves a map from the (2D) image domain to the (3D) world.
From Boundaries to Bumps: when closed (extremal) contours are critical
Invariants underlying shape inference are elusive: a variety of shapes can give rise to the same image, and a variety of images can be rendered from the same shape.
Feature Selection Facilitates Learning Mixtures of Discrete Product Distributions
Feature selection can facilitate the learning of mixtures of discrete random variables as they arise, e. g. in crowdsourcing tasks.
Critical Contours: An Invariant Linking Image Flow with Salient Surface Organization
We further show that, under this model, the contours partition the surface into meaningful parts using the Morse--Smale complex.
What's In A Patch, II: Visualizing generic surfaces
The parameters for the subspace and rotation matrix encapsulate the ambiguity in the shading problem.
What's In A Patch, I: Tensors, Differential Geometry and Statistical Shading Analysis
We develop a linear algebraic framework for the shape-from-shading problem, because tensors arise when scalar (e. g. image) and vector (e. g. surface normal) fields are differentiated multiple times.
Stagewise Learning for Sparse Clustering of Discretely-Valued Data
The performance of EM in learning mixtures of product distributions often depends on the initialization.
Feedforward Learning of Mixture Models
We develop a biologically-plausible learning rule that provably converges to the class means of general mixture models.
Third-Order Edge Statistics: Contour Continuation, Curvature, and Cortical Connections
Association field models have been used to explain human contour grouping performance and to explain the mean frequency of long-range horizontal connections across cortical columns in V1.
Characterizing Ambiguity in Light Source Invariant Shape from Shading
Shape from shading is a classical inverse problem in computer vision.
