no code implementations • 2 May 2024 • Luciano Dyballa, Evan Gerritz, Steven W. Zucker
Which layers of a network are likely to generalize best?
1 code implementation • 21 Feb 2024 • Luciano Dyballa, Samuel Lang, Alexandra Haslund-Gourley, Eviatar Yemini, Steven W. Zucker
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.
2 code implementations • 21 Feb 2024 • Evan Gerritz, Luciano Dyballa, Steven W. Zucker
Generalization to unseen data is a key desideratum for deep networks, but its relation to classification accuracy is unclear.
no code implementations • 11 Jan 2023 • Maria Virginia Bolelli, Giovanna Citti, Alessandro Sarti, Steven W. Zucker
Classical good continuation for image curves is based on $2D$ position and orientation.
1 code implementation • 19 Aug 2022 • Luciano Dyballa, Steven W. Zucker
Invoking the manifold assumption in machine learning requires knowledge of the manifold's geometry and dimension, and theory dictates how many samples are required.
no code implementations • 19 Aug 2020 • Steven W. Zucker
Shape inference is classically ill-posed, because it involves a map from the (2D) image domain to the (3D) world.
no code implementations • 16 May 2020 • Benjamin Kunsberg, Steven W. Zucker
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.
no code implementations • 25 Nov 2017 • Vincent Zhao, Steven W. Zucker
Feature selection can facilitate the learning of mixtures of discrete random variables as they arise, e. g. in crowdsourcing tasks.
no code implementations • 20 May 2017 • Benjamin S. Kunsberg, Steven W. Zucker
We further show that, under this model, the contours partition the surface into meaningful parts using the Morse--Smale complex.
no code implementations • 16 May 2017 • Benjamin S. Kunsberg, Daniel Niels Holtmann-Rice, Steven W. Zucker
The parameters for the subspace and rotation matrix encapsulate the ambiguity in the shading problem.
no code implementations • 16 May 2017 • Daniel Niels Holtmann-Rice, Benjamin S. Kunsberg, Steven W. Zucker
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.
no code implementations • 9 Jun 2015 • Vincent Zhao, Steven W. Zucker
The performance of EM in learning mixtures of product distributions often depends on the initialization.
no code implementations • NeurIPS 2014 • Matthew Lawlor, Steven W. Zucker
We develop a biologically-plausible learning rule that provably converges to the class means of general mixture models.
no code implementations • NeurIPS 2013 • Matthew Lawlor, Steven W. Zucker
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.
no code implementations • 23 Jun 2013 • Benjamin Kunsberg, Steven W. Zucker
Shape from shading is a classical inverse problem in computer vision.