Search Results for author: Matthew Cook

Found 17 papers, 4 papers with code

Learning with SASQuaTCh: a Novel Variational Quantum Transformer Architecture with Kernel-Based Self-Attention

no code implementations21 Mar 2024 Ethan N. Evans, Matthew Cook, Zachary P. Bradshaw, Margarite L. LaBorde

The widely popular transformer network popularized by the generative pre-trained transformer (GPT) has a large field of applicability, including predicting text and images, classification, and even predicting solutions to the dynamics of physical systems.

Operator learning

Omitted Labels in Causality: A Study of Paradoxes

no code implementations12 Nov 2023 Bijan Mazaheri, Siddharth Jain, Matthew Cook, Jehoshua Bruck

We explore what we call ``omitted label contexts,'' in which training data is limited to a subset of the possible labels.

Causal Inference

kNN-Res: Residual Neural Network with kNN-Graph coherence for point cloud registration

1 code implementation31 Mar 2023 Muhammad S. Battikh, Dillon Hammill, Matthew Cook, Artem Lensky

In this paper, we present a residual neural network-based method for point set registration that preserves the topological structure of the target point set.

Point Cloud Registration

k-Means Maximum Entropy Exploration

no code implementations31 May 2022 Alexander Nedergaard, Matthew Cook

We introduce an artificial curiosity algorithm based on lower bounding an approximation to the entropy of the state visitation distribution.

Density Estimation reinforcement-learning +1

Microtubule Tracking in Electron Microscopy Volumes

1 code implementation17 Sep 2020 Nils Eckstein, Julia Buhmann, Matthew Cook, Jan Funke

We present a method for microtubule tracking in electron microscopy volumes.

Outlier Detection through Null Space Analysis of Neural Networks

no code implementations2 Jul 2020 Matthew Cook, Alina Zare, Paul Gader

Specifically, many systems lack the ability to identify when outliers (e. g., samples that are distinct from and not represented in the training data distribution) are being presented to the system.

Classification General Classification +1

Efficient 2D neuron boundary segmentation with local topological constraints

no code implementations3 Feb 2020 Thanuja D. Ambegoda, Matthew Cook

Drawing inspiration from these human strategies, we formulate the segmentation task as an edge labeling problem on a graph with local topological constraints.

Image Segmentation Segmentation +1

Estimation of Z-Thickness and XY-Anisotropy of Electron Microscopy Images using Gaussian Processes

1 code implementation1 Feb 2020 Thanuja D. Ambegoda, Julien N. P. Martel, Jozef Adamcik, Matthew Cook, Richard H. R. Hahnloser

Serial section electron microscopy (ssEM) is a widely used technique for obtaining volumetric information of biological tissues at nanometer scale.

Gaussian Processes

Synaptic partner prediction from point annotations in insect brains

no code implementations21 Jun 2018 Julia Buhmann, Renate Krause, Rodrigo Ceballos Lentini, Nils Eckstein, Matthew Cook, Srinivas Turaga, Jan Funke

High-throughput electron microscopy allows recording of lar- ge stacks of neural tissue with sufficient resolution to extract the wiring diagram of the underlying neural network.

Deep Learning in the Automotive Industry: Applications and Tools

no code implementations30 Apr 2017 Andre Luckow, Matthew Cook, Nathan Ashcraft, Edwin Weill, Emil Djerekarov, Bennie Vorster

In this paper, we describe different automotive uses cases for deep learning in particular in the domain of computer vision.

Image Classification speech-recognition +1

A wake-sleep algorithm for recurrent, spiking neural networks

no code implementations18 Mar 2017 Johannes Thiele, Peter Diehl, Matthew Cook

We investigate a recently proposed model for cortical computation which performs relational inference.

Clustering

Learning and Inferring Relations in Cortical Networks

no code implementations29 Aug 2016 Peter U. Diehl, Matthew Cook

We are at a loss to explain, simulate, or understand such a multi-functional homogeneous sheet-like computational structure - we do not have computational models which work in this way.

Anatomy

Buried object detection using handheld WEMI with task-driven extended functions of multiple instances

no code implementations19 Mar 2016 Matthew Cook, Alina Zare, Dominic Ho

The new algorithm, Task Driven Extended Functions of Multiple Instances, can overcome data that does not have very precise point-wise labels and still learn a highly discriminative dictionary.

Dictionary Learning object-detection +1

Adaptive coherence estimator (ACE) for explosive hazard detection using wideband electromagnetic induction (WEMI)

no code implementations19 Mar 2016 Brendan Alvey, Alina Zare, Matthew Cook, Dominic K. Ho

The adaptive coherence estimator (ACE) estimates the squared cosine of the angle between a known target vector and a sample vector in a whitened coordinate space.

TED: A Tolerant Edit Distance for Segmentation Evaluation

1 code implementation8 Mar 2015 Jan Funke, Francesc Moreno-Noguer, Albert Cardona, Matthew Cook

This measure, which we call Tolerant Edit Distance (TED), is motivated by two observations: (1) Some errors, like small boundary shifts, are tolerable in practice.

Cannot find the paper you are looking for? You can Submit a new open access paper.