Search Results for author: Adrian Barbu

Found 19 papers, 4 papers with code

Online Feature Screening for Data Streams with Concept Drift

no code implementations7 Apr 2021 Mingyuan Wang, Adrian Barbu

Online screening methods are one of the categories of online feature selection methods.

Feature Importance

The Compact Support Neural Network

no code implementations1 Apr 2021 Adrian Barbu, Hongyu Mou

This paper introduces a novel neuron generalization that has the standard dot-product-based neuron and the {\color{black} radial basis function (RBF)} neuron as two extreme cases of a shape parameter.

Autonomous Driving OOD Detection +1

A study of local optima for learning feature interactions using neural networks

no code implementations11 Feb 2020 Yangzi Guo, Adrian Barbu

To deal with the local minima and for feature selection we propose a node pruning and feature selection algorithm that improves the capability of NNs to find better local minima even when there are irrelevant variables.

Network Pruning via Annealing and Direct Sparsity Control

no code implementations11 Feb 2020 Yangzi Guo, Yiyuan She, Adrian Barbu

The attractive fact that the network size keeps dropping throughout the iterations makes it suitable for the pruning of any untrained or pre-trained network.

Network Pruning

Playing Atari Ball Games with Hierarchical Reinforcement Learning

no code implementations27 Sep 2019 Hua Huang, Adrian Barbu

We argue that these instructions have tremendous value in designing a reinforcement learning system which can learn in human fashion, and we test the idea by playing the Atari games Tennis and Pong.

Atari Games Hierarchical Reinforcement Learning +1

Finding Deep Local Optima Using Network Pruning

no code implementations25 Sep 2019 Yangzi Guo, Yiyuan She, Ying Nian Wu, Adrian Barbu

However, in non-vision sparse datasets, especially with many irrelevant features where a standard neural network would overfit, this might not be the case and there might be many non-equivalent local optima.

Network Pruning

The Generalization-Stability Tradeoff In Neural Network Pruning

no code implementations NeurIPS 2020 Brian R. Bartoldson, Ari S. Morcos, Adrian Barbu, Gordon Erlebacher

Pruning neural network parameters is often viewed as a means to compress models, but pruning has also been motivated by the desire to prevent overfitting.

Network Pruning

Are screening methods useful in feature selection? An empirical study

no code implementations14 Sep 2018 Mingyuan Wang, Adrian Barbu

Such an evaluation is needed to compare them with each other and also to answer whether they are at all useful, or a learning algorithm could do a better job without them.

Classification General Classification

Enhancing the Regularization Effect of Weight Pruning in Artificial Neural Networks

no code implementations4 May 2018 Brian Bartoldson, Adrian Barbu, Gordon Erlebacher

Removing weights from an ANN is a form of regularization, but existing pruning algorithms do not significantly improve generalization error.

General Classification Image Classification

Unsupervised Learning of GMM with a Uniform Background Component

1 code implementation8 Apr 2018 Sida Liu, Adrian Barbu

Gaussian Mixture Models are one of the most studied and mature models in unsupervised learning.

A Novel Framework for Online Supervised Learning with Feature Selection

no code implementations30 Mar 2018 Lizhe Sun, Mingyuan Wang, Adrian Barbu

Current online learning methods suffer issues such as lower convergence rates and limited capability to recover the support of the true features compared to their offline counterparts.

online learning

Random Hinge Forest for Differentiable Learning

1 code implementation12 Feb 2018 Nathan Lay, Adam P. Harrison, Sharon Schreiber, Gitesh Dawer, Adrian Barbu

We propose random hinge forests, a simple, efficient, and novel variant of decision forests.

Generating Compact Tree Ensembles via Annealing

no code implementations16 Sep 2017 Gitesh Dawer, Yangzi Guo, Adrian Barbu

Tree ensembles are flexible predictive models that can capture relevant variables and to some extent their interactions in a compact and interpretable manner.

Parameterized Principal Component Analysis

no code implementations16 Aug 2016 Ajay Gupta, Adrian Barbu

We introduce a novel manifold approximation method, parameterized principal component analysis (PPCA) that models data with linear subspaces that change continuously according to the extra parameter of contextual information (e. g. age), instead of ad-hoc atlases.

RENOIR - A Dataset for Real Low-Light Image Noise Reduction

1 code implementation29 Sep 2014 Josue Anaya, Adrian Barbu

Image denoising algorithms are evaluated using images corrupted by artificial noise, which may lead to incorrect conclusions about their performances on real noise.

Color Image Denoising Image Denoising +1

Face Detection with a 3D Model

no code implementations14 Apr 2014 Adrian Barbu, Nathan Lay, Gary Gramajo

This paper presents a part-based face detection approach where the spatial relationship between the face parts is represented by a hidden 3D model with six parameters.

Face Detection

Learning Mixtures of Bernoulli Templates by Two-Round EM with Performance Guarantee

no code implementations2 May 2013 Adrian Barbu, Tianfu Wu, Ying Nian Wu

Each template is a binary vector, and a template generates examples by randomly switching its binary components independently with a certain probability.

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