no code implementations • International Conference on Image Processing (ICIP) 2022 • Cheng Long, Adrian Barbu
Shape modeling is a challenging task with many potential applications in computer vision and medical imaging.
no code implementations • 2 May 2023 • Yiyuan She, Jianhui Shen, Adrian Barbu
Big-data applications often involve a vast number of observations and features, creating new challenges for variable selection and parameter estimation.
1 code implementation • 6 Apr 2023 • Adrian Barbu
Neural networks are usually trained with different variants of gradient descent based optimization algorithms such as stochastic gradient descent or the Adam optimizer.
no code implementations • 3 Mar 2023 • Hakan Pabuccu, Adrian Barbu
In the financial field, limited attention has been paid to this problem with ML solutions.
no code implementations • 28 Feb 2023 • Yijia Zhou, Kyle A. Gallivan, Adrian Barbu
Experiments on real-world large-scale datasets demonstrate the effectiveness of the algorithm when clustering a large number of clusters, and a $k$-means algorithm initialized by the algorithm outperforms many of the classic clustering methods in both speed and accuracy, while scaling well to large datasets such as ImageNet.
1 code implementation • IEEE International Conference on Big Data 2022 • Boshi Wang, Adrian Barbu
Incremental class learning is the classification problem of learning a model where instances from new object classes are added sequentially, and it is desired that the model be retrained only on the new classes with minimal training on the old classes.
Ranked #1 on Class Incremental Learning on CIFAR-100 - 50 classes + 10 steps of 5 classes (using extra training data)
no code implementations • 7 Apr 2021 • Mingyuan Wang, Adrian Barbu
Online screening methods are one of the categories of online feature selection methods.
no code implementations • 1 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.
Ranked #4 on Out-of-Distribution Detection on CIFAR-100 vs SVHN
no code implementations • 11 Feb 2020 • Gitesh Dawer, Yangzi Guo, Sida Liu, Adrian Barbu
Artificial Neural Networks form the basis of very powerful learning methods.
no code implementations • 11 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.
no code implementations • 11 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.
no code implementations • 27 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.
no code implementations • 25 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.
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.
1 code implementation • ICIP 2018 • Hongyu Mou, Adrian Barbu
Dictionary learning is a popular method for obtaining sparse linear representations for high dimensional data, with many applications in image classification, signal processing and machine learning.
no code implementations • 14 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.
no code implementations • 4 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.
1 code implementation • 8 Apr 2018 • Sida Liu, Adrian Barbu
Gaussian Mixture Models are one of the most studied and mature models in unsupervised learning.
no code implementations • 30 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.
1 code implementation • 12 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.
no code implementations • 16 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.
no code implementations • 16 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.
1 code implementation • 29 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.
Ranked #1 on Color Image Denoising on RENOIR
no code implementations • 14 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.
1 code implementation • IEEE Transactions on Pattern Analysis and Machine Intelligence 2017 • Adrian Barbu, Yiyuan She, Liangjing Ding, Gary Gramajo
Many computer vision and medical imaging problems are faced with learning from large-scale datasets, with millions of observations and features.
no code implementations • 2 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.