Search Results for author:
Found 26 papers, 7 papers with code
Learning Mixtures of Bernoulli Templates by Two-Round EM with Performance Guarantee
Each template is a binary vector, and a template generates examples by randomly switching its binary components independently with a certain probability.
Feature Selection with Annealing for Computer Vision and Big Data Learning
Many computer vision and medical imaging problems are faced with learning from large-scale datasets, with millions of observations and features.
Face Detection with a 3D Model
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.
RENOIR - A Dataset for Real Low-Light Image Noise Reduction
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
Parameterized Principal Component Analysis
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.
Generating Compact Tree Ensembles via Annealing
Tree ensembles are flexible predictive models that can capture relevant variables and to some extent their interactions in a compact and interpretable manner.
Random Hinge Forest for Differentiable Learning
We propose random hinge forests, a simple, efficient, and novel variant of decision forests.
A Novel Framework for Online Supervised Learning with Feature Selection
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.
Unsupervised Learning of GMM with a Uniform Background Component
Gaussian Mixture Models are one of the most studied and mature models in unsupervised learning.
Enhancing the Regularization Effect of Weight Pruning in Artificial Neural Networks
Removing weights from an ANN is a form of regularization, but existing pruning algorithms do not significantly improve generalization error.
Are screening methods useful in feature selection? An empirical study
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.
Accurate Dictionary Learning with Direct Sparsity Control
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.
The Generalization-Stability Tradeoff In Neural Network Pruning
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.
Finding Deep Local Optima Using Network Pruning
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.
Playing Atari Ball Games with Hierarchical Reinforcement Learning
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.
Network Pruning via Annealing and Direct Sparsity Control
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.
Neural Rule Ensembles: Encoding Sparse Feature Interactions into Neural Networks
Artificial Neural Networks form the basis of very powerful learning methods.
A study of local optima for learning feature interactions using neural networks
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.
The Compact Support Neural Network
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
Online Feature Screening for Data Streams with Concept Drift
Online screening methods are one of the categories of online feature selection methods.
Scalable Learning with Incremental Probabilistic PCA
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)
Scalable Clustering: Large Scale Unsupervised Learning of Gaussian Mixture Models with Outliers
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.
Feature Selection with Annealing for Forecasting Financial Time Series
In the financial field, limited attention has been paid to this problem with ML solutions.
Training a Two Layer ReLU Network Analytically
Neural networks are usually trained with different variants of gradient descent based optimization algorithms such as stochastic gradient descent or the Adam optimizer.
Slow Kill for Big Data Learning
Big-data applications often involve a vast number of observations and features, creating new challenges for variable selection and parameter estimation.
A Study of Shape Modeling Against Noise
Shape modeling is a challenging task with many potential applications in computer vision and medical imaging.
