Joseph Paul Cohen holds a Ph.D Degree in Computer Science and Machine Learning from the University of Massachusetts Boston. His research interests include machine learning, computer vision, ad-hoc networking, and cyber security. Joseph received a U.S. National Science Foundation Graduate Fellowship in 2013 as well as COSPAR’s Outstanding Paper Award for Young Scientists in the same year. Joseph is the creator of blucat; the cross-platform Bluetooth debugging tool. He is the founder of the Institute for Reproducible Research which produces Academic Torrents; a system designed to move large datasets and become the library of the future. He is also the creator of BlindTool; a mobile application providing a sense of vision to the blind by using an artificial neural network that speaks names of objects as they are identified. He has worked in industry for small startups, large corporations, government research labs, educational museums, as well as been involved in projects sponsored by NASA and the DOE.

A Regularized Framework for Sparse and Structured Neural Attention.

Neural Information Processing Systems Conference - 2017 via Local dblp

Keywords:

Neural Information Processing Systems Conference - 2017 via Local dblp

Keywords:

Understanding deep learning requires rethinking generalization

arXiv e-Print archive - 2016 via Local arXiv

Keywords: cs.LG

more

arXiv e-Print archive - 2016 via Local arXiv

Keywords: cs.LG

Rotation equivariant vector field networks

arXiv e-Print archive - 2016 via Local arXiv

Keywords: cs.CV

more

arXiv e-Print archive - 2016 via Local arXiv

Keywords: cs.CV

Introspective Generative Modeling: Decide Discriminatively

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.CV, cs.LG, cs.NE

more

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.CV, cs.LG, cs.NE

Gene expression inference with deep learning

Bioinformatics - 2016 via Local Bibsonomy

Keywords: dblp

Bioinformatics - 2016 via Local Bibsonomy

Keywords: dblp

Convolutional Networks on Graphs for Learning Molecular Fingerprints

arXiv e-Print archive - 2015 via Local arXiv

Keywords: cs.LG, cs.NE, stat.ML

more

arXiv e-Print archive - 2015 via Local arXiv

Keywords: cs.LG, cs.NE, stat.ML

Network-regularized Sparse Logistic Regression Models for Clinical Risk Prediction and Biomarker Discovery

arXiv e-Print archive - 2016 via Local arXiv

Keywords: q-bio.GN, cs.LG, stat.ML, J.3; H.2.8; G.1.6; I.5

more

arXiv e-Print archive - 2016 via Local arXiv

Keywords: q-bio.GN, cs.LG, stat.ML, J.3; H.2.8; G.1.6; I.5

Efficient Deformable Motion Correction for 3-D Abdominal MRI Using Manifold Regression

Medical Image Computing and Computer Assisted Interventions Conference - 2017 via Local Bibsonomy

Keywords: dblp

Medical Image Computing and Computer Assisted Interventions Conference - 2017 via Local Bibsonomy

Keywords: dblp

Deep Adversarial Networks for Biomedical Image Segmentation Utilizing Unannotated Images

Medical Image Computing and Computer Assisted Interventions Conference - 2017 via Local Bibsonomy

Keywords: dblp

Medical Image Computing and Computer Assisted Interventions Conference - 2017 via Local Bibsonomy

Keywords: dblp

Supervised Intra-embedding of Fisher Vectors for Histopathology Image Classification

Medical Image Computing and Computer Assisted Interventions Conference - 2017 via Local Bibsonomy

Keywords: dblp

Medical Image Computing and Computer Assisted Interventions Conference - 2017 via Local Bibsonomy

Keywords: dblp

Training CNNs for Image Registration from Few Samples with Model-based Data Augmentation

Medical Image Computing and Computer Assisted Interventions Conference - 2017 via Local Bibsonomy

Keywords: dblp

Medical Image Computing and Computer Assisted Interventions Conference - 2017 via Local Bibsonomy

Keywords: dblp

Image-to-Image Translation with Conditional Adversarial Networks

arXiv e-Print archive - 2016 via Local arXiv

Keywords: cs.CV

more

arXiv e-Print archive - 2016 via Local arXiv

Keywords: cs.CV

Learning Hierarchical Features from Generative Models

arXiv e-Print archive - 2017 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2017 via Local Bibsonomy

Keywords: dblp

On orthogonality and learning recurrent networks with long term dependencies

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.LG, cs.NE

more

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.LG, cs.NE

Unimodal Probability Distributions for Deep Ordinal Classification

International Conference on Machine Learning - 2017 via Local Bibsonomy

Keywords: dblp

International Conference on Machine Learning - 2017 via Local Bibsonomy

Keywords: dblp

Self-Normalizing Neural Networks

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.LG, stat.ML

more

arXiv e-Print archive - 2017 via Local arXiv

Keywords: cs.LG, stat.ML

Neural Machine Translation by Jointly Learning to Align and Translate

arXiv e-Print archive - 2014 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2014 via Local Bibsonomy

Keywords: dblp

Learning To Count Objects in Images

Neural Information Processing Systems Conference - 2010 via Local Bibsonomy

Keywords: dblp

Neural Information Processing Systems Conference - 2010 via Local Bibsonomy

Keywords: dblp

Unsupervised Domain Adaptation by Backpropagation

arXiv e-Print archive - 2014 via Local arXiv

Keywords: stat.ML, cs.LG, cs.NE

more

arXiv e-Print archive - 2014 via Local arXiv

Keywords: stat.ML, cs.LG, cs.NE

End-to-End Instance Segmentation and Counting with Recurrent Attention

arXiv e-Print archive - 2016 via Local arXiv

Keywords: cs.LG, cs.CV

more

arXiv e-Print archive - 2016 via Local arXiv

Keywords: cs.LG, cs.CV

Hypercolumns for Object Segmentation and Fine-grained Localization

arXiv e-Print archive - 2014 via Local arXiv

Keywords: cs.CV

more

arXiv e-Print archive - 2014 via Local arXiv

Keywords: cs.CV

Learning to count with deep object features

Conference and Computer Vision and Pattern Recognition - 2015 via Local Bibsonomy

Keywords: dblp

Conference and Computer Vision and Pattern Recognition - 2015 via Local Bibsonomy

Keywords: dblp

Efficient Activity Retrieval through Semantic Graph Queries

Special Interest Group in Multimedia (ACM SIGMM) - 2015 via Local Bibsonomy

Keywords: dblp

Special Interest Group in Multimedia (ACM SIGMM) - 2015 via Local Bibsonomy

Keywords: dblp

Reinforcement Learning for Visual Object Detection

Conference and Computer Vision and Pattern Recognition - 2016 via Local

Keywords:

Conference and Computer Vision and Pattern Recognition - 2016 via Local

Keywords:

Scale-Aware Alignment of Hierarchical Image Segmentation

Conference and Computer Vision and Pattern Recognition - 2016 via Local

Keywords: computer, machine, learning, vision

Conference and Computer Vision and Pattern Recognition - 2016 via Local

Keywords: computer, machine, learning, vision

Algorithms for Non-negative Matrix Factorization

Neural Information Processing Systems Conference - 2000 via Local Bibsonomy

Keywords: dblp

Neural Information Processing Systems Conference - 2000 via Local Bibsonomy

Keywords: dblp

Understanding the difficulty of training deep feedforward neural networks

Journal of Machine Learning Research - 2010 via Local Bibsonomy

Keywords: dblp

Journal of Machine Learning Research - 2010 via Local Bibsonomy

Keywords: dblp

A Nonlinear Mapping for Data Structure Analysis

IEEE Computer Society IEEE Trans. Comput. - 1969 via Local Bibsonomy

Keywords: visualization, dimensionality_reduction

IEEE Computer Society IEEE Trans. Comput. - 1969 via Local Bibsonomy

Keywords: visualization, dimensionality_reduction

Multilayer feedforward networks are universal approximators

Neural Networks - 1989 via Local Bibsonomy

Keywords: dblp

Neural Networks - 1989 via Local Bibsonomy

Keywords: dblp

Wrappers for Feature Subset Selection

Artificial Intelligence Journal - 1997 via Local Bibsonomy

Keywords: dblp

Artificial Intelligence Journal - 1997 via Local Bibsonomy

Keywords: dblp

An Introduction to Variable and Feature Selection

Journal of Machine Learning Research - 2003 via Local Bibsonomy

Keywords: dblp

Journal of Machine Learning Research - 2003 via Local Bibsonomy

Keywords: dblp

Overfitting in Making Comparisons Between Variable Selection Methods

Journal of Machine Learning Research - 2003 via Local Bibsonomy

Keywords: dblp

Journal of Machine Learning Research - 2003 via Local Bibsonomy

Keywords: dblp

Large Margin Classification Using the Perceptron Algorithm

Kluwer Academic Publishers Machine Learning - 1999 via Local Bibsonomy

Keywords: original, perceptron, kernel, shapire, averaged, voted

Kluwer Academic Publishers Machine Learning - 1999 via Local Bibsonomy

Keywords: original, perceptron, kernel, shapire, averaged, voted

Perceptrons - an introduction to computational geometry

MIT Press - 1987 via Local Bibsonomy

Keywords: dblp

MIT Press - 1987 via Local Bibsonomy

Keywords: dblp

Multi-scale Convolutional Neural Networks for Lung Nodule Classification

Information Processing in Medical Imaging - 2015 via Local Bibsonomy

Keywords: dblp

Information Processing in Medical Imaging - 2015 via Local Bibsonomy

Keywords: dblp

Academic Torrents: A Community-Maintained Distributed Repository

The Extreme Science and Engineering Discovery Environment Conference - 2014 via Local Bibsonomy

Keywords: dblp

The Extreme Science and Engineering Discovery Environment Conference - 2014 via Local Bibsonomy

Keywords: dblp

Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation

Conference and Computer Vision and Pattern Recognition - 2014 via Local Bibsonomy

Keywords: dblp

Conference and Computer Vision and Pattern Recognition - 2014 via Local Bibsonomy

Keywords: dblp

Identifying Syntactic differences Between Two Programs

Software: Practice and Experience Journal - 1991 via Local Bibsonomy

Keywords: dblp

Software: Practice and Experience Journal - 1991 via Local Bibsonomy

Keywords: dblp

Comparing semantically-blind and semantically-aware landscape similarity measures with application to query-by-content and regionalization

Ecological Informatics Journal - 2014 via Local Bibsonomy

Keywords: dblp

Ecological Informatics Journal - 2014 via Local Bibsonomy

Keywords: dblp

Deep Residual Learning for Image Recognition

arXiv e-Print archive - 2015 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2015 via Local Bibsonomy

Keywords: dblp

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

International Conference on Machine Learning - 2015 via Local Bibsonomy

Keywords: dblp

International Conference on Machine Learning - 2015 via Local Bibsonomy

Keywords: dblp

Adam: A Method for Stochastic Optimization

arXiv e-Print archive - 2014 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2014 via Local Bibsonomy

Keywords: dblp

Wireless Message Dissemination via Selective Relay over Bluetooth (MDSRoB)

arXiv e-Print archive - 2013 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2013 via Local Bibsonomy

Keywords: dblp

Adaptive Subgradient Methods for Online Learning and Stochastic Optimization

Conference on Learning Theory - 2010 via Local Bibsonomy

Keywords: dblp

Conference on Learning Theory - 2010 via Local Bibsonomy

Keywords: dblp

Semi-Supervised Web Wrapper Repair via Recursive Tree Matching

arXiv e-Print archive - 2015 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2015 via Local Bibsonomy

Keywords: dblp

Prediction gradients for feature extraction and analysis from convolutional neural networks

Conference on Automatic Face and Gesture Recognition - 2015 via Local Bibsonomy

Keywords: dblp

Conference on Automatic Face and Gesture Recognition - 2015 via Local Bibsonomy

Keywords: dblp

RandomOut: Using a convolutional gradient norm to win The Filter Lottery

arXiv e-Print archive - 2016 via Local Bibsonomy

Keywords: dblp

arXiv e-Print archive - 2016 via Local Bibsonomy

Keywords: dblp

About