Deep Network

Deep networks, complex artificial neural networks with multiple layers, aim to learn intricate patterns from data by approximating complex functions. Current research focuses on improving their efficiency (e.g., through dataset distillation and novel activation functions), enhancing their interpretability (e.g., via re-label distillation and analysis of input space mode connectivity), and addressing challenges like noisy labels and domain shifts. These advancements are crucial for expanding the applicability of deep networks across diverse fields, from financial modeling and medical image analysis to time series classification and natural language processing, while simultaneously increasing their reliability and trustworthiness.

Papers

May 17, 2022

Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks using an Incompetent Teacher
Vikram S Chundawat, Ayush K Tarun, Murari Mandal, Mohan Kankanhalli
Machine Learning Deep Network Anti Forgetting Machine Unlearning Unlearning Framework Unlearned Model Mean Teacher

May 14, 2022

Evaluating the Generalization Ability of Super-Resolution Networks
Yihao Liu, Hengyuan Zhao, Jinjin Gu, Yu Qiao, Chao Dong
Super Resolution Deep Network Super Resolution Network Generalization Measure

May 9, 2022

An Effective Scheme for Maize Disease Recognition based on Deep Networks
Saeedeh Osouli, Behrouz Bolourian Haghighi, Ehsan Sadrossadat
Deep Neural Network Transfer Learning Deep Network Convolution Layer Plant Disease Calysto Scheme Maize Plant

May 3, 2022

Deep Multi-Scale U-Net Architecture and Label-Noise Robust Training Strategies for Histopathological Image Segmentation
Nikhil Cherian Kurian, Amit Lohan, Gregory Verghese, Nimish Dharamshi, Swati Meena, Mengyuan Li, Fangfang Liu, Cheryl Gillet, Swapnil Rane, Anita Grigoriadis, Amit Sethi
Deep Network Image Segmentation U Net nnU Net Convolutional Module Scale U Net

April 29, 2022

Wide and Deep Neural Networks Achieve Optimality for Classification
Adityanarayanan Radhakrishnan, Mikhail Belkin, Caroline Uhler
Neural Network Deep Neural Network Classification Code Deep Network Activation Function Near Optimality Wide Neural Network Effective Neural

April 23, 2022

Unsupervised Restoration of Weather-affected Images using Deep Gaussian Process-based CycleGAN
Rajeev Yasarla, Vishwanath A. Sindagi, Vishal M. Patel
Deep Network CycleGAN Model High Quality Reconstruction Fully Supervised Deep Gaussian Process Weather Image Gaussian Neural Network Unsupervised Restoration

April 14, 2022

LEFM-Nets: Learnable Explicit Feature Map Deep Networks for Segmentation of Histopathological Images of Frozen Sections
Dario Sitnik, Ivica Kopriva
High Dimensional Segmentation Based Approach Deep Network Histopathological Image Explicit Feature Map

April 12, 2022

Examining the Proximity of Adversarial Examples to Class Manifolds in Deep Networks
Štefan Pócoš, Iveta Bečková, Igor Farkaš
Deep Neural Network Adversarial Example Deep Network Internal Representation Adversarial Text Class Manifold Hidden Layer Proximity Search

April 9, 2022

Are Two Heads the Same as One? Identifying Disparate Treatment in Fair Neural Networks
Michael Lohaus, Matthäus Kleindessner, Krishnaram Kenthapadi, Francesco Locatello, Chris Russell
Neural Network Deep Network Human Head Multi Head FAir Classifier FAIRness Approach Equal Treatment

April 7, 2022

March 29, 2022

Physics-/Model-Based and Data-Driven Methods for Low-Dose Computed Tomography: A survey
Wenjun Xia, Hongming Shan, Ge Wang, Yi Zhang
Deep Learning Timely Survey Data Driven Deep Network Computed Tomography Low Dose Tomographic Infrastructure

March 21, 2022

Origami in N dimensions: How feed-forward networks manufacture linear separability
Christian Keup, Moritz Helias
Neural Network Deep Network Deep Architecture Linear Separability Activation Space Rigid Origami Separable Representation

March 19, 2022

Deep Learning Generalization, Extrapolation, and Over-parameterization
Roozbeh Yousefzadeh
Neural Network Strong Generalization Deep Network Adversarial Vulnerability Extrapolation Framework Neural Network Generalization Benign Over Parameterization Imperceptible Adversarial Perturbation

March 14, 2022

March 10, 2022

projUNN: efficient method for training deep networks with unitary matrices
Bobak Kiani, Randall Balestriero, Yann LeCun, Seth Lloyd
Deep Network Efficient Method Unitary Gradient Neural Network Orthogonal Recurrent Neural Network

Deep Network

Papers

Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks using an Incompetent Teacher

Evaluating the Generalization Ability of Super-Resolution Networks

An Effective Scheme for Maize Disease Recognition based on Deep Networks

Deep Multi-Scale U-Net Architecture and Label-Noise Robust Training Strategies for Histopathological Image Segmentation

Wide and Deep Neural Networks Achieve Optimality for Classification

Unsupervised Restoration of Weather-affected Images using Deep Gaussian Process-based CycleGAN

LEFM-Nets: Learnable Explicit Feature Map Deep Networks for Segmentation of Histopathological Images of Frozen Sections

Examining the Proximity of Adversarial Examples to Class Manifolds in Deep Networks

Are Two Heads the Same as One? Identifying Disparate Treatment in Fair Neural Networks

Multi-objective optimization determines when, which and how to fuse deep networks: an application to predict COVID-19 outcomes

Total Variation Optimization Layers for Computer Vision

Physics-/Model-Based and Data-Driven Methods for Low-Dose Computed Tomography: A survey

Origami in N dimensions: How feed-forward networks manufacture linear separability

Deep Learning Generalization, Extrapolation, and Over-parameterization

Attacking deep networks with surrogate-based adversarial black-box methods is easy

Deep vanishing point detection: Geometric priors make dataset variations vanish

Learning to Generate Synthetic Training Data using Gradient Matching and Implicit Differentiation

Extracting associations and meanings of objects depicted in artworks through bi-modal deep networks

DKMA-ULD: Domain Knowledge augmented Multi-head Attention based Robust Universal Lesion Detection

projUNN: efficient method for training deep networks with unitary matrices