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

March 7, 2022

Singular Value Perturbation and Deep Network Optimization
Rudolf H. Riedi, Randall Balestriero, Richard G. Baraniuk
Neural Network Deep Network Deep Architecture

March 2, 2022

March 1, 2022

February 24, 2022

Standard Deviation-Based Quantization for Deep Neural Networks
Amir Ardakani, Arash Ardakani, Brett Meyer, James J. Clark, Warren J. Gross
Deep Neural Network Deep Network Quantization Operator Quantization Level Future Standard

February 20, 2022

Alternative design of DeepPDNet in the context of image restoration
Mingyuan Jiu, Nelly Pustelnik
Context Information Deep Network Image Restoration Primal Dual Lloyd Algorithm Novel Design Sparsity Regularization

February 17, 2022

Collaborative Self Organizing Map with DeepNNs for Fake Task Prevention in Mobile Crowdsensing
Murat Simsek, Burak Kantarci, Azzedine Boukerche
Deep Network Deep Clustering Self Organizing Map Mobile Crowdsensing Task Clustering

February 16, 2022

On Measuring Excess Capacity in Neural Networks
Florian Graf, Sebastian Zeng, Bastian Rieck, Marc Niethammer, Roland Kwitt
Neural Network Deep Network Capacity Loss Rademacher Complexity

February 14, 2022

Online-updated High-order Collaborative Networks for Single Image Deraining
Cong Wang, Jinshan Pan, Xiao-Ming Wu
Deep Network Deep Learning Based Image Deraining Rainy Image Higher Order Network

February 12, 2022

Classification of Microscopy Images of Breast Tissue: Region Duplication based Self-Supervision vs. Off-the Shelf Deep Representations
Aravind Ravi
Self Supervised Learning Supervised ImageNet Deep Network Self Supervision Microscopy Image Deep Feature Deep Representation Near Duplicate Breast Tissue

February 11, 2022

Audio Defect Detection in Music with Deep Networks
Daniel Wolff, Rémi Mignot, Axel Roebel
Deep Network Music Industry Audio Processing Audio Quality Music Datasets Audio Coding

February 10, 2022

Information Flow in Deep Neural Networks
Ravid Shwartz-Ziv
Neural Network Deep Neural Network Deep Network Information Bottleneck Information Theory Information Flow

February 7, 2022

February 1, 2022

January 28, 2022

Benchmarking Resource Usage for Efficient Distributed Deep Learning
Nathan C. Frey, Baolin Li, Joseph McDonald, Dan Zhao, Michael Jones, David Bestor, Devesh Tiwari, Vijay Gadepally, Siddharth Samsi
Deep Learning Deep Learning Model New Benchmark High Efficiency Deep Network Computational Resource Deep Learning Task

Deep Network

Papers

Singular Value Perturbation and Deep Network Optimization

Improving Generalization of Deep Networks for Estimating Physical Properties of Containers and Fillings

NESTANets: Stable, accurate and efficient neural networks for analysis-sparse inverse problems

Contrasting random and learned features in deep Bayesian linear regression

DeepNet: Scaling Transformers to 1,000 Layers

Standard Deviation-Based Quantization for Deep Neural Networks

Alternative design of DeepPDNet in the context of image restoration

Collaborative Self Organizing Map with DeepNNs for Fake Task Prevention in Mobile Crowdsensing

On Measuring Excess Capacity in Neural Networks

Online-updated High-order Collaborative Networks for Single Image Deraining

Classification of Microscopy Images of Breast Tissue: Region Duplication based Self-Supervision vs. Off-the Shelf Deep Representations

Audio Defect Detection in Music with Deep Networks

Information Flow in Deep Neural Networks

Deep Impulse Responses: Estimating and Parameterizing Filters with Deep Networks

Discrete-Event Controller Synthesis for Autonomous Systems with Deep-Learning Perception Components

Deep Networks on Toroids: Removing Symmetries Reveals the Structure of Flat Regions in the Landscape Geometry

Benchmarking Deep Models for Salient Object Detection

Is the Performance of My Deep Network Too Good to Be True? A Direct Approach to Estimating the Bayes Error in Binary Classification

Fully Online Meta-Learning Without Task Boundaries

Benchmarking Resource Usage for Efficient Distributed Deep Learning