Deep Learning Architecture

Deep learning architectures are complex computational models designed to learn intricate patterns from data, primarily aiming to improve the accuracy and efficiency of machine learning tasks. Current research focuses on optimizing existing architectures like convolutional neural networks (CNNs), recurrent neural networks (RNNs), transformers, and autoencoders, as well as developing novel activation functions and exploring efficient search algorithms for optimal network structures. These advancements are significantly impacting various fields, from medical image analysis and anomaly detection in complex systems to natural language processing and 3D data processing, driving improvements in accuracy, efficiency, and interpretability.

Papers

February 16, 2023

GLUECons: A Generic Benchmark for Learning Under Constraints
Hossein Rajaby Faghihi, Aliakbar Nafar, Chen Zheng, Roshanak Mirzaee, Yue Zhang, Andrzej Uszok, Alexander Wan, Tanawan Premsri, Dan Roth, Parisa Kordjamshidi
LeArning Abstract Natural Language Processing Domain Knowledge Deep Learning Architecture Participation Constraint Knowledge Integration Phonetically Noised Glue

February 13, 2023

Reliability Assurance for Deep Neural Network Architectures Against Numerical Defects
Linyi Li, Yuhao Zhang, Luyao Ren, Yingfei Xiong, Tao Xie
Deep Neural Network Deep Learning Architecture DNN Model Task Feasibility System Reliability

February 5, 2023

KDEformer: Accelerating Transformers via Kernel Density Estimation
Amir Zandieh, Insu Han, Majid Daliri, Amin Karbasi
Transformer Megatron Decepticons Deep Learning Architecture Sequence Model Kernel Density Dot Product Attention Matrix Vector Product Approximate Attention

January 27, 2023

PrecTime: A Deep Learning Architecture for Precise Time Series Segmentation in Industrial Manufacturing Operations
Stefan Gaugel, Manfred Reichert
Deep Learning Architecture Neural Network Baseline Object State Industrial Process Temporal Neural Network Time Series Segmentation

January 25, 2023

January 17, 2023

Negative Flux Aggregation to Estimate Feature Attributions
Xin Li, Deng Pan, Chengyin Li, Yao Qiang, Dongxiao Zhu
Deep Neural Network Deep Learning Architecture Feature Attribution Attribution Map Aggregated Gradient Gradient Aggregation DNN Prediction

January 16, 2023

Multimodal Side-Tuning for Document Classification
Stefano Pio Zingaro, Giuseppe Lisanti, Maurizio Gabbrielli
Deep Learning Architecture Adaptive Network Document Classification Side Tuning

December 8, 2022

Analysis of Deep Learning Architectures and Efficacy of Detecting Forest Fires
Ryan Marinelli
Data Set Computer Vision General Analysis Deep Learning Architecture Computer Vision Datasets Forest Fire

December 5, 2022

Deep Learning Architectures for FSCV, a Comparison
Thomas Twomey, Leonardo Barbosa, Terry Lohrenz, P. Read Montague
Deep Neural Network Consistent Comparison Deep Learning Architecture Electrode Array

December 2, 2022

A Deep Learning Architecture for Passive Microwave Precipitation Retrievals using CloudSat and GPM Data
Reyhaneh Rahimi, Sajad Vahedizadeh, Ardeshir Ebtehaj
Deep Learning Architecture Precipitation Datasets Passive Microwave Radar Based Precipitation

November 27, 2022

November 21, 2022

November 15, 2022

Photometric identification of compact galaxies, stars and quasars using multiple neural networks
Siddharth Chaini, Atharva Bagul, Anish Deshpande, Rishi Gondkar, Kaushal Sharma, M. Vivek, Ajit Kembhavi
Deep Learning Architecture Deep Learning Based Physiological Biometrics Star Model Multiple Deep Neural Network Dense Object Quasar Host Galaxy

October 28, 2022

Design of Convolutional Extreme Learning Machines for Vision-Based Navigation Around Small Bodies
Mattia Pugliatti, Francesco Topputo
Convolutional Neural Network Computer Vision Product Design Deep Learning Architecture Computer Vision Task Extreme Learning Machine Vision Based Navigation Small Body

October 21, 2022

Real-time Detection of 2D Tool Landmarks with Synthetic Training Data
Bram Vanherle, Jeroen Put, Nick Michiels, Frank Van Reeth
Deep Learning Architecture Synthetic Training Data Real Time Detection Tool Shape Unseen Tool

October 20, 2022

Inference from Real-World Sparse Measurements
Arnaud Pannatier, Kyle Matoba, François Fleuret
Graph Neural Network Scientific Inference Deep Learning Architecture Attention Based Model Day Ahead Sparse Measurement Convection Nowcasting

October 5, 2022

Advanced Deep Learning Architectures for Accurate Detection of Subsurface Tile Drainage Pipes from Remote Sensing Images
Tom-Lukas Breitkopf, Leonard W. Hackel, Mahdyar Ravanbakhsh, Anne-Karin Cooke, Sandra Willkommen, Stefan Broda, Begüm Demir
Remote Sensing Image Deep Learning Architecture Accurate Detection Land Use Subsurface Flow

Deep Learning Architecture

Papers

GLUECons: A Generic Benchmark for Learning Under Constraints

Reliability Assurance for Deep Neural Network Architectures Against Numerical Defects

KDEformer: Accelerating Transformers via Kernel Density Estimation

PrecTime: A Deep Learning Architecture for Precise Time Series Segmentation in Industrial Manufacturing Operations

Connecting metrics for shape-texture knowledge in computer vision

SGCN: Exploiting Compressed-Sparse Features in Deep Graph Convolutional Network Accelerators

Negative Flux Aggregation to Estimate Feature Attributions

Multimodal Side-Tuning for Document Classification

Analysis of Deep Learning Architectures and Efficacy of Detecting Forest Fires

Deep Learning Architectures for FSCV, a Comparison

A Deep Learning Architecture for Passive Microwave Precipitation Retrievals using CloudSat and GPM Data

Neural Font Rendering

A Self-adaptive Neuroevolution Approach to Constructing Deep Neural Network Architectures Across Different Types

Learning on tree architectures outperforms a convolutional feedforward network

Enhancing Accuracy and Robustness of Steering Angle Prediction with Attention Mechanism

Photometric identification of compact galaxies, stars and quasars using multiple neural networks

Design of Convolutional Extreme Learning Machines for Vision-Based Navigation Around Small Bodies

Real-time Detection of 2D Tool Landmarks with Synthetic Training Data

Inference from Real-World Sparse Measurements

Advanced Deep Learning Architectures for Accurate Detection of Subsurface Tile Drainage Pipes from Remote Sensing Images