Architecture Design

Architecture design, encompassing both physical structures and software systems, is undergoing a transformation driven by advancements in artificial intelligence. Current research focuses on developing novel architectures for various applications, including efficient neural networks for tasks like speech emotion recognition and video question answering, as well as generative AI models for architectural design and autonomous systems. These efforts aim to improve efficiency, robustness, and adaptability across diverse domains, impacting fields from robotics and urban planning to computer vision and software engineering.

Papers

May 4, 2022

Optimizing Mixture of Experts using Dynamic Recompilations
Ferdinand Kossmann, Zhihao Jia, Alex Aiken
Neural Network Mixture Component Expert Knowledge DNN Framework Architecture Design Expert Model

April 4, 2022

Spatio-Temporal Analysis of Transformer based Architecture for Attention Estimation from EEG
Victor Delvigne, Hazem Wannous, Jean-Philippe Vandeborre, Laurence Ris, Thierry Dutoit
Transformer Based Architecture Design Brain Electroencephalography Attention Operation Electroencephalography Recording Electroencephalography Signal Attention Level

March 24, 2022

FAMLP: A Frequency-Aware MLP-Like Architecture For Domain Generalization
Kecheng Zheng, Yang Cao, Kai Zhu, Ruijing Zhao, Zheng-Jun Zha
Domain Generalization Architecture Design Frequency Learning MLP Like Model Fourier Layer MLP Like

March 19, 2022

Radiology Text Analysis System (RadText): Architecture and Evaluation
Song Wang, Mingquan Lin, Ying Ding, George Shih, Zhiyong Lu, Yifan Peng
Global Evaluation Architecture Design Radiology Report

March 10, 2022

TextConvoNet:A Convolutional Neural Network based Architecture for Text Classification
Sanskar Soni, Satyendra Singh Chouhan, Santosh Singh Rathore
Convolutional Neural Network Natural Language Processing Text Classification Architecture Design Sentence Representation N Gram

March 2, 2022

February 28, 2022

February 22, 2022

Wavebender GAN: An architecture for phonetically meaningful speech manipulation
Gustavo Teodoro Döhler Beck, Ulme Wennberg, Zofia Malisz, Gustav Eje Henter
Architecture Design Neural Vocoder Speech Feature

February 4, 2022

Data Scaling Laws in NMT: The Effect of Noise and Architecture
Yamini Bansal, Behrooz Ghorbani, Ankush Garg, Biao Zhang, Maxim Krikun, Colin Cherry, Behnam Neyshabur, Orhan Firat
Long Short Term Memory Mixed Effect Neural Machine Translation Industrial Disturbing Noise Architecture Design Scaling Law Encoder Decoder Transformer Model Language Modeling Loss

February 1, 2022

Architecture Matters in Continual Learning
Seyed Iman Mirzadeh, Arslan Chaudhry, Dong Yin, Timothy Nguyen, Razvan Pascanu, Dilan Gorur, Mehrdad Farajtabar
Continual LEArning Catastrophic Forgetting Neural Network Architecture Architecture Design Federat\textbf{T}ed Cl\textbf{A}ss Continual Lea\textbf{R}nin\textbf{G Continual Learning Performance

January 28, 2022

DoubleU-Net++: Architecture with Exploit Multiscale Features for Vertebrae Segmentation
Simindokht Jahangard, Mahdi Bonyani, Abbas Khosravi
Architecture Design Accurate Segmentation Convolutional Block Attention Vertebra Segmentation CLEVR X Dataset Multiscale Feature

January 4, 2022

Identifying the exterior image of buildings on a 3D map and extracting elevation information using deep learning and digital image processing
Donghwa Shon, Byeongjoon Noh, Nahyang Byun
Deep Learning Image Processing Architecture Design Architecture Perspective 3D Mapping 3D Map Building Information Elevation Data

December 15, 2021

Responsive parallelized architecture for deploying deep learning models in production environments
Nikhil Verma, Krishna Prasad
Deep Learning Model Entity Recognition Architecture Design Hierarchical Attention

December 2, 2021

Architecting and Visualizing Deep Reinforcement Learning Models
Alexander Neuwirth, Derek Riley
Deep Reinforcement Learning Policy Gradient Architecture Design Deep Reinforcement Learning Agent Human Player

November 29, 2021

Architecture Matters: Investigating the Influence of Differential Privacy on Neural Network Design
Felix Morsbach, Tobias Dehling, Ali Sunyaev
Neural Network Differential Privacy Neural Architecture External Influence Architecture Design Differential Privacy Constraint Neural Network Design

November 6, 2021

Development of a robust cascaded architecture for intelligent robot grasping using limited labelled data
Priya Shukla, Vandana Kushwaha, G. C. Nandi
Raw Data Semi Supervised Learning Development Activity Architecture Design Grasping Object Intelligent Robot Grasping

Architecture Design

Papers

Optimizing Mixture of Experts using Dynamic Recompilations

Spatio-Temporal Analysis of Transformer based Architecture for Attention Estimation from EEG

FAMLP: A Frequency-Aware MLP-Like Architecture For Domain Generalization

Radiology Text Analysis System (RadText): Architecture and Evaluation

TextConvoNet:A Convolutional Neural Network based Architecture for Text Classification

Parameter-Efficient Mixture-of-Experts Architecture for Pre-trained Language Models

Recent, rapid advancement in visual question answering architecture: a review

A Data-scalable Transformer for Medical Image Segmentation: Architecture, Model Efficiency, and Benchmark

State-of-the-Art in the Architecture, Methods and Applications of StyleGAN

Wavebender GAN: An architecture for phonetically meaningful speech manipulation

Data Scaling Laws in NMT: The Effect of Noise and Architecture

Architecture Matters in Continual Learning

DoubleU-Net++: Architecture with Exploit Multiscale Features for Vertebrae Segmentation

Identifying the exterior image of buildings on a 3D map and extracting elevation information using deep learning and digital image processing

Responsive parallelized architecture for deploying deep learning models in production environments

Architecting and Visualizing Deep Reinforcement Learning Models

Architecture Matters: Investigating the Influence of Differential Privacy on Neural Network Design

Development of a robust cascaded architecture for intelligent robot grasping using limited labelled data