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

February 4, 2024

A Collaborative Model-driven Network for MRI Reconstruction
Xiaoyu Qiao, Weisheng Li, Guofen Wang, Yuping Huang
Deep Learning Deep Network Driven Network

January 26, 2024

Inferring Data Preconditions from Deep Learning Models for Trustworthy Prediction in Deployment
Shibbir Ahmed, Hongyang Gao, Hridesh Rajan
Deep Neural Network Deep Learning Model Deep Network DNN Model Software Deployment Model Precondition Trustworthy Prediction

January 25, 2024

Towards Cheaper Inference in Deep Networks with Lower Bit-Width Accumulators
Yaniv Blumenfeld, Itay Hubara, Daniel Soudry
Deep Neural Network Deep Network DNN Accuracy Directed Accumulator

January 20, 2024

Fast and Exact Enumeration of Deep Networks Partitions Regions
Randall Balestriero, Yann LeCun
Deep Neural Network Deep Network Uniform Sampling Label Mapping Efficient Enumeration Affine Spline Affine Model

January 17, 2024

Classification and Reconstruction Processes in Deep Predictive Coding Networks: Antagonists or Allies?
Jan Rathjens, Laurenz Wiskott
Classification Code Supervised Autoencoder Deep Network Deep Learning Architecture Predictive Coding

January 9, 2024

A Deep Network for Explainable Prediction of Non-Imaging Phenotypes using Anatomical Multi-View Data
Yuxiang Wei, Yuqian Chen, Tengfei Xue, Leo Zekelman, Nikos Makris, Yogesh Rathi, Weidong Cai, Fan Zhang, Lauren J. O' Donnell
Multi View Deep Network Multi View Learning Explainable Prediction Brain Phenotype Feature Set

January 7, 2024

On The Potential of The Fractal Geometry and The CNNs Ability to Encode it
Julia El Zini, Bassel Musharrafieh, Mariette Awad
Deep Network Full Potential Fractal Structure CNN Performance Fractal Dimension Fractal Feature

January 3, 2024

Task and Explanation Network
Moshe Sipper
Artificial Intelligence Line by Line Explanation High Explainability Deep Network Related Task Explicable Reconstruction Network

December 26, 2023

Exploiting the capacity of deep networks only at training stage for nonlinear black-box system identification
Vahid MohammadZadeh Eivaghi, Mahdi Aliyari Shooredeli
Deep Network Deep Model Deep Generative Model System Identification Deep Architecture Capacity Loss Basis Function Training Stage

December 20, 2023

DynaLay: An Introspective Approach to Dynamic Layer Selection for Deep Networks
Mrinal Mathur, Sergey Plis
Deep Learning Model Deep Network Complex Valued Decision Making Agent Layer Selection

December 13, 2023

Curriculum-Enhanced Residual Soft An-Isotropic Normalization for Over-smoothness in Deep GNNs
Jin Li, Qirong Zhang, Shuling Xu, Xinlong Chen, Longkun Guo, Yang-Geng Fu
Deep Network Node Embeddings Undisciplined Over Smoothing Input Graph

December 3, 2023

Brain Decodes Deep Nets
Huzheng Yang, James Gee, Jianbo Shi
Pre Trained Model Deep Network Vision Model Brain Encoding Deep Learning Feature

November 18, 2023

Deep Tensor Network
Yifan Zhang
Deep Network Deep Learning Architecture Tensor Network Tensor Type Calculus Tensorial Template Tensor Attention

November 14, 2023

Convolutional Neural Networks Exploiting Attributes of Biological Neurons
Neeraj Kumar Singh, Nikhil R. Pal
Convolutional Neural Network Deep Network Receptive Field Neural System Biological Neuron Attribute Based Representation

November 6, 2023

Understanding Deep Representation Learning via Layerwise Feature Compression and Discrimination
Peng Wang, Xiao Li, Can Yaras, Zhihui Zhu, Laura Balzano, Wei Hu, Qing Qu
Deep Learning Deep Network Deep Representation Deep Linear Group DIscrimination Feature Compression Deep Layer Deep Nonlinear

November 2, 2023

Improving Robustness via Tilted Exponential Layer: A Communication-Theoretic Perspective
Bhagyashree Puranik, Ahmad Beirami, Yao Qin, Upamanyu Madhow
Native Robustness Deep Network Tilting Angle Robust Inference Communication Perspective

October 30, 2023

October 28, 2023

Deep Network

Papers

A Collaborative Model-driven Network for MRI Reconstruction

Inferring Data Preconditions from Deep Learning Models for Trustworthy Prediction in Deployment

Towards Cheaper Inference in Deep Networks with Lower Bit-Width Accumulators

Fast and Exact Enumeration of Deep Networks Partitions Regions

Classification and Reconstruction Processes in Deep Predictive Coding Networks: Antagonists or Allies?

A Deep Network for Explainable Prediction of Non-Imaging Phenotypes using Anatomical Multi-View Data

On The Potential of The Fractal Geometry and The CNNs Ability to Encode it

Task and Explanation Network

Exploiting the capacity of deep networks only at training stage for nonlinear black-box system identification

DynaLay: An Introspective Approach to Dynamic Layer Selection for Deep Networks

Curriculum-Enhanced Residual Soft An-Isotropic Normalization for Over-smoothness in Deep GNNs

Brain Decodes Deep Nets

Deep Tensor Network

Convolutional Neural Networks Exploiting Attributes of Biological Neurons

Understanding Deep Representation Learning via Layerwise Feature Compression and Discrimination

Improving Robustness via Tilted Exponential Layer: A Communication-Theoretic Perspective

Exploring Geometry of Blind Spots in Vision Models

TransXNet: Learning Both Global and Local Dynamics with a Dual Dynamic Token Mixer for Visual Recognition

Improving Compositional Generalization Using Iterated Learning and Simplicial Embeddings

The Evolution of the Interplay Between Input Distributions and Linear Regions in Networks