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

June 9, 2023

June 8, 2023

Beyond Probability Partitions: Calibrating Neural Networks with Semantic Aware Grouping
Jia-Qi Yang, De-Chuan Zhan, Le Gan
Neural Network Deep Network Prediction Error Calibration Metric Grouping Network Random Partition Model

June 2, 2023

Towards Sustainable Learning: Coresets for Data-efficient Deep Learning
Yu Yang, Hao Kang, Baharan Mirzasoleiman
Deep Network Deep Model Faster Convergence Convex Loss Data Efficient Deep Learning Sustainable Deep Learning

May 31, 2023

The Tunnel Effect: Building Data Representations in Deep Neural Networks
Wojciech Masarczyk, Mateusz Ostaszewski, Ehsan Imani, Razvan Pascanu, Piotr Miłoś, Tomasz Trzciński
Deep Neural Network Continual LEArning Deep Network Deeper Network Separable Representation

May 30, 2023

May 27, 2023

On the special role of class-selective neurons in early training
Omkar Ranadive, Nikhil Thakurdesai, Ari S Morcos, Matthew Leavitt, Stéphane Deny
Supervised ImageNet Integral Role Deep Network Training Dynamic Individual Neuron Selective Engagement Selective Neuron

May 25, 2023

Detecting Heart Disease from Multi-View Ultrasound Images via Supervised Attention Multiple Instance Learning
Zhe Huang, Benjamin S. Wessler, Michael C. Hughes
Deep Network Multiple Instance Learning Ultrasound Image Aortic Aneurysm Heart Disease Detection Aortic Stenosis

May 22, 2023

May 17, 2023

Connected Hidden Neurons (CHNNet): An Artificial Neural Network for Rapid Convergence
Rafiad Sadat Shahir, Zayed Humayun, Mashrufa Akter Tamim, Shouri Saha, Md. Golam Rabiul Alam
Neural Network Deep Network Biological Neural Network Convergence Performance Hidden Neuron Conventional Neural Network

May 14, 2023

Analyzing Compression Techniques for Computer Vision
Maniratnam Mandal, Imran Khan
Knowledge Distillation Computer Vision Deep Network Compression Technique Small Object Detection Computer Vision Application

May 12, 2023

May 11, 2023

Deep Network

Papers

How Sparse Can We Prune A Deep Network: A Fundamental Limit Viewpoint

Hidden Classification Layers: Enhancing linear separability between classes in neural networks layers

Beyond Probability Partitions: Calibrating Neural Networks with Semantic Aware Grouping

Towards Sustainable Learning: Coresets for Data-efficient Deep Learning

On the Weight Dynamics of Deep Normalized Networks

Parallel Neurosymbolic Integration with Concordia

Combining Explicit and Implicit Regularization for Efficient Learning in Deep Networks

The Tunnel Effect: Building Data Representations in Deep Neural Networks

Recognizing People by Body Shape Using Deep Networks of Images and Words

Adaptation of Tongue Ultrasound-Based Silent Speech Interfaces Using Spatial Transformer Networks

On the special role of class-selective neurons in early training

Detecting Heart Disease from Multi-View Ultrasound Images via Supervised Attention Multiple Instance Learning

DeepBern-Nets: Taming the Complexity of Certifying Neural Networks using Bernstein Polynomial Activations and Precise Bound Propagation

Interpretable Mesomorphic Networks for Tabular Data

Connected Hidden Neurons (CHNNet): An Artificial Neural Network for Rapid Convergence

Analyzing Compression Techniques for Computer Vision

Field theory for optimal signal propagation in ResNets

Machine Vision Using Cellphone Camera: A Comparison of deep networks for classifying three challenging denominations of Indian Coins

Provable Guarantees for Nonlinear Feature Learning in Three-Layer Neural Networks

ReMark: Receptive Field based Spatial WaterMark Embedding Optimization using Deep Network