IJCNN 2020
440 papers
The 2020 International Joint Conference on Neural Networks (IJCNN) featured 546 papers, with research focusing on domain adaptation and the development of invariant representations. Key themes involved improving model generalization through statistical alignment and unsupervised learning. Knowledge distillation was also a major area of study, particularly regarding collaborative training and dynamic weighting for adaptive model training. Additionally, the conference highlighted advancements in model robustness, such as adversarial purification via generative manifold reconstruction and geometric stability for deep neural networks.
Other research directions included continual learning through feature stabilization and efficient optimization for dense prediction. Practical applications presented during the event ranged from traffic signal control using centralized coordinators to multimodal autoencoders for music recommendation and transformer-based architectures for abstractive text summarization. Prolific authors contributing to this year's proceedings included Imran Razzak, Albert Bifet, and Saeeda Naz. The research collectively addressed the challenges of making neural networks more adaptive, resilient, and efficient across diverse data environments.
Top Research Directions
Research directions most represented by IJCNN 2020 papers.
Top Authors
Impactful Papers
Papers from IJCNN 2020 that shaped research clusters.
Foundational
G1020: A Benchmark Retinal Fundus Image Dataset for Computer-Aided Glaucoma Detection
foundational
Overcoming the Clinical Generalization G
An Efficient Spiking Neural Network for Recognizing Gestures with a DVS Camera on the Loihi Neuromor
foundational
Residual Potential Preservation in Spiki
Identity-Preserving Realistic Talking Face Generation
foundational
Synchronizing Head Pose with Speech Pros
Adversarial Reinforcement Learning under Partial Observability in Autonomous Computer Network Defenc
foundational
Adversarial Vulnerability in Multi Agent
Minibatch Processing for Speed-up and Scalability of Spiking Neural Network Simulation
foundational
Mitigating Spike Degradation in Deep Spi
Attention-based 3D Object Reconstruction from a Single Image
foundational
Self Attention for Long Range 3D Spatial
Mutual Information Maximization in Graph Neural Networks
foundational
Aligning Local Substructures with Global
Influential
Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning
influential
Overcoming Confirmation Bias in Semi-Sup
Unseen Target Stance Detection with Adversarial Domain Generalization
influential
Resolving Neutral Class Ambiguity in Sen
"I'm Sorry Dave, I'm Afraid I Can't Do That" Deep Q-Learning from Forbidden Actions
influential
Bridging the Discrete and Continuous Rei
Accelerating Reinforcement Learning for Reaching Using Continuous Curriculum Learning
influential
Zero-Shot Sim-to-Real Transfer for Robot
On Interpretability of Deep Learning based Skin Lesion Classifiers using Concept Activation Vectors
influential
Unsupervised Concept Discovery in Deep L
Mutual Information Maximization in Graph Neural Networks
influential
Scaling Graph Learning to Massive Networ
AM-MobileNet1D: A Portable Model for Speaker Recognition
influential
Feature Learning Directly from Raw Audio
Continuous Emotion Recognition via Deep Convolutional Autoencoder and Support Vector Regressor
influential
Modeling the Temporal Evolution of Facia
Fisher Discriminant Triplet and Contrastive Losses for Training Siamese Networks
influential
Overcoming Small Batch Instability in De
An improved online learning algorithm for general fuzzy min-max neural network
influential
Handling Mixed Discrete and Continuous D
Papers
« prev Page 9/9