Picture for Jinyung Hong

Jinyung Hong

Learning Decomposable and Debiased Representations via Attribute-Centric Information Bottlenecks

Add code
Mar 21, 2024
Viaarxiv icon

Concept-Centric Transformers: Concept Transformers with Object-Centric Concept Learning for Interpretability

Add code
May 25, 2023
Viaarxiv icon

Learning to modulate random weights can induce task-specific contexts for economical meta and continual learning

Add code
Apr 08, 2022
Figure 1 for Learning to modulate random weights can induce task-specific contexts for economical meta and continual learning
Figure 2 for Learning to modulate random weights can induce task-specific contexts for economical meta and continual learning
Figure 3 for Learning to modulate random weights can induce task-specific contexts for economical meta and continual learning
Figure 4 for Learning to modulate random weights can induce task-specific contexts for economical meta and continual learning
Viaarxiv icon

Representing Prior Knowledge Using Randomly, Weighted Feature Networks for Visual Relationship Detection

Add code
Nov 20, 2021
Figure 1 for Representing Prior Knowledge Using Randomly, Weighted Feature Networks for Visual Relationship Detection
Figure 2 for Representing Prior Knowledge Using Randomly, Weighted Feature Networks for Visual Relationship Detection
Figure 3 for Representing Prior Knowledge Using Randomly, Weighted Feature Networks for Visual Relationship Detection
Viaarxiv icon

An Insect-Inspired Randomly, Weighted Neural Network with Random Fourier Features For Neuro-Symbolic Relational Learning

Add code
Sep 11, 2021
Figure 1 for An Insect-Inspired Randomly, Weighted Neural Network with Random Fourier Features For Neuro-Symbolic Relational Learning
Figure 2 for An Insect-Inspired Randomly, Weighted Neural Network with Random Fourier Features For Neuro-Symbolic Relational Learning
Figure 3 for An Insect-Inspired Randomly, Weighted Neural Network with Random Fourier Features For Neuro-Symbolic Relational Learning
Figure 4 for An Insect-Inspired Randomly, Weighted Neural Network with Random Fourier Features For Neuro-Symbolic Relational Learning
Viaarxiv icon

KCNet: An Insect-Inspired Single-Hidden-Layer Neural Network with Randomized Binary Weights for Prediction and Classification Tasks

Add code
Aug 17, 2021
Figure 1 for KCNet: An Insect-Inspired Single-Hidden-Layer Neural Network with Randomized Binary Weights for Prediction and Classification Tasks
Figure 2 for KCNet: An Insect-Inspired Single-Hidden-Layer Neural Network with Randomized Binary Weights for Prediction and Classification Tasks
Figure 3 for KCNet: An Insect-Inspired Single-Hidden-Layer Neural Network with Randomized Binary Weights for Prediction and Classification Tasks
Figure 4 for KCNet: An Insect-Inspired Single-Hidden-Layer Neural Network with Randomized Binary Weights for Prediction and Classification Tasks
Viaarxiv icon

Randomly Weighted, Untrained Neural Tensor Networks Achieve Greater Relational Expressiveness

Add code
Jun 01, 2020
Figure 1 for Randomly Weighted, Untrained Neural Tensor Networks Achieve Greater Relational Expressiveness
Figure 2 for Randomly Weighted, Untrained Neural Tensor Networks Achieve Greater Relational Expressiveness
Figure 3 for Randomly Weighted, Untrained Neural Tensor Networks Achieve Greater Relational Expressiveness
Figure 4 for Randomly Weighted, Untrained Neural Tensor Networks Achieve Greater Relational Expressiveness
Viaarxiv icon