Search Results for author: Seokjun Kim

Found 6 papers, 0 papers with code

Imagine Networks

no code implementations4 Nov 2021 Seokjun Kim, Jaeeun Jang, Hyeoncheol Kim

In this paper, we introduce an imagine network that can simulate itself through artificial association networks.

reinforcement-learning Reinforcement Learning (RL)

Memory Association Networks

no code implementations3 Nov 2021 Seokjun Kim, Jaeeun Jang, Yeonju Jang, Seongyune Choi, Hyeoncheol Kim

We introduce memory association networks(MANs) that memorize and remember any data.

Deductive Association Networks

no code implementations2 Nov 2021 Seokjun Kim, Jaeeun Jang, Hyeoncheol Kim

we introduce deductive association networks(DANs), a network that performs deductive reasoning.

All-In-One: Artificial Association Neural Networks

no code implementations31 Oct 2021 Seokjun Kim, Jaeeun Jang, Hyeoncheol Kim

Further, we propose a new neural data structure that can express all basic models of existing neural networks in a tree structure.

Graph Tree Neural Networks

no code implementations29 Sep 2021 Seokjun Kim, Jaeeun Jang, Heeseok Jung, Hyeoncheol Kim

Instead of using fixed sequence layers, we create a GT for each data and train GTNN according to the tree's structure.

Pixab-CAM: Attend Pixel, not Channel

no code implementations29 Sep 2021 Jaeeun Jang, Seokjun Kim, Hyeoncheol Kim

To understand the internal behaviors of convolution neural networks (CNNs), many class activation mapping (CAM) based methods, which generate an explanation map by a linear combination of channels and corresponding weights, have been proposed.

Adversarial Attack

Cannot find the paper you are looking for? You can Submit a new open access paper.