5 papers
Hierarchical Scaffolding Enables Human-Like Cognitive Selectivity under Data Scarcity
Juhyoung Park, Jaehyuk Bae, Hyeonbo Yang +1
Modern machine learning systems demand extensive datasets for visual recognition. Conversely, humans learn with high efficiency despite severe data limitations, often by acquiring…
One-Time Soft Alignment Enables Resilient Learning without Weight Transport
Jeonghwan Cheon, Jaehyuk Bae, Se-Bum Paik
Backpropagation is the cornerstone of deep learning, but its reliance on symmetric weight transport and global synchronization makes it computationally expensive and biologically i…
Pretraining with Random Noise for Fast and Robust Learning without Weight Transport
Jeonghwan Cheon, Sang Wan Lee, Se-Bum Paik
The brain prepares for learning even before interacting with the environment, by refining and optimizing its structures through spontaneous neural activity that resembles random no…
Pretraining with random noise for uncertainty calibration
Jeonghwan Cheon, Se-Bum Paik
Uncertainty calibration is crucial for various machine learning applications, yet it remains challenging. Many models exhibit hallucinations - confident yet inaccurate responses -…
Neuromimetic metaplasticity for adaptive continual learning
Suhee Cho, Hyeonsu Lee, Seungdae Baek +1
Conventional intelligent systems based on deep neural network (DNN) models encounter challenges in achieving human-like continual learning due to catastrophic forgetting. Here, we…