PulseAugur
LIVE 01:29:18
research · [2 sources] ·
1
research

New HTAF activation function enables stable training of binary neural networks

Researchers have developed a new activation function called Heavy Tailed Activation Function (HTAF) to address the challenges of training neural networks with binary representations. HTAF is a smooth approximation of the Heaviside function, designed to maintain a large gradient mass for stable optimization. This new function enables the stable training of various neural network types, including Spiking Neural Networks and Binary Neural Networks, using gradient-based methods. The researchers also introduced Implicit Concept Bottleneck Models (ICBMs), which utilize HTAF to create interpretable image models with discrete feature representations, achieving performance comparable to or better than existing models. AI

Summary written by gemini-2.5-flash-lite from 2 sources. How we write summaries →

IMPACT Enables more efficient and interpretable neural network training for specific applications.

RANK_REASON The cluster contains an academic paper detailing a new method for training neural networks.

Read on arXiv stat.ML →

COVERAGE [2]

  1. arXiv stat.ML TIER_1 · Seokhun Park, Choeun Kim, Kwanho Lee, Sehyun Park, Insung Kong, Yongdai Kim ·

    A Composite Activation Function for Learning Stable Binary Representations

    arXiv:2605.11558v1 Announce Type: cross Abstract: Activation functions play a central role in neural networks by shaping internal representations. Recently, learning binary activation representations has attracted significant attention due to their advantages in computational and…

  2. arXiv stat.ML TIER_1 · Yongdai Kim ·

    A Composite Activation Function for Learning Stable Binary Representations

    Activation functions play a central role in neural networks by shaping internal representations. Recently, learning binary activation representations has attracted significant attention due to their advantages in computational and memory efficiency, as well as interpretability. H…