Gompertz Linear Units (GoLU) (sps25)

Chaos Computer Club - recent events feed (high quality)

Content provided by CCC media team. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by CCC media team or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://podcastplayer.com/legal.

19d ago 33:53

MP4•Episode home

Activation functions are fundamental elements of deep learning architectures as they significantly influence training dynamics. ReLU, while widely used, is prone to the dying neuron problem, which has been mitigated by variants such as LeakyReLU, PReLU, and ELU that better handle negative neuron outputs. Recently, self-gated activations like GELU and Swish have emerged as state-of-the-art alternatives, leveraging their smoothness to ensure stable gradient flow and prevent neuron inactivity. In this work, we introduce the Gompertz Linear Unit (GoLU), a novel self-gated activation function defined as `GoLU(x) = x Gompertz(x)`, where `Gompertz(x) = exp(−exp(−x))`. The GoLU activation leverages the asymmetry in the Gompertz function to reduce variance in the latent space more effectively compared to GELU and Swish, while preserving robust gradient flow. Extensive experiments across diverse tasks, including Image Classification, Language Modeling, Semantic Segmentation, Object Detection, Instance Segmentation, and Diffusion, highlight GoLU's superior performance relative to state-of-the-art activation functions, establishing GoLU as a robust alternative to existing activation functions. about this event: https://talks.python-summit.ch/sps25/talk/PNL9LP/

2002 episodes

#Tech #Ccc Congress Hacking Security Netzpolitik #Germany #CCC media team #Video