Fabian Fuchs
# Gumbel Softmax This post introduces the Gumbel Softmax estimator for stochastic neural networks. It was simultaneously discovered by [Maddison et al.](https://arxiv.org/abs/1611.00712) and [Jang et al.](https://arxiv.org/abs/1611.01144), with both papers published at ICLR 2017. I took figures, equations and notation from the latter of the two. ## Vanilla Gumbel Softmax Estimator...
Fabian Fuchs Gumbel Softmax This post introduces the Gumbel Softmax estimator for stochastic neural networks. It was simultaneously discovered by Maddison et al. and Jang et al. , with both papers published at ICLR 2017. I took figures, equations and notation from the latter of the two. Vanilla Gumbel Softmax Estimator The Gumbel Softmax trick can be looked at from different angles. I will approach it from an attention angle, which has a broad range of applications in deep learning. For example, imagine a neural network that processes an image and decomposes it into multiple objects. Now we wa
Explore this link on the map →saved by
related reading
- Generative Modeling by Estimating Gradients of the Data Distribution | Yang Songyang-song.github.io
- [1611.01144] Categorical Reparameterization with Gumbel-Softmaxarxiv.org
- Attention Is Off By One – Evan Millerevanmiller.org
- Bayesian Neural Networkscs.toronto.edu
- The Decade of Deep Learning | Leo Gaobmk.sh
- 2409.02908arxiv.org
- microgptkarpathy.github.io
- arxiv.org/pdf/1805.08522arxiv.org
- [1706.04599] On Calibration of Modern Neural Networksarxiv.org
- Annotated Research Paper Implementations: Transformers, StyleGAN, Stable Diffusion, DDPM/DDIM, LayerNorm, Nucleus Sampling and morenn.labml.ai
- Softmax function - Wikipediaen.wikipedia.org
- Stochastic gradient descent - Wikipediaen.m.wikipedia.org