Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning

An image with multiple objects: Person, dog and cars
Two images for digit classification. A network should classify both as ‘4’ but suffer higher uncertainty for the left image.
Neural Network with dropout. Neoruns randomly dropped during training
Neural Network with dropout enabled during testing. Multiple feed-forwards, for the same input, generate multiple outputs.
  1. I find the paper contribution significant.
  2. I humbling express my admiration for the theoretical foundation.
  3. A round of applause is due for the released github source code.
  4. From my practical experience, I have one minor negative feedback. The paper language like in “with dropout applied before every weight layer” gives the impression that dropout layers can be simply placed before every trainable layer. This confused me; probably because I am a “deep learning generation”. I prefer “ before every fully-connected layer”. A convolution layer is also a weight layer, yet it requires a different handling.
  5. Based on the previous comment, I must mention followup papers that extend the current theoretical foundation to CNNs[3] and RNNs[4]

--

--

--

I write reviews on computer vision papers. Writing tips are welcomed.

Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

My Encounter with Neural Net: The Exaggerated and Acclaimed “Brain” behind Artificial Intelligence

Pretrained Transformer Language Models for Search — part 3

Localization of Manipulated Image Regions

Classification Vs. Clustering in ML

PyOD: a Unified Python Library for Anomaly Detection

Create a Gradient Descent Algorithm with Regularization from Scratch in Python

Retrosynthesis Using Transformer model

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Ahmed Taha

Ahmed Taha

I write reviews on computer vision papers. Writing tips are welcomed.

More from Medium

Review — A ConvNet for the 2020s

Self-Supervised Learning: Representation Learning via Invariant Causal Mechanisms

Inverse Problems with Unrolled Adversarial Regularization

Object Detection: Intersection over Union (IoU)