Greg Surma
Greg Surma

Jan 9, 2021

·
9 min read
·

CNN Explainer - Interpreting Convolutional Neural Networks (1/N)

Generating Area Importance Heatmaps with Occlusions

In today’s article, we are going to start a series of articles that aim to demystify the results of Convolutional Neural Networks (CNNs). CNNs are very successful in solving many Computer Vision tasks, but as they are Neural Networks after all, they may fall into the…

--

--

More from Greg Surma

https://gsurma.github.io

Recommended from Medium

Serafeim Loukas

Serafeim Loukas

in

MLearning.ai

How To Classify Handwritten Digits Using A Multilayer Perceptron Classifier

Frank Zickert | Quantum Machine Learning

Frank Zickert | Quantum Machine Learning

in

Towards Data Science

A Generalized Quantum Linear Function

Ignitarium

Ignitarium

Automatic Container Code Recognition using Deep Learning | ignitarium.com

陳翰儒

陳翰儒

往googler的路上day178

Frank Zickert | Quantum Machine Learning

Frank Zickert | Quantum Machine Learning

in

Towards Data Science

Solving Optimization Problems With A Quantum Computer Is Surprisingly Easy

Deep Gojariya

Deep Gojariya

Introduction to Machine Learning

Yigit Can Turk

Yigit Can Turk

in

Analytics Vidhya

The Affect of Regularization Techniques

Tim Lee

Tim Lee

Moviegoer: Cinematography Shot Modeling

AboutHelpTermsPrivacy


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
Get unlimited access
Greg Surma

Greg Surma

1.8K Followers

https://gsurma.github.io

Help

Status

Writers

Blog

Careers

Privacy

Terms

About

Text to speech