Depthwise separable convolutions for machine learning

Depthwise separable convolutions for machine learning

  • April 12, 2018
Table of Contents

Depthwise separable convolutions for machine learning

Convolutions are an important tool in modern deep neural networks (DNNs). This post is going to discuss some common types of convolutions, specifically regular and depthwise separable convolutions. My focus will be on the implementation of these operation, showing from-scratch Numpy-based code to compute them and diagrams that explain how things work.

Source: thegreenplace.net

Tags :
Share :
comments powered by Disqus

Related Posts

Gift of Garb: How AI Helps Fashion Followers Choose the Best Dress

Gift of Garb: How AI Helps Fashion Followers Choose the Best Dress

Read More
Lessons Learned Reproducing a Deep Reinforcement Learning Paper

Lessons Learned Reproducing a Deep Reinforcement Learning Paper

There are a lot of neat things going on in deep reinforcement learning. One of the coolest things from last year was OpenAI and DeepMind’s work on training an agent using feedback from a human rather than a classical reward signal. There’s a great blog post about it at Learning from Human Preferences, and the original paper is at Deep Reinforcement Learning from Human Preferences.

Read More
Spyce Kitchen, a robotic chef built by four recent M.I.T. grads

Spyce Kitchen, a robotic chef built by four recent M.I.T. grads

Read More