Become a member
Sign in
Hans Kim
Hans Kim

Hans Kim

15 Following
3 Followers
  • Profile

  • Claps

  • Highlights

Highlighted by Hans Kim

See more

From Visual Interpretability for Convolutional Neural Networks by Himanshu Rawlani

In block5 (especially block5_conv3) we see a lot of blank convolution outputs. This means that the pattern encoded by the filters were not found in the input image. Most probably, these patterns must be complex shapes that are not present in this input image.

From Complete Guide to Machine Learning Project Structuring for Managers by Marco Peixeiro

In the case that your model is underfitting the data, you must then reduce bias by:

From Complete Guide to Machine Learning Project Structuring for Managers by Marco Peixeiro

In the case that your model is overfitting, you mus reduce variance by:

Claps from Hans Kim

See more

Visual Interpretability for Convolutional Neural Networks

Himanshu Rawlani

JSON — The Python Way

The Fellow

A Practical Intro to Test-Driven Development

Luca Piccinelli