Explore >> Select a destination
|
You are here 
|
cgad.ski | ||
| | | | |
marcospereira.me
|
|
| | | | | In this post we summarize the math behind deep learning and implement a simple network that achieves 85% accuracy classifying digits from the MNIST dataset. | |
| | | | |
nickhar.wordpress.com
|
|
| | | | | The algorithm for probabilistically embedding metric spaces into trees has numerous theoretical applications. It is a key tool in the design of many approximation algorithms and online algorithms. Today we will illustrate the usefulness of these trees in designing an algorithm for the online Steiner tree problem. 1. Online Steiner Tree Let $latex {G=(V,E)}&fg=000000$ be... | |
| | | | |
theorydish.blog
|
|
| | | | | The chain rule is a fundamental result in calculus. Roughly speaking, it states that if a variable $latex c$ is a differentiable function of intermediate variables $latex b_1,\ldots,b_n$, and each intermediate variable $latex b_i$ is itself a differentiable function of $latex a$, then we can compute the derivative $latex \frac{{\mathrm d} c}{{\mathrm d} a}$ as... | |
| | | | |
www.superannotate.com
|
|
| | | Why use an activation function and how to choose the right one to train a neural network? Get answers to these questions and more in this post. | ||
