Solving toxicity on the internet using AI

What is an LSTM

Our example Credit: Udacity
A more likely version of events Credit: Udacity
How our RNN works Credit: Udacity
An overview of an LSTM Credit: Udacity

Basics of LSTM’s

Our four gates Credit: Udacity
What our outputs are like after running them through an LSTM Credit: Udacity
Credit: Udacity

The architecture of LSTM’s

The learn gate

What the equation looks like Credit: Udacity

Forget gate

The equation for the forget gate Credit: Udacity

The remember gate

Remember gate equation Credit: Udacity

The use gate

The use gate equation Credit: Udacity

LSTM’s on Toxic Comments

Building a vocabulary and dictionary
Labeling the words
Giving our sentences number values as discussed previously
Final steps before we generate the model
Our final AI
Calculating when to stop training our model
A pretty normal graph






15 years old. Contact me at:

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

Recommended from Medium

Neural Networks and Fibonacci Numbers

Machine Learning at Insurance Companies

Reading: Li ICME’17 — Three-Branch Deep CNN for Complexity Reduction on Intra-Mode HEVC (Fast HEVC)

Review — Exemplar-CNN: Discriminative Unsupervised Feature Learning with Convolutional Neural…

A Machine Learning Approach to Databases Indexes

Review: Representation Learning with Contrastive Predictive Coding (CPC/CPCv1)

Using TPUs on Google Colab with Keras

Detecting Cassava Leaf Disease, Part 1

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
Abhi Siripurapu

Abhi Siripurapu

15 years old. Contact me at:

More from Medium

Decentral announces strategic partnership with 7StarPay

Oblique Strategies

DES 102 Interaction choose your own -Ethnography

How to build a modern outbound sales machine that grows your sales in a predictable way of scaling