Recurrent Neural Network Writes Sentences About Images | Two Minute Papers #23

This strategy is a mix of two impressive machine learning algorithms:
– convolutional neural networks are outstanding at image classification, i.e., getting out what is noticed on an input image,
– recurrent neural networks that are able of processing a sequence of inputs and outputs, therefore it can produce sentences of what is noticed on the image.

Combining these two strategies tends to make it attainable for a computer to explain in a sentence what is noticed on an input image.


The paper “Deep Visible-Semantic Alignments for Producing Image Descriptions” is offered right here: today/karpathy/deepimagesent/

A gallery with more effects with the same algorithm: today/karpathy/deepimagesent/generationdemo/

You can practice your have convolutional neural network right here: today/karpathy/convnetjs/demo/cifar10.html

The supply code for the job is now offered right here:

Subscribe if you would like to see more of these! –

The thumbnail image qualifications was produced by Georgie Pauwels (CC BY two.) –
Splash display screen/thumbnail design and style: Felícia Fehér –

Károly Zsolnai-Fehér’s back links:
Patreon →
Fb →
Twitter →
World-wide-web →