{"id":1617,"date":"2023-02-02T13:35:21","date_gmt":"2023-02-02T17:35:21","guid":{"rendered":"http:\/\/jeffq.com\/blog\/?p=1617"},"modified":"2023-02-02T13:35:21","modified_gmt":"2023-02-02T17:35:21","slug":"literai-ai-generated-open-source-visual-podcasts","status":"publish","type":"post","link":"http:\/\/jeffq.com\/blog\/literai-ai-generated-open-source-visual-podcasts\/","title":{"rendered":"literAI: AI-generated open source visual podcasts"},"content":{"rendered":"\n

Demo: https:\/\/literai.hooloovoo.ai\/<\/a> Source: Generator<\/a>, UI<\/a><\/em><\/p>\n\n\n\n

At my previous job I did some shader programming, and generally tinkered around with GPU workloads, and even had the chance to attend Nvidia’s GPU Technology Conference a few times. I remember in 2018 or so being surprised that more and more of the conversation in this area was being dominated by these things called “deep neural networks”. During my CS studies I was focused on cryptography, but I was curious what all this was about and took an early version of Udacity’s Deep Learning Nanodegree (don’t laugh!)<\/p>\n\n\n\n

The class was actually fairly insightful — making you learn about backpropagation, etc. from scratch and took you through the motions of the classic MNIST classification tasks and so forth. It ended with doing face generation using these fancy things called convolutional<\/em> neural networks.<\/p>\n\n\n\n

\n

Some randomly generated faces created by a
deep convolutional generative adversarial network I made as part of my #udacity<\/a> course. Not super practical, but still eminently cool

P.S. Twitter asks "Who's in these photos?" when I upload them. The dreams of electric sheep, Twitter. pic.twitter.com\/Tf6iAWHEl8<\/a><\/p>— emozilla (@theemozilla) July 8, 2018<\/a><\/blockquote>