Two Minute Papers highlights an academic research paper that covers how to teach a computer to draw caricatures.
Imagination comes naturally to humans, but how can we create artificial intelligence that can imagine? It turns out that GANs are the key.
In this episode of the AI show Erika follows up on her previous episode by showing the actual code behind training and using the music generation model.
This includes the code for both creating the features from the midi file and returning a midi file from the features. She also shows how Keras is used to generate the actual model.
In this episode of the AI show Erika explains how to create deep learning models with music as the input. She begins by describing the problem of generating music by specifically describing how she generated the appropriate features from a midi file. She then describes the deep learning model she used in order to generate music.
Siraj Raval explores Generative Adversarial Network (GANs) by using them to create new Pokemon.
In this Heroes of Deep Learning video, the legendary Andrew Ng interviews the equally illustrious Ian Goodfellow, the creator of GANs.
Computerphile has a great video explaining Generative Adversarial Networks aka GANs.