Discussion for topics dealt with on W3D5
Reposting a reference question here from the Q&A:
@mpbrigham - Were you able to find the papers where they used autoencoders to predict next movie frames and occluded objects in video games?
Thank you very much!
Joram
Thank you for your question @joramvanrheede! Autoencoders are such an inspiring subject - I’ll post some other of my favorite articles and blogs!
A Neural Representation of Sketch Drawings by Ha and Eck
also see Teaching Machines to Draw
Neural scene representation and rendering by Eslami et al.
also see blog: Neural scene representation and rendering
Unsupervised Learning of Video Representations using LSTMs by Srivastava et al.
Deep Learning in Next-Frame Prediction: A Benchmark Review by Zhou et al.
Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles by Noroozi and Favaro
Self-Supervised Scene De-occlusion by Zhan et al
An Uncertain Future: Forecasting from Static Images using Variational Autoencoders by Walker et al.
Generating Sequences With Recurrent Neural Networks by Graves
also see Four Experiments in Handwriting with a Neural Network
Fantastic, thank you very much!