2014/02/10 by Vincent Michalski, Roland Memisevic, Michalski, Vincent +3 · 1 citation
Computer Science · Mathematics · #Advanced Image Processing Techniques #Artificial intelligence #Autoencoder #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Deep learning #ENCODE #Encoding (memory) #FOS: Computer and information sciences #Feature (linguistics) #Frame (networking) #Generative Adversarial Networks and Image Synthesis #Image and Signal Denoising Methods #Linear model #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine learning #Pattern recognition (psychology) #Sequence (biology) #cs.CV #cs.LG #stat.ML
paper · pdf · doi:10.48550/arxiv.1402.2333
arxiv created 2014/02/10 · openalex publication_date 2014/02/10 · arxiv updated 2014/02/12 · openalex created_date 2016/06/24 · openalex updated_date 2026/07/28
Bi-linear feature learning models, like the gated autoencoder, were proposed as a way to model relationships between frames in a video. By minimizing reconstruction error of one frame, given the previous frame, these models learn "mapping units" that encode the transformations inherent in a sequence, and thereby learn to encode motion. In this work we extend bi-linear models by introducing "higher-order mapping units" that allow us to encode transformations between frames and transformations between transformations. We show that this makes it possible to encode temporal structure that is more complex and longer-range than the structure captured within standard bi-linear models. We also show that a natural way to train the model is by replacing the commonly used reconstruction objective with a prediction objective which forces the model to correctly predict the evolution of the input multiple steps into the future. Learning can be achieved by back-propagating the multi-step prediction through time. We test the model on various temporal prediction tasks, and show that higher-order mappings and predictive training both yield a significant improvement over bi-linear models in terms of prediction accuracy.