A Machine Learning Perspective on Predictive Coding with PAQ8

34 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Programmable Agents (2017, neutral): “Use of programs to specify hard deterministic gating is also reminiscent of PAQ8 [24, 18].”
Deep Networks with Internal Selective Attention through Feedback Connections (2014, methodology): “Iterative processing of images using recurrency has been successfully used for image reconstruction [48], face-localization [49] and compression [50].”
Online Learning with Gated Linear Networks (2017, background): “Interestingly, while the original motivation for introducing gating was computational (Mahoney, 2000; Knoll and de Freitas, 2012), we show that this technique also adds meaningful representational power as well; • introduce an adaptive regularization technique which allows a Gated Linear Network to…”
Locality Sensitive Sparse Encoding for Learning World Models Online (2024, background): “Inspired by Knoll & de Freitas (2012), we propose an expressive sparse non-linear feature representation which we call locality sensitive sparse encoding.”