Compressed Network Search Finds Complex Neural Controllers with a Million Weights First Deep Learner to learn control policies directly from high-dimensional sensory input using reinforcement learning Jürgen Schmidhuber, 2013 http://people.idsia.ch/~juergen/compressednetworksearch.html
On Fri, Oct 5, 2018 at 4:05 PM Jim Bromer via AGI <[email protected]> wrote: > A good goal for a next generation compression system is to allow > functional transformations to operate on some compressed data without > needing to decompress it first. (I forgot what this is called but > there is a Wikipedia entry on something s8milar in cryptography.) > This is how multiplication works by the way. > > If a 'dynamic compression' was preformed in stages using 'components' > which had certain abstract attributes that could be used in > computations that were done in multiple passes, then it might be > possible to postpone a complete analysis or computation until the data > was presented in a more abstract format (relative to the given > problem). The goal is to find a way to make each pass effective but > seriously less complicated. The idea is that the data 'components' > (the data produced by a previous pass) might have certain abstract > properties that were general, and subsequent passes might then operate > on narrower classes. (This is how many algorithms work now that I > think about it, but they are not described and defined using the > concept of compression abstractions as a fundamental principle.) > Jim Bromer ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T55454c75265cabe2-M01199666719c06c491928b24 Delivery options: https://agi.topicbox.com/groups/agi/subscription
