From fa48f91b6389cc3736816d6416ed83e43f90d84c Mon Sep 17 00:00:00 2001 From: mhjensen Date: Sat, 29 Dec 2018 20:32:47 +0100 Subject: [PATCH] Overaching view on RNNs --- doc/pub/Recurrent/html/._Recurrent-bs000.html | 3 +- doc/pub/Recurrent/html/._Recurrent-bs001.html | 23 + doc/pub/Recurrent/html/Recurrent-bs.html | 3 +- doc/pub/Recurrent/html/Recurrent-reveal.html | 26 +- .../Recurrent/html/Recurrent-solarized.html | 25 +- doc/pub/Recurrent/html/Recurrent.html | 25 +- doc/pub/Recurrent/html/reveal.js/.gitignore | 7 +- doc/pub/Recurrent/html/reveal.js/.travis.yml | 6 +- doc/pub/Recurrent/html/reveal.js/LICENSE | 2 +- doc/pub/Recurrent/html/reveal.js/README.md | 592 +++---- doc/pub/Recurrent/html/reveal.js/bower.json | 6 +- .../html/reveal.js/css/print/paper.css | 7 +- .../html/reveal.js/css/print/pdf.css | 97 +- .../Recurrent/html/reveal.js/css/reveal.scss | 588 ++----- .../html/reveal.js/css/theme/README.md | 6 +- .../reveal.js/css/theme/source/black.scss | 4 +- .../reveal.js/css/theme/source/white.scss | 4 +- doc/pub/Recurrent/html/reveal.js/index.html | 390 ++++- doc/pub/Recurrent/html/reveal.js/js/reveal.js | 1419 ++++------------- .../html/reveal.js/lib/css/zenburn.css | 119 +- .../html/reveal.js/lib/js/head.min.js | 17 +- doc/pub/Recurrent/html/reveal.js/package.json | 42 +- .../reveal.js/plugin/highlight/highlight.js | 55 +- .../reveal.js/plugin/markdown/example.html | 7 - .../html/reveal.js/plugin/markdown/example.md | 5 - .../reveal.js/plugin/markdown/markdown.js | 57 +- .../html/reveal.js/plugin/markdown/marked.js | 2 +- .../html/reveal.js/plugin/math/math.js | 7 +- .../html/reveal.js/plugin/multiplex/client.js | 2 +- .../html/reveal.js/plugin/multiplex/index.js | 38 +- .../html/reveal.js/plugin/multiplex/master.js | 61 +- .../reveal.js/plugin/notes-server/client.js | 7 +- .../reveal.js/plugin/notes-server/index.js | 31 +- .../reveal.js/plugin/notes-server/notes.html | 241 +-- .../html/reveal.js/plugin/notes/notes.html | 417 +---- .../html/reveal.js/plugin/notes/notes.js | 45 +- .../reveal.js/plugin/print-pdf/print-pdf.js | 75 +- .../html/reveal.js/plugin/search/search.js | 72 +- .../html/reveal.js/plugin/zoom-js/zoom.js | 40 +- .../html/reveal.js/test/examples/math.html | 2 +- .../test/examples/slide-backgrounds.html | 2 +- .../html/reveal.js/test/test-markdown.html | 2 +- .../Recurrent/html/reveal.js/test/test.html | 3 +- doc/pub/Recurrent/html/reveal.js/test/test.js | 10 +- doc/pub/Recurrent/ipynb/Recurrent.ipynb | 23 +- .../ipynb/ipynb-Recurrent-src.tar.gz | Bin 211 -> 212 bytes doc/pub/Recurrent/pdf/Recurrent-minted.pdf | Bin 158158 -> 172349 bytes doc/src/Recurrent/Recurrent.do.txt | 19 + 48 files changed, 1562 insertions(+), 3072 deletions(-) diff --git a/doc/pub/Recurrent/html/._Recurrent-bs000.html b/doc/pub/Recurrent/html/._Recurrent-bs000.html index 76bf464e9..6df563e32 100644 --- a/doc/pub/Recurrent/html/._Recurrent-bs000.html +++ b/doc/pub/Recurrent/html/._Recurrent-bs000.html @@ -6,6 +6,7 @@ Automatically generated HTML file from DocOnce source + Data Analysis and Machine Learning: Recurrent neural networks @@ -100,7 +101,7 @@ end of tocinfo -->
[2] Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University

-

Nov 10, 2018

+

Dec 29, 2018


diff --git a/doc/pub/Recurrent/html/._Recurrent-bs001.html b/doc/pub/Recurrent/html/._Recurrent-bs001.html index 4f4a9d0ba..090fd5c9e 100644 --- a/doc/pub/Recurrent/html/._Recurrent-bs001.html +++ b/doc/pub/Recurrent/html/._Recurrent-bs001.html @@ -6,6 +6,7 @@ Automatically generated HTML file from DocOnce source + Data Analysis and Machine Learning: Recurrent neural networks @@ -83,6 +84,28 @@ end of tocinfo -->

Recurrent neural networks: Overarching view

+

+We have mostly looked at feedforward neural networks, where the +activations flow only in one direction, from the input layer to the +output layer. + +

+A recurrent neural network (RNN) looks very much like a feedforward +neural network, except it also has connections pointing +backward. Let’s look at the simplest possible RNN, composed of just +one neuron receiving inputs, producing an output, and sending that +output back to itself. + +

+RNNs are used to analyze time series data such as stock prices, and +tell you when to buy or sell. In autonomous driving systems, they can +anticipate car trajectories and help avoid accidents. More generally, +they can work on sequences of arbitrary lengths, rather than on +fixed-sized inputs like all the nets we have discussed so far. For +example, they can take sentences, documents, or audio samples as +input, making them extremely useful for natural language processing +systems such as automatic translation and speech-to-text. +