mhjensen
47 lines
2.1 KiB
Plaintext
47 lines
2.1 KiB
Plaintext
{
|
||
"cells": [
|
||
{
|
||
"cell_type": "markdown",
|
||
"metadata": {},
|
||
"source": [
|
||
"<!-- dom:TITLE: Data Analysis and Machine Learning: Recurrent neural networks -->\n",
|
||
"# Data Analysis and Machine Learning: Recurrent neural networks\n",
|
||
"<!-- dom:AUTHOR: Morten Hjorth-Jensen at Department of Physics, University of Oslo & Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University -->\n",
|
||
"<!-- Author: --> \n",
|
||
"**Morten Hjorth-Jensen**, Department of Physics, University of Oslo and Department of Physics and Astronomy and National Superconducting Cyclotron Laboratory, Michigan State University\n",
|
||
"\n",
|
||
"Date: **Dec 29, 2018**\n",
|
||
"\n",
|
||
"Copyright 1999-2018, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license\n",
|
||
"\n",
|
||
"\n",
|
||
"\n",
|
||
"\n",
|
||
"## Recurrent neural networks: Overarching view\n",
|
||
"\n",
|
||
"We have mostly looked at feedforward neural networks, where the\n",
|
||
"activations flow only in one direction, from the input layer to the\n",
|
||
"output layer.\n",
|
||
"\n",
|
||
"A recurrent neural network (RNN) looks very much like a feedforward\n",
|
||
"neural network, except it also has connections pointing\n",
|
||
"backward. Let’s look at the simplest possible RNN, composed of just\n",
|
||
"one neuron receiving inputs, producing an output, and sending that\n",
|
||
"output back to itself.\n",
|
||
"\n",
|
||
"RNNs are used to analyze time series data such as stock prices, and\n",
|
||
"tell you when to buy or sell. In autonomous driving systems, they can\n",
|
||
"anticipate car trajectories and help avoid accidents. More generally,\n",
|
||
"they can work on sequences of arbitrary lengths, rather than on\n",
|
||
"fixed-sized inputs like all the nets we have discussed so far. For\n",
|
||
"example, they can take sentences, documents, or audio samples as\n",
|
||
"input, making them extremely useful for natural language processing\n",
|
||
"systems such as automatic translation and speech-to-text."
|
||
]
|
||
}
|
||
],
|
||
"metadata": {},
|
||
"nbformat": 4,
|
||
"nbformat_minor": 2
|
||
}
|