aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorDeterminant <[email protected]>2016-05-01 00:42:26 +0800
committerDeterminant <[email protected]>2016-05-01 00:42:26 +0800
commit2bb64ecc5e0350f89cff1e978a1b8dcca1528a06 (patch)
treeaf99e478c754405725e1a5d6f3e23acede523044
parent6051c37a2c55365a5834d5b4c11d973e2e4e1ad4 (diff)
add overview doc
-rw-r--r--nerv/doc/source/conf.py18
-rw-r--r--nerv/doc/source/overview.rst127
-rw-r--r--nerv/doc/source/user.rst6
3 files changed, 140 insertions, 11 deletions
diff --git a/nerv/doc/source/conf.py b/nerv/doc/source/conf.py
index 4d6119f..c17c333 100644
--- a/nerv/doc/source/conf.py
+++ b/nerv/doc/source/conf.py
@@ -1,6 +1,6 @@
# -*- coding: utf-8 -*-
#
-# Nerv documentation build configuration file, created by
+# NERV documentation build configuration file, created by
# sphinx-quickstart on Thu Jun 25 19:40:07 2015.
#
# This file is execfile()d with the current directory set to its
@@ -50,9 +50,9 @@ source_suffix = '.rst'
master_doc = 'index'
# General information about the project.
-project = u'Nerv'
-copyright = u'2015, Ted Yin, Tianxing He'
-author = u'Ted Yin, Tianxing He'
+project = u'NERV'
+copyright = u'2015, SJTU SpeechLab'
+author = u'SJTU SpeechLab'
# The version info for the project you're documenting, acts as replacement for
# |version| and |release|, also used in various other places throughout the
@@ -204,7 +204,7 @@ html_static_path = ['_static']
#html_search_scorer = 'scorer.js'
# Output file base name for HTML help builder.
-htmlhelp_basename = 'Nervdoc'
+htmlhelp_basename = 'nervdoc'
# -- Options for LaTeX output ---------------------------------------------
@@ -226,7 +226,7 @@ latex_elements = {
# (source start file, target name, title,
# author, documentclass [howto, manual, or own class]).
latex_documents = [
- (master_doc, 'Nerv.tex', u'Nerv Documentation',
+ (master_doc, 'nerv.tex', u'NERV Documentation',
u'Ted Yin, Tianxing He', 'manual'),
]
@@ -256,7 +256,7 @@ latex_documents = [
# One entry per manual page. List of tuples
# (source start file, name, description, authors, manual section).
man_pages = [
- (master_doc, 'nerv', u'Nerv Documentation',
+ (master_doc, 'nerv', u'NERV Documentation',
[author], 1)
]
@@ -270,8 +270,8 @@ man_pages = [
# (source start file, target name, title, author,
# dir menu entry, description, category)
texinfo_documents = [
- (master_doc, 'Nerv', u'Nerv Documentation',
- author, 'Nerv', 'One line description of project.',
+ (master_doc, 'nerv', u'NERV Documentation',
+ author, 'NERV', 'One line description of project.',
'Miscellaneous'),
]
diff --git a/nerv/doc/source/overview.rst b/nerv/doc/source/overview.rst
new file mode 100644
index 0000000..ccdd2ef
--- /dev/null
+++ b/nerv/doc/source/overview.rst
@@ -0,0 +1,127 @@
+Overview
+========
+
+What is NERV?
+-------------
+
+NERV is a general-purpose deep learning toolkit designed to be be simple,
+lightweight and extensible. The name "NERV" comes from the German word "nerv"
+for "nerve" in English. It is also a fictional organization in the *Neon
+Genesis Evangelion*, a famous anime.
+
+
+Why NERV?
+---------
+
+In recent years, the invention and prevalence of the deep neural network (DNN)
+and related deep learning techniques have given rise to many tools and toolkits
+which are designed for constructing and training neural networks which could
+facilitate and routinize the research cycle of deep learning applied to areas
+such as speech processing, computer vision, natural language processing and so
+on. Such tools or toolkits can be categorized into two by design: task-specific or general-purpose.
+
+The first category tries to address the deep learning in a direct way. These
+tools usually have a very specific goal, which means to support a certain type
+of neural network model and provides with peripheral facilities dedicated to
+one specific task, such as image classification or phone state prediction. Not
+only the network model is hard-coded into the very core of the tool, but some
+modifications or tricks that are only specific to a certain task are wired into
+the code. The effect of this approach is two-fold. On the one hand, they have a
+complete and tightly designed system that appears to provide with a simple user
+interface. Thus, researchers who are familiar with that specific area can use
+it easily. Also, because the network is hard-coded and task-specific, the
+implementation could be easy and optimization could be effective so that offers
+a very efficient running speed (such as Current). However, on the other hand,
+these usability and efficiency come at the cost of lacking reusability and
+flexibility. People need to hack the code and make modifications to suit the
+tool to another structure of neural network model, and it is very difficult and
+tricky to use the tool designed for one specific area (for example, image
+classification) in another area (like speech recognition). Engineering details
+and implementation tricks refrain people from doing so. Caffee, which is
+designed for computer vision, has a comprehensive variety of tools for
+processing images and training convolution neural networks (CNN). But it cannot
+be directly applied to speech processing tasks. Luckily, there is Kaldi, a
+counterpart in speech processing that can process wave-form files, extract the
+acoustic features, train GMM-HMM models, fully-connected DNN models, LSTM
+models and so on.
+
+The second category strives to be general-purpose. As mentioned above, there are two types of generalities:
+
+- General among different network structures
+- General among different tasks
+
+The advantages of such general approach is obvious: we can train different
+network structures as long as the required basic computation units are provided
+by the toolkit. Besides, general-purpose toolkits usually have a unified
+interface for data input and output (I/O) which is the most task-specific
+part. Therefore, the task-specific implementation details are limited to
+separated I/O modules as possible. This concept of design also presents in
+operating systems where device-specific code are modularized and isolated from
+the core part and several abstraction layers are often used. Therefore, by this
+approach, general-purpose toolkits usually can be potentially adapted to
+various kinds of tasks without hacking or changing core code. Admittedly, the
+generalities are accomplished at the cost of losing implementation simplicity
+and efficiency. However, the overhead brought by abstraction and a relatively
+complex design would not be a huge problem given the importance of those
+benefits. Over the recent years, there have been many new network structures
+being proposed, examined, and applied to various kinds of tasks. Given the
+trend and difficulty to hack or modify the task-specific tools, the
+benefits in generalities outweigh those concerns and are handy.
+
+There are some well-known and successful general-purpose deep learning toolkit.
+They all have their strengths and weaknesses.
+
+Theano is numerical computation library for Python. It supports mainstream
+neural network structures such as fully-connected DNN, CNN, recurrent neural
+network (RNN) and its variants like long-short term memory network (LSTM). It
+also has a short learning curve once the user get to know about the symbolic
+computation and appears to be friendly to new users. However, some concepts may
+not be very friendly to users (such as "scans"), the compilation time of
+network could be very long for complex models, Python-based environment implies
+the toolkit cannot be lightweight, and large runtime footprint makes it hard to
+port the toolkit to embedding environment (where resources are very limited).
+So here comes a strong competitor, Torch.
+
+Torch is an open source machine learning library whose initial release dates
+back to 2002. Their design goals are similar: to provide with a "MATLAB-like"
+low-level computation library that comes with separated functional blocks that
+can be used by users to build and train their own network. Torch has a steeper
+learning curve than Theano, while it is more lightweight than the latter using
+Lua as the scripting language and only implement the time-consuming operations
+in C.
+
+However, Torch is not perfect. Its limitation comes with its advantage: there
+are few general training or network building patterns inside the toolkit.
+Torch plays a role more like MATLAB, so users need to write their own code to
+put all things together: to deal with data I/O, mini-batching, training
+scheduling and so on, many of which are not a trivial task, but are repeated by
+each user in their scripts. This may lead to the phenomenon that each user has
+her own code base, and on this level, it degrades Torch to a task-specific
+tool.
+
+Imagine a user wants to build and train an state-of-the-art LSTM model for
+acoustic modeling, and she needs to read from some pre-existing feature files
+extracted by popular speech processing framework like HTK or Kaldi. She has to
+implement the data I/O all on her own. Moreover, she has to implement
+mini-batching, network unrolling, BPTT, etc., to deal with loops and schedule
+the training. What's worse, when another user wants to train a different model
+for the same task or train the same model for a different task, he has two
+choices: to write his own training script or to copy the script from the
+previous person. However, either choice is not ideal, because it turns
+scripting into reinventing the wheel or hacking other's code, which goes
+against the goal of a general-purpose toolkit. In fact, Torch seemingly goes
+towards a more distributed and isolated development style, which can ease the
+project management and collaboration, but also implies less collaboration
+because people no longer work together at all but tend to write their own
+scripts with duplicate functionalities. So there will be less and less common
+code base among users' scripts.
+
+- simplicity: the learning curve is not steep and code are straight forward
+- extensibility: users can quickly become developers and add the missing
+ modules or tailor the toolkit for their needs; major building blocks in NERV
+ are modularized and the interfaces are standardized so that users can plug-in
+ their additionally implemented ones and even use the modules implemented by others
+- lightweight: NERV strives to stay at minimal core code base and dependencies,
+ which makes it fairly easy to embed it into other task-specific tools, such
+ as Kaldi (in speech-processing).
+
diff --git a/nerv/doc/source/user.rst b/nerv/doc/source/user.rst
index 48f0c69..eb85deb 100644
--- a/nerv/doc/source/user.rst
+++ b/nerv/doc/source/user.rst
@@ -1,5 +1,7 @@
User Manual
===========
-- Overview
-- `NERV Lua Reference <lua/>`_
+.. toctree::
+
+ overview
+ NERV Lua Reference <lua/#http://>