인생의 문제를 초월했다는 듯

우리는 곧잘 노 프라블럼이라고 말한다.

그러나 그 노 프라블럼의 기준을 '나'에서

'타인'으로, 나 아닌 다른 존재로 전환하지 않는다면

그것이야말로 '빅 프라블럼'(Big problem)이다.

자기 중심에만 머물러 있는 관점은

결코 노 프라블럼일 수가 없다.

- 류시화의《새는 날아가면서 뒤돌아보지 않는다》중에서 - 

* 사람은 모든 상황을 자기 중심,

자기 관점에서만 인식하고 해석하려는 경향이 있습니다.

자기중심에서 문제를 인식하고 해결하려고 하지 말고

나를 둘러싼 타인 관점에서 보면 문제가 없던 것도

문제가 있을 수 있습니다. 다른 사람의 관점에서도 

상황을 인식하고 해결하려는 노력이 필요합니다.

세상 문제를 '나의 관점'에서 '우리의 관점'으로

바라보는 사람들이 더 많아졌으면 좋겠습니다.

.

TensorFlow-Tutorials

Introduction to deep learning based on Google's TensorFlow framework. These tutorials are direct ports of Newmu's Theano Tutorials.

Topics

• Simple Multiplication
• Linear Regression
• Logistic Regression
• Feedforward Neural Network (Multilayer Perceptron)
• Deep Feedforward Neural Network (Multilayer Perceptron with 2 Hidden Layers O.o)
• Convolutional Neural Network
• Denoising Autoencoder
• Recurrent Neural Network (LSTM)
• Word2vec
• TensorBoard
• Save and restore net
• Generative Adversarial Network

Dependencies

• TensorFlow 1.0 alpha
• Numpy
• matplotlib

# TensorFlow-Tutorials

[](https://travis-ci.org/nlintz/TensorFlow-Tutorials)

[](https://www.codacy.com/app/hunkim/TensorFlow-Tutorials)

Introduction to deep learning based on Google's TensorFlow framework. These tutorials are direct ports of

Newmu's [Theano Tutorials](https://github.com/Newmu/Theano-Tutorials).

***Topics***

* [Simple Multiplication](00_multiply.py)

* [Linear Regression](01_linear_regression.py)

* [Logistic Regression](02_logistic_regression.py)

* [Feedforward Neural Network (Multilayer Perceptron)](03_net.py)

* [Deep Feedforward Neural Network (Multilayer Perceptron with 2 Hidden Layers O.o)](04_modern_net.py)

* [Convolutional Neural Network](05_convolutional_net.py)

* [Denoising Autoencoder](06_autoencoder.py)

* [Recurrent Neural Network (LSTM)](07_lstm.py)

* [Word2vec](08_word2vec.py)

* [TensorBoard](09_tensorboard.py)

* [Save and restore net](10_save_restore_net.py)

* [Generative Adversarial Network](11_gan.py)

***Dependencies***

* TensorFlow 1.0 alpha

* Numpy

* matplotlib

.

요즘 세상은 더 이상 혼자 살수 없는 시대다.

과거에는 누구에게 ‘의존적’이라는 말이

굴욕적인 뜻이었는데 지금은 반대다.

가장 진취적인 말이 됐다.

- 고은 시인

혼자 힘으로는 살아갈 수 없는 시대가 되었습니다.

남과 더불어 협력해서 살아가야만 하는 시대입니다.

남에게 의존하는 만큼 남이 나에게 의존할 수 있도록

서로 서로 먼저 손을 내미는 따뜻한 사회가 될 수 있기를 희망합니다.

.

그들의 분노는 

바로 자기 자신의 분노라고 그는 말했다. 

비록 그 분노에서 영원히 벗어날 수는 없지만, 

기도를 통해서 분노를 억제하는 법을 배웠다고 했다. 

그리고 그 분노를 자기 아이들에게는 물려주지 

않으려고 애써왔다고 했다.

- 버락 오바마의《내 아버지로부터의 꿈》중에서 -

* 사람은 분노 속에 살아갑니다.

스파크처럼 일어나는 작은 분노, 큰 분노...

그 크고 작은 분노를 어떻게 다스리냐가 관건입니다.

자칫 들불로 번져 산야를 태우고 검은 잿더미를

대물림하게 됩니다. 기도와 명상은 

분노를 다스리는 명약입니다.

평화로 가는 길입니다.

https://www.tensorflow.org/api_docs/python/tf/compat

Module: tf.compat

scikit-learn: machine learning in Python http://scikit-learn.org

https://github.com/scikit-learn/scikit-learn

scikit-learn

scikit-learn is a Python module for machine learning built on top of SciPy and distributed under the 3-Clause BSD license.

The project was started in 2007 by David Cournapeau as a Google Summer of Code project, and since then many volunteers have contributed. See the AUTHORS.rst file for a complete list of contributors.

It is currently maintained by a team of volunteers.

Website: http://scikit-learn.org

Installation

Dependencies

scikit-learn requires:

• Python (>= 2.7 or >= 3.3)
• NumPy (>= 1.6.1)
• SciPy (>= 0.9)

For running the examples Matplotlib >= 1.1.1 is required.

scikit-learn also uses CBLAS, the C interface to the Basic Linear Algebra Subprograms library. scikit-learn comes with a reference implementation, but the system CBLAS will be detected by the build system and used if present. CBLAS exists in many implementations; see Linear algebra libraries for known issues.

User installation

If you already have a working installation of numpy and scipy, the easiest way to install scikit-learn is using pip

pip install -U scikit-learn

or conda:

conda install scikit-learn

The documentation includes more detailed installation instructions.

Development

We welcome new contributors of all experience levels. The scikit-learn community goals are to be helpful, welcoming, and effective. The Development Guide has detailed information about contributing code, documentation, tests, and more. We've included some basic information in this README.

Important links

• Official source code repo: https://github.com/scikit-learn/scikit-learn
• Download releases: https://pypi.python.org/pypi/scikit-learn
• Issue tracker: https://github.com/scikit-learn/scikit-learn/issues

Source code

You can check the latest sources with the command:

git clone https://github.com/scikit-learn/scikit-learn.git

Setting up a development environment

Quick tutorial on how to go about setting up your environment to contribute to scikit-learn: https://github.com/scikit-learn/scikit-learn/blob/master/CONTRIBUTING.md

Testing

After installation, you can launch the test suite from outside the source directory (you will need to have the nose package installed):

nosetests -v sklearn

Under Windows, it is recommended to use the following command (adjust the path to the python.exe program) as using the nosetests.exe program can badly interact with tests that use multiprocessing:

C:\Python34\python.exe -c "import nose; nose.main()" -v sklearn

See the web page http://scikit-learn.org/stable/developers/advanced_installation.html#testing for more information.

Random number generation can be controlled during testing by setting the SKLEARN_SEED environment variable.

Submitting a Pull Request

Before opening a Pull Request, have a look at the full Contributing page to make sure your code complies with our guidelines: http://scikit-learn.org/stable/developers/index.html

Project History

The project was started in 2007 by David Cournapeau as a Google Summer of Code project, and since then many volunteers have contributed. See the AUTHORS.rst file for a complete list of contributors.

The project is currently maintained by a team of volunteers.

Note: scikit-learn was previously referred to as scikits.learn.

Help and Support

Documentation

• HTML documentation (stable release): http://scikit-learn.org
• HTML documentation (development version): http://scikit-learn.org/dev/
• FAQ: http://scikit-learn.org/stable/faq.html

Communication

• Mailing list: https://mail.python.org/mailman/listinfo/scikit-learn
• IRC channel: #scikit-learn at webchat.freenode.net
• Stack Overflow: http://stackoverflow.com/questions/tagged/scikit-learn
• Website: http://scikit-learn.org

Citation

If you use scikit-learn in a scientific publication, we would appreciate citations: http://scikit-learn.org/stable/about.html#citing-scikit-learn

.