notebooks/bayesian_linear_regression.ipynb at master · liviu-/notebooks · GitHub

Quick demonstration of Bayesian linear regression #MachineLearning liviu-/notebooks  #Bayes

  • liviu- Elaborate a bit on adding a constant to a Gaussian r.v.
  • We recommend upgrading to the latest Internet Explorer , Google Chrome , or Firefox .
  • If you are using IE 11, make sure you turn off “Compatibility View” .
  • Personal Open source Business Explore
  • Issues 0 Pull requests 0 Projects 0 Pulse Graphs

Directory of Jupyter notebooks exploring various topics
Continue reading “notebooks/bayesian_linear_regression.ipynb at master · liviu-/notebooks · GitHub”

predict/Geoscience_Machine_Learning_notebook_1.ipynb at master · mycarta/predict · GitHub

And here's the first Jupyter Notebook in the Geoscience Machine Learning series:

  • Please note that GitHub no longer supports old versions of Internet Explorer.
  • If you are using IE 11, make sure you turn off “Compatibility View” .
  • We recommend upgrading to the latest Internet Explorer , Google Chrome , or Firefox .
  • Personal Open source Business Explore
  • Issues 0 Pull requests 0 Projects 0 Pulse Graphs

Contribute to predict development by creating an account on GitHub.
Continue reading “predict/Geoscience_Machine_Learning_notebook_1.ipynb at master · mycarta/predict · GitHub”

GitHub

Nice #GitHub project: Deep Q-learning for Super #Mario Bros. #DeepLearning #MachineLearning

  • Please note that GitHub no longer supports old versions of Internet Explorer.
  • A modification of Google’s Deep Q-Network to learn to play Super Mario Bros.
  • For instructions and a summary of changes to the original Google project, please see this blog post.
  • We recommend upgrading to the latest Internet Explorer , Google Chrome , or Firefox .
  • It uses a double deep Q network to control an open-source Nintendo Entertainment System emulator called FCEUX.

Read the full article, click here.


@randal_olson: “Nice #GitHub project: Deep Q-learning for Super #Mario Bros. #DeepLearning #MachineLearning”


DeepQNetwork – A modification of Google’s Deep Q-Network to learn to play Super Mario Bros.


GitHub

GitHub

Very simple implementation of Neural Algorithm of the Artistic Style in #Tensorflow  #python

  • {top,center,bottom,left,right} specify how to crop the style image to obtain an image of the same size as the content image
  • In the examples below I used content image as an initialization, it seems to provide more consistent image, but in the code, you can switch easily to noise initialization on line 109 in style.py .
  • content_scale specifies scale factor that is applied to the input content image.
  • style_weight is a number between 0-1 that specifies emphasis on the style.
  • Please note that GitHub no longer supports old versions of Internet Explorer.

Read the full article, click here.


@alxndrkalinin: “Very simple implementation of Neural Algorithm of the Artistic Style in #Tensorflow #python”


Contribute to Artistic-Style development by creating an account on GitHub.


GitHub

GitHub

  • Weights are automatically downloaded if necessary, and cached locally in ~/.keras/models/ .
  • For instance, if you have set image_dim_ordering=tf , then any model loaded from this repository will get built according to the TensorFlow dimension ordering convention, “Width-Height-Depth”.
  • Note that using the models requires the latest version of Keras (from the Github repo, not PyPI).
  • All architectures are compatible with both TensorFlow and Theano, and upon instantiation the models will be built according to the image dimension ordering set in your Keras configuration file at ~/.keras/keras.json .
  • Weights can be automatically loaded upon instantiation ( weights=’imagenet’ argument in model constructor).

Read the full article, click here.


@fchollet: “I made available VGG16, VGG19, ResNet50: Keras code +ImageNet weights for both TF and Theano.”


deep-learning-models – Keras code and weights files for popular deep learning models.


GitHub

GitHub

Collection of #DeepLearning tutorials

  • Week6 – Deep learning is so FUN!
  • Please note that GitHub will soon be dropping support for Internet Explorer 10.
  • Failed to load latest commit information.
  • We recommend upgrading to the latest Internet Explorer , Google Chrome , or Firefox .
  • If you are using IE 11, make sure you turn off “Compatibility View” .

Read the full article, click here.


@kdnuggets: “Collection of #DeepLearning tutorials”


dl_tutorials – Deep learning tutorials (2nd ed.)


GitHub

GitHub

Introduction to Deep Learning for Image Recognition - SciPy US 2016 w/ slides |

  • The notebook accompanies the Introduction to Deep Learning for Image Recognition workshop to explain the core concepts of deep learning with emphasis on classifying images as the application.
  • The slides used for the workshop are available
  • Python data stack is used for the workshop.
  • Unsupervised learning using Autoencoders
  • Depending on time, the following topics might be covered

Read the full article, click here.


@YhatHQ: “Introduction to Deep Learning for Image Recognition – SciPy US 2016 w/ slides |”


scipyUS2016_dl-image – Introduction to Deep Learning for Image Recognition – SciPy US 2016


GitHub