https://github.com/rusty1s/deep-learning-on-graphs
https://github.com/rusty1s/deep-learning-on-graphs
Last synced: over 1 year ago
JSON representation
- Host: GitHub
- URL: https://github.com/rusty1s/deep-learning-on-graphs
- Owner: rusty1s
- Created: 2016-10-01T08:56:34.000Z (almost 10 years ago)
- Default Branch: master
- Last Pushed: 2017-11-27T06:17:41.000Z (over 8 years ago)
- Last Synced: 2025-04-23T16:05:50.263Z (over 1 year ago)
- Language: TeX
- Size: 36.5 MB
- Stars: 32
- Watchers: 3
- Forks: 8
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Deep Learning
## Resources
* [Awesome Deep Vision](https://www.github.com/kjw0612/awesome-deep-vision)
* [8 Inspirational Applications of Deep Learning](http://www.machinelearningmastery.com/inspirational-applications-deep-learning)
* [Neural Networks and Deep Learning](http://www.neuralnetworksanddeeplearning.com) (Free Online Book)
* [A Guide to
Deep Learning](http://yerevann.com/a-guide-to-deep-learning/?utm_campaign=Revue%20newsletter&utm_medium=Newsletter&utm_source=revue)
* [Deep Learning Weekly](http://www.deeplearningweekly.com) (Newsletter)
* [TensorFlow](https://www.tensorflow.org) (Open Source Library)
* [TensorFlow in a Nutshell](http://camron.xyz)
* [A Year of Artificial Intelligence](https://ayearofai.com/)
* [Introduction to Convolutional Neural
Networks](http://cs.nju.edu.cn/wujx/paper/CNN.pdf)
## Python Tutorials
* [Learn Python the hard way](https://learnpythonthehardway.org/book/)
* [Style Guide](https://www.python.org/dev/peps/pep-0008/)
* [Principle component analysis in python with
matplotlib](http://blog.nextgenetics.net/?e=42)
## TensorFlow Tutorials
* [Official](https://www.tensorflow.org/versions/r0.11/tutorials/index.html)
* [Examples](https://github.com/aymericdamien/TensorFlow-Examples)
## Paper
* [A method for stochastic optimization](https://arxiv.org/pdf/1412.6980v8.pdf)
* Adam-Optimizer
* [VGG 16/19](https://arxiv.org/pdf/1409.1556v6.pdf)
* [VGG in TensorFlow](https://www.cs.toronto.edu/~frossard/post/vgg16/)
* Kontinuierliche Filter
* [Deep Function Machines: Generalized Neural Networks for Topological Layer
Expression](https://arxiv.org/pdf/1612.04799v1.pdf) (Section 4.1 und 4.2)
* CNNs auf Daten mit variierenden Größen
* [Spatial Pyramid Pooling in Deep Convolutional Networks for Visual
Recognition](https://arxiv.org/pdf/1406.4729.pdf)
* [A convolutional neraul network for modelling
sentences](https://arxiv.org/pdf/1404.2188.pdf)
* [Efficient and Scalable Computations with Sparse
Tensors](http://ieee-hpec.org/2012/index_htm_files/Baskaranpaper.pdf)
## Reduce Overfitting
* [Dropout: A Simple Way to Prevent Neural Networks from
Overfitting](https://www.cs.toronto.edu/~hinton/absps/JMLRdropout.pdf)
* L2-Regularisierung
* Batch-Normalisierung
## Data
* [CIFAR-10](http://www.cs.toronto.edu/%7Ekriz/cifar.html)
([Citation](http://www.cs.toronto.edu/%7Ekriz/learning-features-2009-TR.pdf))
* [How to
use](https://www.tensorflow.org/versions/r0.12/tutorials/deep_cnn/index.html)
* [ImageNet](http://image-net.org/)
* 224x224 klassische Größe für allgemeine Bildklassifikation
* [ILSVRC2014](http://image-net.org/challenges/LSVRC/2014/download-images-5jj5.php)
* [Random Ramblings on
ImageNet](http://peekaboo-vision.blogspot.de/2011/10/random-ramblings-on-imagenet.html)
* [PascalVOC](http://host.robots.ox.ac.uk/pascal/VOC/)
## Applications
### Object Detection
* Distance detection of objects
* Detect friends on images based on their facebook profiles
* Detect emotions from photos and represent them with an emoji
* Detect rotations/poses of objects and replace them with objects that have a similar rotation
### Vector Graphics
* Convert svgs as graphs to input them in neural networks
* Convert pixelbased images to vectorbased images
* [Fake Chine Characters in Vector Format with TensorFlow](http://blog.otoro.net/2015/12/28/recurrent-net-dreams-up-fake-chinese-characters-in-vector-format-with-tensorflow/)
* Create responsive svgs via Attention Detection (see [SVG has more potential](https://madebymike.com.au//writing/svg-has-more-potential/))
* **Comparison:** Performance and accuracy tests on different networking tasks like classification on pixelbased images and pixelbased images converted to vector graphics
### Fonts
* Font Variant Generation
* [Anaylizing 50k fonts using deep neural networks](https://erikbern.com/2016/01/21/analyzing-50k-fonts-using-deep-neural-networks/)
### Image Generation
* LowPoly Image Creation
* [Create an Image from a Sketch](https://github.com/alexjc/neural-doodle)
* [Image Analogies](https://github.com/awentzonline/image-analogies)
* [Paint Photos in Style Of Any Artist](http://www.boredpanda.com/computer-deep-learning-algorithm-painting-masters/)
* Create an image from a text (A pictures says more than thousand words)
### Graph-based image classification
* Efficiency and Performance by converting images to superpixels, segmentation graphs or svgs