Machine Learning - Deep Learning (Network)

About

Deep Learning (Networks) is an algorithms which is basically neural networks with many layers.

Deep learning is also known as:

• deep machine learning,
• deep structured learning,
• hierarchical learning,
• or DL

Deep learning has been characterized as a buzzword, or a rebranding of neural networks.

These systems are made up of many layers with artificial neurons. Each layer learns certain properties, recognizing structure in the incoming information flow; for example vertical lines, rectangles, faces, or facial expressions. The first layers learn simple structures, while the later layers learn more complex properties on this basis.

Articles Related

Example

• Speech recognition

Library

• tensorflow (80000)
• deeplearning4j.org
• wiki/MXNet (23000)
• https://github.com/Microsoft/cntk (Microsoft Cognitive Toolkit (CNTK), an open source deep-learning toolkit )
• https://github.com/Theano/Theano (7000)
• https://github.com/lsds/Crossbow - Crossbow: A Multi-GPU Deep Learning System for Training with Small Batch Sizes - Java (34)

Others:

• Keras (layer on top of Tensorflow, Cntk or Theano)
• Python package that provides two high-level features: Tensor computation (like NumPy) with strong GPU acceleration and Deep neural networks built on a tape-based autograd system.

Course

• https://stats385.github.io/
• https://www.coursera.org/specializations/deep-learning - Based on tensforflow
• https://www.udemy.com/computer-vision-a-z/

Video

• what *is* a Neural Network? - 3Blue1Brown

Documentation / Reference

• wiki/Deep learning
• http://www.deeplearningbook.org/
• https://medium.freecodecamp.org/want-to-know-how-deep-learning-works-heres-a-quick-guide-for-everyone-1aedeca88076
• https://docs.azuredatabricks.net/applications/deep-learning/index.html