Deep Learning is a branch of machine-learning aimed at building neural-networks to learn complex functions using special neural network architectures with many layers (hence the term "deep").

Deep neural network architectures allow for more complex tasks to be learned because, in addition to these neural networks having more layers to perform transformations, the larger number of layers and more complex architectures of the neural network allow a hierarchical organization of functionality to emerge.

Deep Learning was introduced into machine learning research with the intention of moving machine learning closer to artificial intelligence. A significant impact of deep learning lies in feature learning, mitigating much of the effort going into manual feature engineering in non-deep learning neural networks.

NOTE: If you want to use this tag for a question not directly concerning implementation, then consider posting on Cross Validated, Data Science, or Artificial Intelligence instead; otherwise your question is probably off-topic. Please choose one site only and do not cross-post to more than one - see Is cross-posting a question on multiple Stack Exchange sites permitted if the question is on-topic for each site? (tl;dr: no).

Resources

Papers

• Deep Learning in Neural Networks: An Overview

Books

• Neural Networks and Deep Learning By Michael Nielsen - this is a free book with associated Python source code on Github

• Deep Learning

• Deep Learning Made Easy with R: A Gentle Introduction For Data Science

• Deep Learning: Methods and Applications

• Autonomous Robotics and Deep Learning

• Deep Learning with Python

• Probabilistic Deep Learning with Python

Videos

• Neural Networks Demystified - accompanied by a set of Jupyter Notebooks

Stack Exchange Sites

Other StackExchange sites with Deep Learning tag:

• Cross Validated
• Data Science
• Artificial Intelligence