A Mindmap summarising Deep Learning concepts, Architectures, and the Tensorflow library.
Deep Learning is part of a broader family of Machine Learning methods based on learning data representations, as opposed to task-specific algorithms. Learning can be supervised, partially supervised, or unsupervised. This is an attempt to summarize this large field in one .PDF file.
Here's another mindmap which focuses on Machine Learning basics and Data Science.
Download the PDF here:
I've built the mindmap with MindNode for the Mac. https://mindnode.com
A partial list of the building blocks of Deep Learning architectures, with notes on the mathematics behind each component.
Different Deep Learning architectures have been developed depending on the question being answered. Here's a list of some of them and notes on tuning.
TensorFlow is an open source software library for numerical computation using data flow graphs. The mindmap lists some of its components, packages, and overall architecture.
I'm planning to built a more complete list of references in the future. For now, these are some of the sources I've used to create this Mindmap.
- Stanford and Oxford Lectures. CS20SI, CS224d.
- Books:
- Deep Learning - Goodfellow.
- Pattern Recognition and Machine Learning - Bishop.
- The Elements of Statistical Learning - Hastie.
- Colah's Blog. http://colah.github.io
- Kaggle Notebooks.
- Tensorflow Documentation pages.
- Google Cloud Data Engineer certification materials.
- Multiple Wikipedia articles.
Twitter:
Linkedin:
Email: