Fundamentals & Theoretical
-
Neural Networks and Deep Learning by Michael Nielsen.
Discuss the core principles of neural networks and deep learning; very thorough with simulation and python code examples in Github; Could take a while to read but well worth it. -
Deep Learning; MIT Press book; by Ian Goodfellow and Yoshua Bengio and Aaron Courville.
Require background in mathematics and computer science; Target audiences include university students taking machine learning courses; beginning a career in deep learning and artiļ¬cial intelligence research; software engineers with no machine learning or statistics background but
begin development using deep learning for product or platform. -
Dive into Deep Learning Online; Open Source; by Zhang et. al. Looks good but have not reviewed;
-
Courses by Andrew Ng:
-
AI for Everyone; Coursera non-technical
-
Computer Vision; lecture series;
-
Convolutional Neural Network
- Stanford CS231n - Convolutional Neural Networks for Visual Recognition
Notes; Lecture Collection Youtube
Frameworks
- Gluon MXNet - Deep Learning - The Straight Dope Online; Open Source; by Gluon MXNet Looks good with very wide topic coverage;
Blogs
- Classifying fruits with a Convolutional Neural Network in Keras; Daniel Pradilla; very thorough discussion about CNN and object recognition;