- “Maker Faire Rome – The European edition” returns to the Gazometro OstiensePosted 13 hours ago
- Single-chip saturation meterPosted 4 weeks ago
- Raspberry Pi Relay BoardPosted 2 months ago
- PCB CAD, A SELECTION GUIDEPosted 3 months ago
- Automatic dispenser for catsPosted 3 months ago
- Do you have a mask? RASPBERRY Pi SEES ITPosted 3 months ago
- RFID based Attendance system using Arduino and External EEPROMPosted 4 months ago
- ESP32 Neopixel Status Indicator and Sensor PCB Shield with Wi-Fi ManagerPosted 4 months ago
- Remote control power functions usbPosted 4 months ago
- ESP32-CAM with Telegram: Take Photos Control Outputs Sensor Readings and Motion NotificationsPosted 4 months ago
What Neural Networks/Deep Learning Books Should I Read?
There are lots of deep learning books on the market and is a common question for who want to start to understand somethings.
In this post, we collect some info, and please leave your comment and suggestion for other books. ;-)
Free ebook to learn Neural Networks/Deep Learning
- The Michael Nielsen online text is very well-regarded. It covers some interesting topics including the universal approximation proof: http://neuralnetworksanddeeplearning.com
- When it comes to the mathematical background, Deep Learning Book by Ian Goodfellow et al. is a great starting point, giving a lot of overviews. Though, it requires a lot of interest in maths. Convolutional networks start well after page 300.
- The book is not intended to cover advanced machine learning techniques because there are already plenty of books doing this. Instead, we aim to provide the necessary mathematical skills to read those other books. https://mml-book.github.io/
- This is also useful, but harder to read: https://web.stanford.edu/~hastie/Papers/ESLII.pdf
- It is a little old given how quickly the field moves, but ‘Information Theory, Inference and Learning Algorithms’ has a chapter on neural networks. It is an outstanding book: a labour of love from a very smart person. The exercises are varied, explanations are great, there’s a sprinkling of humor, and connections drawn between multiple fields of study. Moreover, it is freely available from the author’s website: http://www.inference.org.uk/itprnn/book.html
- Stanford’s CS231n (http://cs231n.stanford.edu) for Computer Vision
- Stanford’s CS224n (http://web.stanford.edu/class/cs224n/) for NLP
- Numerical Algorithms introduces the skills necessary to be both clients and designers of numerical methods for computer science applications. This text is designed for advanced
undergraduate and early graduate students who are comfortable with mathematical notation and formality but need to review continuous concepts alongside the algorithms under
Ebook to learn Neural Networks/Deep Learning
- Neural Networks and Deep Learning: A Textbook by Charu Aggarwal
The author (from IBM Watson Research center) also has written several other books on related domains.
- This book (hence no DL) is very good to really understand the intuition behind ANNs:
Neural Networks for Applied Sciences and Engineering: From Fundamentals to Complex Pattern Recognition by Sandhya Samarasinghe
- Another recommendation is Deep Learning in Python by François Chollet (the Keras author).