Technical editor: Zong Enyi from sifou Office
SegmentFault has he reported the official account number: SegmentFault
In recent years, artificial intelligence technology represented by machine learning and knowledge map has gradually become popular. From license plate recognition, face recognition, speech recognition, intelligent Q & A, recommendation system to automatic driving, people may use artificial intelligence technology intentionally or unintentionally in their daily life.
These technologies are inseparable from the long-term efforts of researchers in the field of artificial intelligence. Especially in recent years, thanks to the increase of data, the enhancement of computing power, the maturity of learning algorithms and the enrichment of application scenarios, more and more people begin to pay attention to this “new” research field: deep learning.
Deep learning takes neural network as the main model, which was initially used to solve the representation learning problem in machine learning. However, due to its powerful ability, deep learning is increasingly used to solve some general AI problems, such as reasoning, decision-making and so on. At present, deep learning technology has achieved extensive success in academia and industry, received great attention, and set off a new round of artificial intelligence upsurge.
“Neural network and deep learning” is a free online book. It has moderate demand for readers’ mathematical knowledge and gives consideration to theory and practical practice. (previously, we gave the best solutions to many problems in the fields of image recognition, language recognition and natural language processing, and taught readers many core concepts behind neural networks and deep learning.
This book will teach you: neural network, a wonderful programming paradigm inspired by physics, which allows computers to learn from observed data; Deep learning is a collection of many techniques that are strong in neural network learning.
The address of the original English version of this book is:
Michael Nielsen, ⼀ bit quantity ⼦ physicist, science writer, computer programming researcher.
• Xiaohu Zhu: translate the contents of chapters 2, 3, 5 and 6 and appendices.
• Freeman Zhang: (in) translating the remaining chapters, supplementing missing contents, proofreading, sorting and typesetting.
• other contributors
Scanning the end of the two-dimensional code into WeChat official account SegmentFault backstage reply: “neural network”
You can get the Chinese PDF learning document of the latest version of Neurology and deep learning in 2020 for free.