Make Your Own Neural Network by Tariq Rashid

Make Your Own Neural Network by Tariq Rashid

Regular price
Checking stock...
Regular price
Checking stock...
Proud to be B-Corp

Our business meets the highest standards of verified social and environmental performance, public transparency and legal accountability to balance profit and purpose. In short, we care about people and the planet.

The feel-good place to buy books
  • Free delivery in the UK
  • Supporting authors with AuthorSHARE
  • 100% recyclable packaging
  • B Corp - kinder to people and planet
  • Buy-back with World of Books - Sell Your Books

Make Your Own Neural Network by Tariq Rashid

A step-by-step gentle journey through the mathematics of neural networks, and making your own using the Python computer language. Neural networks are a key element of deep learning and artificial intelligence, which today is capable of some truly impressive feats. Yet too few really understand how neural networks actually work. This guide will take you on a fun and unhurried journey, starting from very simple ideas, and gradually building up an understanding of how neural networks work. You won't need any mathematics beyond secondary school, and an accessible introduction to calculus is also included. The ambition of this guide is to make neural networks as accessible as possible to as many readers as possible - there are enough texts for advanced readers already You'll learn to code in Python and make your own neural network, teaching it to recognise human handwritten numbers, and performing as well as professionally developed networks. Part 1 is about ideas. We introduce the mathematical ideas underlying the neural networks, gently with lots of illustrations and examples. Part 2 is practical. We introduce the popular and easy to learn Python programming language, and gradually builds up a neural network which can learn to recognise human handwritten numbers, easily getting it to perform as well as networks made by professionals. Part 3 extends these ideas further. We push the performance of our neural network to an industry leading 98% using only simple ideas and code, test the network on your own handwriting, take a privileged peek inside the mysterious mind of a neural network, and even get it all working on a Raspberry Pi. All the code in this has been tested to work on a Raspberry Pi Zero.
Rashid, Tariq: - Ever since he was a kid, Tariq has loved the beauty and excitement of science, maths and computing. He devoured everything he could get his hands on in the libraries near his home, in England, especially books on fractals and programming the BBC micro ... this was a long time before the world wide web! Despite all the fun and adventures over the 30 years since then, he still thinks too many amazing ideas are badly explained. His personal mission is to do the hard work to make beautiful exciting ideas simple and accessible enough for anyone to understand and appreciate. He has a degree in Physics, a Masters in Machine Learning and Data Mining, is active in London's tech scene, leads the London Python meetup group (almost 3000 members) and loves doing talks/workshops whenever he can. For a day job, he works mostly in technology and digital strategy, but really he's trying to introduce design thinking. He loves open source, and was lucky enough to lead on open source reform for the UK Government. He leads the beginner-friendly London Algorithmic Art community which meets monthly to explore a very broad range of topics from algorithmic music, coding tutorials to computer graphics technologies. He's been lucky to have taught undergraduate students creative coding, where he learned more than they did. More importantly, he has an amazing wife and a cute clever daughter who seems to have inherited the genes for loving art from both parents.
SKU Nicht verfügbar
ISBN 13 9781530826605
ISBN 10 1530826608
Titel Make Your Own Neural Network
Autor Tariq Rashid
Buchzustand Nicht verfügbar
Bindungsart Paperback
Verlag Createspace Independent Publishing Platform
Erscheinungsjahr 2016-03-31
Seitenanzahl 224
Hinweis auf dem Einband Die Abbildung des Buches dient nur Illustrationszwecken, die tatsächliche Bindung, das Cover und die Auflage können sich davon unterscheiden.
Hinweis Nicht verfügbar