Neuronale Netze selbst programmieren

Neural networks and the basics of artificial intelligence presented in an understandable way

This bestseller has caused a sensation because the author explains this both dry and difficult subject matter with exceptional clarity. New in the completely updated 2nd edition: The neural network is finally created with PyTorch to transfer it into a typical professional scenario.Neural networks are the basis of many applications in everyday life such as speech recognition, facial recognition on photos, the self-driving car, conversion of speech into text, etc. Neural networks are the key to many applications in the field of artificial intelligence.
Neural networks are key elements of deep learning and artificial intelligence that are capable of amazing things today. Yet few understand how neural networks actually work. This updated new edition of the bestseller takes you on an entertaining journey that starts with very simple ideas and shows you step by step how neural networks work. You don't need any in-depth knowledge of maths, as all the mathematical concepts are explained carefully and with lots of illustrations. Then it's time to put it into practice: you program your own neural network with Python and teach it to recognise handwritten numbers until it achieves optimum performance. Finally, you will create the neural network with PyTorch and get to know a professional working environment.Tariq Rashid has a special ability to explain difficult concepts in an understandable way, making neural networks accessible and practical for anyone interested.