Deep Learning with Python – François Chollet – 1st Edition

If you’ve read this book, you’re probably aware of the extraordinary progress that deep learning has brought to the field of artificial intelligence in the recent past. In just five years, we’ve gone from nearly unusable image recognition and speech transcription to superhuman performance on these tasks. The consequences of this sudden breakthrough ripple across almost every industry. But to start implementing deep learning technology into all the problems it could solve, we need to make it accessible to as many people as possible. , including non-experts, people who are not researchers or graduate students.For deep learning to reach its full potential, we need to radically democratize it.

When I released the first version of the Keras deep learning framework in March 2015, the democratization of AI was not what I had in mind. I had been doing machine learning research for several years and had created Keras to help me with my own experiments. But throughout 2015 and 2016, tens of thousands of new people entered the field of deep learning, many of them chose Keras because it was, and still is, the easiest framework to get started with.

As I watched dozens of newcomers use Keras in unexpected and powerful ways, I grew to care deeply about the accessibility and democratization of AI. I realized that the more we spread these technologies, the more useful and valuable they become. Accessibility quickly became an explicit goal in the development of Keras, and in just a few short years, the Keras developer community has made some fantastic accomplishments on this front. We have put deep learning in the hands of tens of thousands of people, who in turn are using it to solve important problems that we didn’t even know existed until recently.”