Thursday 14:00 - 14:45
Session type: Lecture
Session level: Suitable for all
A Gentle Introduction to Neural Networks
Neural networks are not only a powerful machine learning tool, they’re at the heart of recent breakthroughs in deep learning and artificial intelligence. This talk, designed for a complete beginners and anyone non-technical, will introduce the history and ideas behind neural networks, in a fun and informal way.
We’ll progress from asking why humans are better at image recognition than computers, to understanding how the learning inside neural networks actually happens. We’ll also see how to make a useful neural network using only basic Python, and teach it to recognise human hand written digits. There will even be a live demo! By the end of the talk, you should have an intuition for how neural networks actually work, and enough basics to make your own useful networks in any programming language, and to more confidently progress onto popular machine learning frameworks like TensorFlow and PyTorch. Videos, slides, data, code, guest posts and more discussion are on the blog http://makeyourownneuralnetwork.blogspot.com
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 public libraries near his home, 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 is active in London’s tech scene, and until recently led the London Python meetup group, doubling its membership to 4000. Whenever he can, he loves organising community events, teaching and mentoring. He loves open source, and was lucky enough to lead on open source reform for the UK Government.
His current focus is the London Algorithmic Art community, and his next book on creative coding. It’s sometimes hard to tell, but he has a masters degree in machine learning and data mining, and started using Python in the last century.