Sunday 10:00–10:45 in Auditorium
A Gentle Introduction to Neural Networks (and making your own with Python)
Tariq Rashid
- Audience level:
- Novice
Description
Neural networks are not only a powerful data science 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. You won't need anything more than basic school maths. We'll gently build our own neural network in Python too.
Abstract
Ideas: - search for intelligence machines, what's easy for us not easy for computers - pigeon and worm brains few neutrons but impressively capable - biologically inspired computing - simple function -> classifier -> iterative refinement - problems that need more nodes (XOR) -> many nodes - how to train - gently explain backdrop
DIY: - MINST dataset - simple network 3 layer - matrix multiplication to aid calculations - preprocessing, priming weights - 95% accuracy with very simple code! - improvements lead to 98% accuracy!
source code will be online Python 3 notebook on makeyourownneuralnetwork.blogspot.com and @myoneuralnet
Sponsors
