Deep Learning for Computer Vision

Alex Conway (@alxcnwy)

Alex is the founder & CTO of NumberBoost, a startup that builds deep learning applications. He previously worked as a quant for a hedge fund and as a data scientist for an e-commerce company. He has an honours degree in actuarial science and a MSc in statistics. He is one of the organizers of the Cape Town Deep Learning meet-up and has built numerous computer vision systems that run at scale in production predicting labels for millions of images per day.


Tags: business data-science use-case deep learning ai machine learning

The state-of-the-art in image classification has skyrocketed thanks to the development of deep convolutional neural networks and increases in the amount of data and computing power available to train them. The top-5 error rate in the ImageNet competition to predict which of 1000 classes an image belongs to has plummeted from 28% error in 2010 to just 2.25% in 2017 (human level error is around 5%).

In addition to being able to classify objects in images (including not hotdogs), deep learning can be used to automatically generate captions for images, convert photos into paintings, detect cancer in pathology slide images, and help self-driving cars ‘see’.

The talk will give an overview of the cutting edge and some of the core mathematical concepts and will also include a short code-first tutorial to show how easy it is to get started using deep learning for computer vision in python…


This talk is a crash course on convolutional neural networks and how to use them to solve 2 real-world applications at scale. The first is an image moderation system and the second is a visual similarity system where a user uploads an image of an item and the system returns visually similar items.