Hidden Difficulties in Building Deep Learning Models and How to Resolve Them
As deep learning gains momentum in its application to business, an end-to-end approach where the model handles everything from the input data to the output predictions, seems very attractive. There are plenty of available resources on deep learning projects that focus on the model building aspect of deep learning. But in order to build an effective deep learning model, numerous crucial small obstacles often get overlooked. At LV=, we are currently investigating the power of deep learning to understand from images whether a car is repairable or if it should be over-written, to improve our decision making. This talk will take a deep dive on the problems that we have encountered when building convolutional neural networks, and our approach to solve them.
Dapeng Wang is a Data Scientist at the insurance company LV=. He graduated in maths from the University of Cambridge and has an MSc from the University of Sussex. At LV=, Dapeng is leading in the adoption of Deep Learning across the company. He is currently developing the end to end pipeline to build and integrate Deep Learning within current LV= processes. Dapeng is also a frequent Kaggle competitor and Kaggle competition expert. Dapeng looks forward to using his experience to help the deep learning community find suitable and better implementation solutions for deep learning.