AI is being used for scientific breakthroughs like protein folding, creating art with GANs and neural style transfer, and optimizing business logistics.
The shift to "Software 2.0" means developers will train software instead of writing explicit instructions, requiring them to handle probabilistic outputs and confidence levels.
The AWS stack is structured in three layers to cater to different skill levels, from pre-trained AI services to the comprehensive SageMaker platform and foundational infrastructure.
The project aims to use image classification to identify knitting stitch patterns from a photograph, simplifying a complex reverse-engineering problem.
An automated email pipeline using SES, Lambda, and S3 was built to crowdsource images, which were then labeled by volunteers using SageMaker Ground Truth.
After simplifying the problem to binary classification, the first model was trained using the SageMaker console, but the initial results were highly inaccurate.
Model accuracy was improved from 45% to 95% by applying data augmentation techniques, adding non-knitting "clutter" images, and running a hyperparameter tuning job.
Amazon Rekognition Custom Labels provides a simpler, managed alternative to SageMaker for building custom image classification models with a built-in UI and less expertise required.
While both services achieved comparable accuracy, SageMaker offers more control and cost-saving options for experts, whereas Rekognition prioritizes ease of use and speed for non-specialists.
39:58Linda Mohamed
57:46Adrian Schmitt
34:21Aarno Aukia
58:06Anna Fritsch-Weninger
44:11Alexandra Waldherr
58:21Julian Joseph
38:24Håkan Silfvernagel
27:23Nico Martin
Jobs that call for the skills explored in this talk.
Warmwind
LEONHARD WEISS GmbH & Co. KG
Sonarsource Sa