Choosing the problem task
What are the core classes of problem?
Before collecting any data at all it is worth carefully considering what kind of question you are hoping to answer with your experiment. Three very common types of problem that can be tackled using deep learning are classification, regression and segmentation.
Classification applies a text label to an image (e.g. “Diseased”).
Regression is tasked with predicting a number from an image or area of an image (e.g.. “Amount of disease”)
Segmentation problems need areas of an image marking (e.g. labelling the pixels covered by diseased patches).
Experimental Design for Machine Learning
Reach your personal and professional goals
Unlock access to hundreds of expert online courses and degrees from top universities and educators to gain accredited qualifications and professional CV-building certificates.
Join over 18 million learners to launch, switch or build upon your career, all at your own pace, across a wide range of topic areas.
