An orchard desk has still photos of leaf spots, a river desk has hourly gauge readings, and a permits desk has long statutes whose early clause changes a later one. Which deep-learning families match those data shapes?

Still photos of leaf spots want convolutional nets. Hourly gauge readings want recurrent nets. Long statutes whose early clause changes a later one want transformers. Match the family to the data shape; do not reverse them or turn this into a training-job tune-up.