As others have said, this is the way ML is headed and it has been clear for the last couple of years.
Assuming a multi-task and multi-modal architecture is achievable, won't we reach a point in the future where preprocessing data is just as difficult as the machine learning component? Today, the input to ML models is almost always carefully curated and processed.
Assuming a multi-task and multi-modal architecture is achievable, won't we reach a point in the future where preprocessing data is just as difficult as the machine learning component? Today, the input to ML models is almost always carefully curated and processed.