Hristo Vrigazov: Multi task learning in the real world with Catalyst

Data Fest Online 2020 Catalyst Workshop Track Many realworld problems can be solved very computationally cheaply using multitask learning where we share weights between tasks and have taskspecific layers only in the final few layers of the neural network. But the complexity of managing a multitask learning project grows very quickly. Using Catalyst makes such a project much easier in the real world, and we will have a look at three different usecases and how Catalyst was used to greatly ease the training, evaluation, interpretation and tuning of the results in a multitask setting. Register and get access to the tracks: Join the community: