Sivan Doveh - Meta-learning: few-shot learning and neural architecture search
Details
Sivan Doveh, Student Researcher @IBM
Abstract: Few-Shot Learning (FSL) is a topic of rapidly growing interest. Typically, in FSL a model is trained on a dataset consisting of many small tasks (meta-tasks) and learns to adapt to novel tasks that it will encounter during test time. This is also referred to as meta-learning. Another topic also referred to as meta-learning is Neural Architecture Search (NAS), automatically finding optimal architecture instead of engineering it manually.
In this talk, first, we will go over these two subjects. Next, we will show our work where we combine those aspects of meta-learning.
In our work, we propose to employ tools inspired by the Differentiable Neural Architecture Search (D-NAS) literature in order to optimize the architecture for FSL. Additionally, to make the architecture task adaptive, we propose the concept of `MetAdapt Controller' modules. These modules are added to the model and are meta-trained to predict the optimal network connections for a given novel task.
Join Zoom Meeting
https://zoom.us/j/6043600514?pwd=VTFuU2VSTTNhTE1RRFJTZjhZNTN1Zz09
Meeting ID: 604 360 0514
Password: 703769