Structured Memory based Deep Model to Detect as well as Characterize Novel Inputs
This addresses the limitation of current deep learning models in replicating human-like reasoning for novel inputs, though it appears incremental as it builds on existing memory-based architectures.
The authors tackled the problem of deep models failing to handle novel inputs by designing a structured memory-based architecture that can both detect and characterize unseen categories, demonstrating its success on synthetic and real-world image datasets.
While deep learning has pushed the boundaries in various machine learning tasks, the current models are still far away from replicating many functions that a normal human brain can do. Explicit memorization based deep architecture have been recently proposed with the objective to understand and predict better. In this work, we design a system that involves a primary learner and an adjacent representational memory bank which is organized using a comparative learner. This spatially forked deep architecture with a structured memory can simultaneously predict and reason about the nature of an input, which may even belong to a category never seen in the training data, by relating it with the memorized past representations at the higher layers. Characterizing images of unseen object classes in both synthetic and real world datasets is used as an example to showcase the operational success of the proposed framework.