Labeled Memory Networks for Online Model Adaptation

Understand

Augmenting a neural network with memory that can grow without growing the number of trained parameters is a recent powerful concept with many exciting applications.

• We propose a design of memory augmented neural networks (MANNs) called Labeled Memory Networks (LMNs) suited for tasks requiring online adaptation in classification models.
• LMNs organize the memory with classes as the primary key.The memory acts as a second boosted stage following a regular neural network thereby allowing the memory and the primary network to play complementary roles.
• Unlike existing MANNs that write to memory for every instance and use LRU based memory replacement, LMNs write only for instances with non-zero loss and use label-based memory replacement.