Using Fast Weights to Deblur Old Memories
نویسندگان
چکیده
Connectionist models usually have a single weight on each connection. Some interesting new properties emerge if each connection has two weights: A slowly changing, plastic weight which stores long-term knowledge and a fast-changing, elastic weight which stores temporary knowledge and spontaneously decays towards zero. If a network learns a set of associations and then these associations are "blurred" by subsequent learning, all the original associations can be "deblurred" by rehearsing on just a few of them. The rehearsal allows the fast weights to take on values that temporarily cancel out the changes in the slow weights caused by the subsequent learning.
منابع مشابه
Fast Weight Long Short-term Memory
Associative memory using fast weights is a short-term memory mechanism that substantially improves the memory capacity and time scale of recurrent neural networks (RNNs). As recent studies introduced fast weights only to regular RNNs, it is unknown whether fast weight memory is beneficial to gated RNNs. In this work, we report a significant synergy between long short-term memory (LSTM) networks...
متن کاملUsing Fast Weights to Attend to the Recent Past
Until recently, research on artificial neural networks was largely restricted to systems with only two types of variable: Neural activities that represent the current or recent input and weights that learn to capture regularities among inputs, outputs and payoffs. There is no good reason for this restriction. Synapses have dynamics at many different time-scales and this suggests that artificial...
متن کاملLearning to Control Fast-Weight Memories: An Alternative to Dynamic Recurrent Networks
Previous algorithms for supervised sequence learning are based on dynamic recurrent networks. This paper describes alternative gradient-based systems consisting of two feed-forward nets which learn to deal with temporal sequences by using fast weights: The rst net learns to produce context dependent weight changes for the second net whose weights may vary very quickly. The method o ers a potent...
متن کاملDeblur Rapidly Resolves Single-Nucleotide Community Sequence Patterns
High-throughput sequencing of 16S ribosomal RNA gene amplicons has facilitated understanding of complex microbial communities, but the inherent noise in PCR and DNA sequencing limits differentiation of closely related bacteria. Although many scientific questions can be addressed with broad taxonomic profiles, clinical, food safety, and some ecological applications require higher specificity. He...
متن کاملGated Fast Weights for Associative Retrieval
We improve previous end-to-end differentiable neural networks (NNs) with fast weight memories. A gate mechanism updates fast weights at every time step of a sequence through two separate outer-product-based matrices generated by slow parts of the net. The system is trained on a complex sequence to sequence variation of the Associative Retrieval Problem with roughly 70 times more temporal memory...
متن کامل