Timezone: »

 
Poster
BayesPCN: A Continually Learnable Predictive Coding Associative Memory
Jinsoo Yoo · Frank Wood

Wed Nov 30 02:00 PM -- 04:00 PM (PST) @ Hall J #424
in Poster Session 4 »
Associative memory plays an important role in human intelligence and its mechanisms have been linked to attention in machine learning. While the machine learning community's interest in associative memories has recently been rekindled, most work has focused on memory recall ($read$) over memory learning ($write$). In this paper, we present BayesPCN, a hierarchical associative memory capable of performing continual one-shot memory writes without meta-learning. Moreover, BayesPCN is able to gradually forget past observations ($forget$) to free its memory. Experiments show that BayesPCN can recall corrupted i.i.d. high-dimensional data observed hundreds to a thousand ``timesteps'' ago without a large drop in recall ability compared to the state-of-the-art offline-learned parametric memory models.
Keywords: bayesian inference · associative memory · machine learning · continual learning · predictive coding

Author Information

Jinsoo Yoo (University of British Columbia)

I'm an undergraduate student from the University of British Columbia working with Dr. Frank Wood on Automated Machine Learning. I love following new research and looking at machine learning memes.

Frank Wood (University of British Columbia)

More from the Same Authors