Numenta Research Meeting - August 5, 2020


In a follow-up to Monday’s research meeting on continuous learning models, today Karan reviewed a paper from 1991 that looks to be one of the first papers to reference sparse representations in continuous learning.

In our previous research meeting, Subutai reviewed three different papers on continuous learning models. In today’s short research meeting, Karan reviews a paper from 1991 that he points out was referenced by all three. The paper, “Using Semi-Distributed Representations to Overcome Catastrophic Forgetting in Connectionist Networks,” was one of the first papers to reference sparse representations in continuous learning.

Using Semi-Distributed Representations to Overcome Catastrophic Forgetting in Connectionist Networks Robert M. French

License
Creative Commons Attribution license (reuse allowed)

1 Like