Back in the 1990s, network topologies like Bidirectional Associative Memory and Hopfield Nets were all the rage. Largely, these were billed as having energy states and recurrents that would help them learn/store and recall specific patterns readily.

These topologies are perhaps less pertinent now, but I'm wondering if they are still an optimal way to approach data mining? They seem like they would be pertinent for things like contextual analysis in NLP, with a network trained to observe what it has "seen" before. Will these topologies come back in, or have they been replaced by options with better accuracy rates?


1 Answer 1


Things have evolved, not necessarily changed. Now there is great emphasis in Boltzmann Machines (BMs) and Restricted Boltzmann Machines (RBMs) that are stochastic, generative counterparts to Hopfield networks. It would also be important to mention Markov Random Fields (MRFs) in this list although it is a relatively more general concept. Boltzmann Machines have received a lot attention recently because they are an important building block for Deep Learning.

So, to answer your question, are they pertinent? Yes, definitely. Are things the same than back in the 90s? No, absolutely not, things have evolved quite a bit.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.