Thanks for these insights Linas and Nil. I was wondering how I could "name" the concepts, but indeed, being graphs each of them should be unique.
Regarding the monthly community call, how should I join it ? Regards Aymeric Le mardi 4 janvier 2022 à 13:38:11 UTC+1, Nil a écrit : > Hi Aymeric, > > I think you want to have a look at ROCCA > > https://wiki.opencog.org/w/ROCCA > > If possible you may join our monthly community call, next one is Friday. > > Regarding recognizing, storing and reusing abstractions, as Linas said, > the AtomSpace provides that, you don't even need to name your > abstractions due to the graphical nature of the data store. However the > more abstractions you have, the more focus you need to overcome > information overload. > > Nil > > On 1/3/22 21:08, aymeric wrote: > > > > Hello everyone, > > > > I am defining my Phd subject which will revolve around Neuro-symbolim. > > The goal would be to make an agent to learn as much knowledge as it can > > from its environement, and I found the opencog and the atomspace graph > > very interesting for the implementation. > > > > My questions might be too vague, but maybe somebody can provide an > > answer or at least some guiding ideas. > > > > How can we use the opencog system to store increasingly more complex > > concepts of the environment an agent is exploring ? Can the concepts be > > casted as atoms ? How would the relations between atoms be constructed ? > > Is there already a solution in the opencog ecosystem to store concepts > > in a hierarchical or composed manner ? (I am thinking for instance of > > the Option framework, where long sequences of actions are stored (as RL > > algos) and guided by a meta-policy, can this framework be "easily" > > implemented with opencog?). > > > > Hope my questions are a bit clear. I am reading a lot of papers now and > > it sometimes difficult to grasp all the concepts and be articulated when > > talking about them. > > > > Thanks! > > > > Aymeric > > > > -- > > You received this message because you are subscribed to the Google > > Groups "opencog" group. > > To unsubscribe from this group and stop receiving emails from it, send > > an email to [email protected] > > <mailto:[email protected]>. > > To view this discussion on the web visit > > > https://groups.google.com/d/msgid/opencog/f6de7a4a-d91c-4acb-9cf3-41dbdf27d6f2n%40googlegroups.com > > > < > https://groups.google.com/d/msgid/opencog/f6de7a4a-d91c-4acb-9cf3-41dbdf27d6f2n%40googlegroups.com?utm_medium=email&utm_source=footer > >. > -- You received this message because you are subscribed to the Google Groups "opencog" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To view this discussion on the web visit https://groups.google.com/d/msgid/opencog/40ada392-9c97-4db2-a339-4ffe658efb03n%40googlegroups.com.
