#metalearning — Public Fediverse posts

Bayesian Meta-Learning Is All You Need

— Why is the deterministic view of meta-learning not sufficient?

— What is the variational inference?

— How can we design neural-based Bayesian meta-learning algorithms?

https://jameskle.com/writes/bayesian-meta-learning-is-all-you-need

#machinelearning #bayesian #metalearning #variational

Very interesting work by Confavreux and colleagues on #MetaLearning families of #plasticity rules in #RecurrentSpikingNetworks using simulation-based inference 👌

🌍 https://openreview.net/forum?id=FLFasCFJNo

#RSN #CompNeuro #Neuroscience #NeurIPS2023 #SynapticPlasticity #SpikingNeuronalNetwork #SNN

Very interesting work by Confavreux and colleagues on #MetaLearning families of #plasticity rules in #RecurrentSpikingNetworks using simulation-based inference 👌

🌍 https://openreview.net/forum?id=FLFasCFJNo

#RSN #CompNeuro #Neuroscience #NeurIPS2023 #SynapticPlasticity #SpikingNeuronalNetwork #SNN

Very interesting work by Confavreux and colleagues on #MetaLearning families of #plasticity rules in #RecurrentSpikingNetworks using simulation-based inference 👌

🌍 https://openreview.net/forum?id=FLFasCFJNo

#RSN #CompNeuro #Neuroscience #NeurIPS2023 #SynapticPlasticity #SpikingNeuronalNetwork #SNN

Very interesting work by Confavreux and colleagues on #MetaLearning families of #plasticity rules in #RecurrentSpikingNetworks using simulation-based inference 👌

🌍 https://openreview.net/forum?id=FLFasCFJNo

#RSN #CompNeuro #Neuroscience #NeurIPS2023 #SynapticPlasticity #SpikingNeuronalNetwork #SNN

Very interesting work by Confavreux and colleagues on #MetaLearning families of #plasticity rules in #RecurrentSpikingNetworks using simulation-based inference 👌

🌍 https://openreview.net/forum?id=FLFasCFJNo

#RSN #CompNeuro #Neuroscience #NeurIPS2023 #SynapticPlasticity #SpikingNeuronalNetwork #SNN

Rethinking the #hippocampal #cognitivemap as a #metalearning computational module – New publication by Luca Ambrogioni &
H. Freyja Ólafsdóttir (2023)

📔 https://doi.org/10.1016/j.tics.2023.05.011

#computationalneuroscience #learning

Approfondissez vos connaissances avec ces 5 ressources peu connues que j'utilise au quotidien :

- https://fmhy.pages.dev
- https://github.com/JushBJJ/Mr.-Ranedeer-AI-Tutor
- https://github.com/sindresorhus/awesome
- https://learn-anything.xyz
- https://singlelogin.re

#apprendre #metalearning #autodidacte #education

Me:
What would be the best hashtags to use for that post?

ChatGPT:
Based on the content of the post, the following hashtags may be appropriate:

#AGI #AI #ArtificialIntelligence #MachineLearning #DeepLearning #DataScience #AlphaZero #AlphaGo #MetaLearning #SelfCompetition #MultiModality #Robotics #PhysicalInteractions #Research

Through scaling #DeepNeuralNetworks we have found in two different domains, #ReinforcementLearning and #LanguageModels, that these models learn to learn (#MetaLearning).

They spontaneously learn internal models with memory and learning capability which are able to exhibit #InContextLearning much faster and much more effectively than any of our standard #backpropagation based deep neural networks can.

These rather alien #LearningModels embedded inside the deep learning models are emulated by #neuron layers, but aren't necessarily deep learning models themselves.

I believe it is possible to extract these internal models which have learned to learn, out of the scaled up #DeepLearning #substrate they run on, and run them natively and directly on #hardware.

This allows those much more efficient learning models to be used either as #LearningAgents themselves, or as a further substrate for further meta-learning.

I have an #embodiment #research on-going but with a related goal and focus specifically in extracting (or distilling) the models out of the meta-models here:
https://github.com/keskival/embodied-emulated-personas

It is of course an open research problem how to do this, but I have a lot of ideas!

If you're inspired by this, or if you think the same, let's chat!