How to train your MAML

By Anonymous: https://openreview.net/forum?id=HJGven05Y7

'TL;DR: MAML is great, but it has many problems, we solve many of those problems and as a result we learn most hyper parameters end to end, speed-up training and inference and set a new SOTA in few-shot learning'

#metalearning #deeplearning #fewshotlearning

Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning

Wortsman et al.: https://arxiv.org/abs/1812.00971

#ArtificialIntelligence #DeepLearning #MetaLearning

Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning

Wortsman et al.: https://arxiv.org/abs/1812.00971

#ArtificialIntelligence #DeepLearning #MetaLearning

ProMP: Proximal Meta-Policy Search

Builds on MAML, E-MAML and DiCE.

Rothfuss et al.: https://arxiv.org/pdf/1810.06784.pdf

Code: https://github.com/jonasrothfuss/promp

#ArtificialIntelligence #DeepLearning #MachineLearning #MetaLearning #ReinforcementLearning

AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence

"We should keep in mind the grandeur of the task we are discussing, which is nothing short than the creation of an artificial intelligence smarter than humans. If we succeed, we arguably have also created life itself..."

By Jeff Clune : https://arxiv.org/abs/1905.10985

#ArtificialIntelligence #ArtificialGeneralIntelligence #MetaLearning

Meta-Learning with Implicit Gradients
Aravind Rajeswaran, Chelsea Finn, Sham Kakade, Sergey Levine : https://arxiv.org/abs/1909.04630
#MachineLearning #ArtificialIntelligence #Optimization #Control #MetaLearning

Meta-Learning with Implicit Gradients
Aravind Rajeswaran, Chelsea Finn, Sham Kakade, Sergey Levine : https://arxiv.org/abs/1909.04630
#MachineLearning #ArtificialIntelligence #Optimization #Control #MetaLearning

Notes on iMAML: Meta-Learning with Implicit Gradients
By Ferenc Huszar : https://www.inference.vc/notes-on-imaml-meta-learning-without-differentiating-through/
#ArtificialIntelligence #MetaLearning #NeuralNetworks

Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML
Raghu et al.: https://arxiv.org/abs/1909.09157
#DeepLearning #MachineLearning #MetaLearning

Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML
Raghu et al.: https://arxiv.org/abs/1909.09157
#DeepLearning #MachineLearning #MetaLearning

Learning Neural Causal Models from Unknown Interventions
Nan Rosemary Ke, Olexa Bilaniuk, Anirudh Goyal, Stefan Bauer, Hugo Larochelle, Chris Pal, Yoshua Bengio : https://arxiv.org/abs/1910.01075
#MetaLearning #ArtificialIntelligence #CausalModels

Meta-Learning Deep Energy-Based Memory Models
Bartunov et al.: https://arxiv.org/abs/1910.02720
#MachineLearning #MetaLearning #EnergyBasedMemoryModels

Learning Neural Causal Models from Unknown Interventions
Nan Rosemary Ke, Olexa Bilaniuk, Anirudh Goyal, Stefan Bauer, Hugo Larochelle, Chris Pal, Yoshua Bengio : https://arxiv.org/abs/1910.01075
#MetaLearning #MachineLearning #ArtificialIntelligence

Useful Models for Robot Learning
Slides by Marc Deisenroth : https://deisenroth.cc/talks/2019-12-14-neurips-ws.pdf
#ReinforcementLearning #Robotics #MetaLearning

How Meta-Learning Could Help Us Accomplish Our Grandest AI Ambitions, and Early, Exotic Steps in that Direction
Jeff Clune : http://www.cs.uwyo.edu/~jeffclune/share/2019_12_13_NeurIPS_Metalearning.pdf
#ArtificialGeneralIntelligence #AGI #MetaLearning

"Meta-Learning and Universality: Deep Representations and Gradient Descent can Approximate any Learning Algorithm"
Chelsea Finn and Sergey Levine : https://arxiv.org/abs/1710.11622
#MachineLearning #ArtificialIntelligence #MetaLearning #NeuralComputing

Stanford CS330: Multi-Task and Meta-Learning, 2019

Lecture videos, Finn et al.: http://youtube.com/playlist?list=PLoROMvodv4rMC6zfYmnD7UG3LVvwaITY5

#ArtificialIntelligence #DeepLearning #MetaLearning