# Numenta Research Meeting - July 15, 2020

**URL:** <https://discourse.numenta.org/t/numenta-research-meeting-july-15-2020/7732>\
**Category:** Current Research\
**Created:** [July 16, 2020, 10:31pm UTC](https://discourse.numenta.org/t/numenta-research-meeting-july-15-2020/7732 "2020-07-16T22:31:39Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Bitking](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/bitking/32/3099_2.png) [@Bitking](https://discourse.numenta.org/u/Bitking)\
**Post date:** [July 16, 2020, 10:31pm UTC](https://discourse.numenta.org/t/numenta-research-meeting-july-15-2020/7732/1 "2020-07-16T22:31:39Z")

</div>

In this research meeting Subutai and Karan focus on reviewing 4 related meta-learning papers. Subutai (after an initial surprise reveal) summarizes MAML, a core meta-learning technique, by @chelseabfinn et al, and a simpler variant, Reptile, by Alex Nichol et al. Karan reviews two probabilistic/Bayesian variants of MAML by Tom Griffiths et al.

[![](https://img.youtube.com/vi/vZ3WOnnseMY/maxresdefault.jpg "Meta-Learning Paper Reviews - July 15, 2020") ](https://www.youtube.com/watch?v=vZ3WOnnseMY)

In this research meeting Subutai and Karan focus on reviewing 4 related meta-learning papers. Subutai (after an initial surprise reveal) summarizes MAML, a core meta-learning technique, by @chelseabfinn et al, and a simpler variant, Reptile, by Alex Nichol et al. Karan reviews two probabilistic/Bayesian variants of MAML by Tom Griffiths et al. Papers: Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks,

> **[Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://arxiv.org/abs/1703.03400)**
>
> We propose an algorithm for meta-learning that is model-agnostic, in the
> sense that it is compatible with any model trained with gradient descent and
> applicable to a variety of different learning problems, including
> classification, regression, and...

On First-Order Meta-Learning Algorithms,

> **[On First-Order Meta-Learning Algorithms](https://arxiv.org/abs/1803.02999)**
>
> This paper considers meta-learning problems, where there is a distribution of
> tasks, and we would like to obtain an agent that performs well (i.e., learns
> quickly) when presented with a previously unseen task sampled from this
> distribution. We...

Recasting Gradient-Based Meta-Learning as Hierarchical Bayes,

> **[Recasting Gradient-Based Meta-Learning as Hierarchical Bayes](https://arxiv.org/abs/1801.08930)**
>
> Meta-learning allows an intelligent agent to leverage prior learning episodes
> as a basis for quickly improving performance on a novel task. Bayesian
> hierarchical modeling provides a theoretical framework for formalizing
> meta-learning as inference for...

and Reconciling meta-learning and continual learning with online mixtures of tasks.

> **[Reconciling meta-learning and continual learning with online mixtures of tasks](https://arxiv.org/abs/1812.06080)**
>
> Learning-to-learn or meta-learning leverages data-driven inductive bias to
> increase the efficiency of learning on a novel task. This approach encounters
> difficulty when transfer is not advantageous, for instance, when tasks are
> considerably...