Questions tagged [meta-learning]

For questions related to the concept of meta-learning (or learning-to-learn).

Filter by
Sorted by
Tagged with
1
vote
0answers
39 views

Why doesn't anyone use reinforcement learning to find the best possible alternative to backpropagation?

To be clear, I'm very uninformed on the topic of alternative learning algorithms to backprop, all my knowledge comes from articles like these: lets-not-stop-at-backprop backprop-alternatives we-need-a-...
1
vote
0answers
12 views

What's mutual exclusivity in meta-learning?

What do we mean by mutual exclusivity of tasks? This work (E Pan, 21) and this one (M Yin, 20) state that most classification meta-learning algorithms fail for non-mutually exclusive tasks as the ...
0
votes
0answers
18 views

Is there a different approach, other than MAML combined with LSTM, for meta-regression of time-series data?

I am working on the calibration of low-cost air sensor data (a time series regression problem). My primary focus is to use some meta/ few-shot learning approach to solve this problem with fewer data. ...
1
vote
1answer
33 views

How to split data for meta-learning?

I've been trying to understand the meta-learning paradigm, more precisely, the optimization-based models, such as MAML, but I have a hard time understanding how I should correctly split my data to ...
0
votes
0answers
23 views

Should I use the Siamese or the matching network to find the closest match between one image and other images?

I have to find the closest match between my image and a bunch of already collected images of different classes in the folder. Which of the meta-learning approach should I select? I am thinking about ...
0
votes
1answer
23 views

Which meta-learning approach selection methodology should I use for similarity learning of an image?

Meta-learning has 3 broad approaches: model, metric and optimization-based approach. Each of them has its own sub-approach, like matching network, meta-agonistic and Siamese-based network, and so on. ...
2
votes
1answer
62 views

What is $ \nabla_{\theta_{k-1}} \theta_{k}$ in the context of MAML?

I am attempting to fully understand the explicit derivation and computation of the Hessian and how it is used in MAML. I came across this blog: https://lilianweng.github.io/lil-log/2018/11/30/meta-...
2
votes
0answers
57 views

In few-shot classification, should I use my custom dataset as the validation dataset and mini-ImageNet as the training dataset?

I am new to few-shot learning, and I wanted to get a hands-on understanding of it, using Reptile algorithm, applied to my custom dataset. My custom dataset has 30 categories, with 5 images per ...
2
votes
0answers
36 views

What exactly does meta-learning in reinforcement learning setting mean?

We can use DDPG to train agents to stack objects. And stacking objects can be viewed as first grasping followed by pick and place. In this context, how does meta-reinforcement learning fit? Does it ...
1
vote
1answer
40 views

Finding the optimal policy from a set of fixed policies in reinforcement learning

This is an open-ended question.Suppose I have a reinforcement learning task that is being solved using many different fixed policies, one of which is optimal. The goal of the agent is not to figure ...
1
vote
1answer
99 views

How are mujoco environments used for meta-rl?

Afaik, investigating meta reinforcement learning algorithms requires a collection of two or more environments which have similar structure but are still different enough. When I read this paper it was ...
0
votes
0answers
55 views

Is there a theory of “meta-layer thinking”?

Some years ago, I came across a notion that states something like: "a machine cannot leave its current level of thinking, move one level up and think about the level below", meaning that a machine ...
1
vote
0answers
16 views

How do I format task features with a one-hot task identification vector to ensure separate weight matrices for each task in multi-task RL?

I am on Lecture 2 of Stanford CS330 Multi-Task and Meta-learning, and on slide 10, the professor describes using a one-hot input vector to represent the task, and she also explained that there would ...
3
votes
0answers
36 views

What is the difference between “out-of-distribution (generalisation)” and “(meta)-transfer learning”?

I'm trying to develop a better understanding of the concept of "out-of-distribution" (generalization) in the context of Bengio's "Moving from System 1 DL to System 2 DL" and the concept of "(meta)-...
1
vote
1answer
336 views

Understanding the derivation of the first-order model-agnostic meta-learning

According to the authors of this paper, to improve the performance, they decided to drop backward pass and using a first-order approximation I found a blog which discussed how to derive the math ...
2
votes
1answer
146 views

What are recent AI software systems and research papers close to J. Pitrat's ideas?

J. Pitrat (born in 1934) was a French leading artificial intelligence scientist (the first to get a Ph.D. in France mentioning "artificial intelligence"). His blog is still online and of ...
1
vote
1answer
53 views

What AI conferences in Europe should I consider submitting papers to explaining the ongoing work on RefPerSys?

https://afia.asso.fr/journee-hommage-j-pitrat/ is a seminar on March 6th, 2020, in Paris (France, European Union), in honor of the late Jacques Pitrat, who advocated during all his professional life a ...
6
votes
3answers
4k views

What are the differences between transfer learning and meta learning?

What are the differences between meta-learning and transfer learning? I have read 2 articles on Quora and TowardDataScience. Meta learning is a part of machine learning theory in which some ...
6
votes
2answers
845 views

What are the state-of-the-art meta-reinforcement learning methods?

This question can seem a little bit too broad, but I am wondering what are the current state-of-the-art works on meta reinforcement learning. Can you provide me with the current state-of-the-art in ...
2
votes
0answers
474 views

What does “episodic training” mean?

I'm reading the book Hands-On Meta Learning with Python, and in Prototypical networks said: So, we use episodic training—for each episode, we randomly sample a few data points from each class in ...
4
votes
1answer
96 views

How important is learning to learn for the development of AGI?

Some people say that abstract thinking, intuition, common sense, and understanding cause and effect are important to make AGI. How important is learning to learn for the development of AGI?
2
votes
1answer
375 views

What are the features get from a feature extraction using a CNN?

I've just started to learn CNN and somewhere I have read if I remove the last FCL I will get the features extracted from the input image but... what are those features? Are they numbers? Labels? An ...
4
votes
1answer
52 views

Why not go another layer deeper with Auto-AutoML?

So I'm finding AutoML to be pretty interesting but I'm still learning how it all works. I've played with the incredibly broken AutoKeras and got some decent results. The question is, if you are using ...
2
votes
1answer
227 views

What is the internal state of a Simple Neural Attentive Meta-Learner(SNAIL)?

In the paper A Simple Neural Attentive Meta-Learner, the authors mentioned right before Section 3.1: we preserve the internal state of a SNAIL across episode boundaries, which allows it to have ...
2
votes
1answer
457 views

What is the difference between meta-learning and zero-shot learning?

What is the difference between meta-learning and zero-shot learning? Are they synonymous? I have seen articles where they seem to imply that they are at least very similar concepts.
5
votes
2answers
336 views

Do genetic algorithms also evolve?

After witnessing the rise of deep learning as automatic feature/pattern recognition over classic machine learning techniques, I had an insight that the more you automate at each level, the better the ...