Related papers: learn2learn: A Library for Meta-Learning Research

Machine learning researchers and practitioners steadily enlarge the multitude of successful learning models. They achieve this through in-depth theoretical analyses and experiential heuristics. However, there is no known general-purpose…

The results from most machine learning experiments are used for a specific purpose and then discarded. This results in a significant loss of information and requires rerunning experiments to compare learning algorithms. This also requires…

Reproducibility is one of the core dimensions that concur to deliver Trustworthy Artificial Intelligence. Broadly speaking, reproducibility can be defined as the possibility to reproduce the same or a similar experiment or method, thereby…

There currently exist two main approaches to reproducing visual appearance using Machine Learning (ML): The first is training models that generalize over different instances of a problem, e.g., different images of a dataset. As one-shot…

Reproducibility is an increasing concern in Artificial Intelligence (AI), particularly in the area of Deep Learning (DL). Being able to reproduce DL models is crucial for AI-based systems, as it is closely tied to various tasks like…

A fundamental challenge in Continual Learning (CL) is catastrophic forgetting, where adapting to new tasks degrades the performance on previous ones. While the field has evolved with diverse methods, this rapid surge in diverse…

Reinforcement learning has recently experienced increased prominence in the machine learning community. There are many approaches to solving reinforcement learning problems with new techniques developed constantly. When solving problems…

Meta-learning enables rapid generalization to new tasks by learning knowledge from various tasks. It is intuitively assumed that as the training progresses, a model will acquire richer knowledge, leading to better generalization…

We hypothesize that curiosity is a mechanism found by evolution that encourages meaningful exploration early in an agent's life in order to expose it to experiences that enable it to obtain high rewards over the course of its lifetime. We…

Meta-learning algorithms produce feature extractors which achieve state-of-the-art performance on few-shot classification. While the literature is rich with meta-learning methods, little is known about why the resulting feature extractors…

Meta-learning enables algorithms to quickly learn a newly encountered task with just a few labeled examples by transferring previously learned knowledge. However, the bottleneck of current meta-learning algorithms is the requirement of a…

Meta-learning stands for 'learning to learn' such that generalization to new tasks is achieved. Among these methods, Gradient-based meta-learning algorithms are a specific sub-class that excel at quick adaptation to new tasks with limited…

As a subset of machine learning, meta-learning, or learning to learn, aims at improving the model's capabilities by employing prior knowledge and experience. A meta-learning paradigm can appropriately tackle the conventional challenges of…

We propose a novel and flexible approach to meta-learning for learning-to-learn from only a few examples. Our framework is motivated by actor-critic reinforcement learning, but can be applied to both reinforcement and supervised learning.…

The notion of meta-mining has appeared recently and extends the traditional meta-learning in two ways. First it does not learn meta-models that provide support only for the learning algorithm selection task but ones that support the whole…

In this paper, we introduce a discrete variant of the meta-learning framework. Meta-learning aims at exploiting prior experience and data to improve performance on future tasks. By now, there exist numerous formulations for meta-learning in…

Machine learning (ML) is an increasingly important scientific tool supporting decision making and knowledge generation in numerous fields. With this, it also becomes more and more important that the results of ML experiments are…

The integration of machine learning techniques in materials discovery has become prominent in materials science research and has been accompanied by an increasing trend towards open-source data and tools to propel the field. Despite the…

Recent studies on catastrophic forgetting during sequential learning typically focus on fixing the accuracy of the predictions for a previously learned task. In this paper we argue that the outputs of neural networks are subject to rapid…

Meta-learning is a tool that allows us to build sample-efficient learning systems. Here we show that, once meta-trained, LSTM Meta-Learners aren't just faster learners than their sample-inefficient deep learning (DL) and reinforcement…