Related papers: Neural Routing in Meta Learning
We describe a mechanism by which artificial neural networks can learn rapid adaptation - the ability to adapt on the fly, with little data, to new tasks - that we call conditionally shifted neurons. We apply this mechanism in the framework…
Multi-task learning (MTL) is a subfield of machine learning in which multiple tasks are simultaneously learned by a shared model. Such approaches offer advantages like improved data efficiency, reduced overfitting through shared…
Current training regimes for deep learning usually involve exposure to a single task / dataset at a time. Here we start from the observation that in this context the trained model is not given any knowledge of anything outside its…
We explore the behavior of a standard convolutional neural net in a continual-learning setting that introduces visual classification tasks sequentially and requires the net to master new tasks while preserving mastery of previously learned…
Integrating knowledge across different domains is an essential feature of human learning. Learning paradigms such as transfer learning, meta-learning, and multi-task learning reflect the human learning process by exploiting the prior…
Despite impressive performance on numerous visual tasks, Convolutional Neural Networks (CNNs) --- unlike brains --- are often highly sensitive to small perturbations of their input, e.g. adversarial noise leading to erroneous decisions. We…
Recent work has shown the efficiency of deep learning models such as Fully Convolutional Networks (FCN) or Recurrent Neural Networks (RNN) to deal with Time Series Regression (TSR) problems. These models sometimes need a lot of data to be…
Despite its size and complexity, the human cortex exhibits striking anatomical regularities, suggesting there may simple meta-algorithms underlying cortical learning and computation. We expect such meta-algorithms to be of interest since…
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.…
Deep neural networks are highly effective when a large number of labeled samples are available but fail with few-shot classification tasks. Recently, meta-learning methods have received much attention, which train a meta-learner on massive…
Though deep learning methods have shown great success in 3D point cloud part segmentation, they generally rely on a large volume of labeled training data, which makes the model suffer from unsatisfied generalization abilities to unseen…
Over the past decade, the field of machine learning has experienced remarkable advancements. While image recognition systems have achieved impressive levels of accuracy, they continue to rely on extensive training datasets. Additionally, a…
Learning to learn is a powerful paradigm for enabling models to learn from data more effectively and efficiently. A popular approach to meta-learning is to train a recurrent model to read in a training dataset as input and output the…
We propose meta-curvature (MC), a framework to learn curvature information for better generalization and fast model adaptation. MC expands on the model-agnostic meta-learner (MAML) by learning to transform the gradients in the inner…
Convolutional Neural Networks (CNNs) are successfully used for the important automotive visual perception tasks including object recognition, motion and depth estimation, visual SLAM, etc. However, these tasks are typically independently…
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, the notion of learning to learn, enables learning systems to quickly and flexibly solve new tasks. This usually involves defining a set of outer-loop meta-parameters that are then used to update a set of inner-loop…
This paper presents a novel optimization method for maximizing generalization over tasks in meta-learning. The goal of meta-learning is to learn a model for an agent adapting rapidly when presented with previously unseen tasks. Tasks are…
Gradient-based meta-learning algorithms have gained popularity for their ability to train models on new tasks using limited data. Empirical observations indicate that such algorithms are able to learn a shared representation across tasks,…
\textit{Graph neural networks} (GNNs) are effective models for many dynamical systems consisting of entities and relations. Although most GNN applications assume a single type of entity and relation, many situations involve multiple types…