Pathology diagnosis based on EEG signals and decoding brain activity hol...
Large language models (LLMs) are routinely pre-trained on billions of to...
Continual Learning (CL, sometimes also termed incremental learning) is a...
Standard gradient descent algorithms applied to sequences of tasks are k...
Rapid development of large-scale pre-training has resulted in foundation...
Continual Learning (CL) is the research field addressing learning settin...
The field of Continual Learning (CL) seeks to develop algorithms that
ac...
We study how different output layer types of a deep neural network learn...
Classical machine learning algorithms often assume that the data are dra...
Continual learning is a machine learning sub-field specialized in settin...
Humans learn all their life long. They accumulate knowledge from a seque...
In classical machine learning, the data streamed to the algorithms is as...
In multi-task reinforcement learning there are two main challenges: at
t...
Continual learning (CL) is a particular machine learning paradigm where ...
We focus on the problem of teaching a robot to solve tasks presented
seq...
Scaling end-to-end reinforcement learning to control real robots from vi...
Which generative model is the most suitable for Continual Learning? This...
We present a new replay-based method of continual classification learnin...
State representation learning aims at learning compact representations f...
Generative models are known to be difficult to assess. Recent works,
esp...
The problem of object localization and recognition on autonomous mobile
...
Representation learning algorithms are designed to learn abstract featur...
Our understanding of the world depends highly on our capacity to produce...