Related papers: Consistency is the key to further mitigating catas…

Continual Learning is an unresolved challenge, whose relevance increases when considering modern applications. Unlike the human brain, trained deep neural networks suffer from a phenomenon called catastrophic forgetting, wherein they…

Lifelong learning is the problem of learning multiple consecutive tasks in a sequential manner, where knowledge gained from previous tasks is retained and used to aid future learning over the lifetime of the learner. It is essential towards…

Replaying past experiences has proven to be a highly effective approach for averting catastrophic forgetting in supervised continual learning. However, some crucial factors are still largely ignored, making it vulnerable to serious failure,…

Consistency training regularizes a model by enforcing predictions of original and perturbed inputs to be similar. Previous studies have proposed various augmentation methods for the perturbation but are limited in that they are agnostic to…

Generalisation to unseen subjects in EEG-based emotion classification remains a challenge due to high inter-and intra-subject variability. Continual learning (CL) poses a promising solution by learning from a sequence of tasks while…

Models trained on a new task typically degrade on prior tasks, a phenomenon known as forgetting. Traditionally, mitigating forgetting has required replaying stored exemplars from prior tasks, which is often impractical. By contrast,…

Deep learning requires regularization mechanisms to reduce overfitting and improve generalization. We address this problem by a new regularization method based on distributional robust optimization. The key idea is to modify the…

In supervised machine learning, an agent is typically trained once and then deployed. While this works well for static settings, robots often operate in changing environments and must quickly learn new things from data streams. In this…

Compared with traditional deep learning techniques, continual learning enables deep neural networks to learn continually and adaptively. Deep neural networks have to learn new tasks and overcome forgetting the knowledge obtained from the…

Despite huge success, deep networks are unable to learn effectively in sequential multitask learning settings as they forget the past learned tasks after learning new tasks. Inspired from complementary learning systems theory, we address…

Continual relation extraction (CRE) aims to continuously train a model on data with new relations while avoiding forgetting old ones. Some previous work has proved that storing a few typical samples of old relations and replaying them when…

Reinforcement Learning algorithms aim to learn optimal control strategies through iterative interactions with an environment. A critical element in this process is the experience replay buffer, which stores past experiences, allowing the…

Experience replay (ER) is a fundamental component of off-policy deep reinforcement learning (RL). ER recalls experiences from past iterations to compute gradient estimates for the current policy, increasing data-efficiency. However, the…

The lifelong learning paradigm in machine learning is an attractive alternative to the more prominent isolated learning scheme not only due to its resemblance to biological learning but also its potential to reduce energy waste by obviating…

Various work has suggested that the memorability of an image is consistent across people, and thus can be treated as an intrinsic property of an image. Using computer vision models, we can make specific predictions about what people will…

With the rise of deep reinforcement learning (RL) methods, many complex robotic manipulation tasks are being solved. However, harnessing the full power of deep learning requires large datasets. Online-RL does not suit itself readily into…

Deep neural networks have become popular in many supervised learning tasks, but they may suffer from overfitting when the training dataset is limited. To mitigate this, many researchers use data augmentation, which is a widely used and…

Overfitting is one of the most critical challenges in deep neural networks, and there are various types of regularization methods to improve generalization performance. Injecting noises to hidden units during training, e.g., dropout, is…

Sequential learning of multiple tasks in artificial neural networks using gradient descent leads to catastrophic forgetting, whereby previously learned knowledge is erased during learning of new, disjoint knowledge. Here, we propose a new…

The pursuit of long-term autonomy mandates that machine learning models must continuously adapt to their changing environments and learn to solve new tasks. Continual learning seeks to overcome the challenge of catastrophic forgetting,…