Related papers: Selective Experience Replay for Lifelong Learning

To cope with real-world dynamics, an intelligent system needs to incrementally acquire, update, and exploit knowledge throughout its lifetime. This ability, known as Continual learning, provides a foundation for AI systems to develop…

Despite remarkable successes achieved by modern neural networks in a wide range of applications, these networks perform best in domain-specific stationary environments where they are trained only once on large-scale controlled data…

Deep learning has emerged as a powerful method for extracting valuable information from large volumes of data. However, when new training data arrives continuously (i.e., is not fully available from the beginning), incremental training…

Loss of plasticity is one of the main challenges in continual learning with deep neural networks, where neural networks trained via backpropagation gradually lose their ability to adapt to new tasks and perform significantly worse than…

Continual lifelong learning is essential to many applications. In this paper, we propose a simple but effective approach to continual deep learning. Our approach leverages the principles of deep model compression, critical weights…

In Federated Learning (FL), the data in each client is typically assumed fixed or static. However, data often comes in an incremental manner in real-world applications, where the data domain may increase dynamically. In this work, we study…

Experience replay is one of the most commonly used approaches to improve the sample efficiency of reinforcement learning algorithms. In this work, we propose an approach to select and replay sequences of transitions in order to accelerate…

Human beings are able to master a variety of knowledge and skills with ongoing learning. By contrast, dramatic performance degradation is observed when new tasks are added to an existing neural network model. This phenomenon, termed as…

To mitigate forgetting, existing lifelong event detection methods typically maintain a memory module and replay the stored memory data during the learning of a new task. However, the simple combination of memory data and new-task samples…

Despite advances in deep learning, neural networks can only learn multiple tasks when trained on them jointly. When tasks arrive sequentially, they lose performance on previously learnt tasks. This phenomenon called catastrophic forgetting…

Continual learning, the setting where a learning agent is faced with a never ending stream of data, continues to be a great challenge for modern machine learning systems. In particular the online or "single-pass through the data" setting…

Continual Learning (CL) aims at incrementally learning new tasks without forgetting the knowledge acquired from old ones. Experience Replay (ER) is a simple and effective rehearsal-based strategy, which optimizes the model with current…

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 ability to continuously process and retain new information like we do naturally as humans is a feat that is highly sought after when training neural networks. Unfortunately, the traditional optimization algorithms often require large…

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 introduce a novel continual learning problem: how to sequentially update the weights of a personalized 2D and 3D generative face model as new batches of photos in different appearances, styles, poses, and lighting are captured regularly.…

Learning new tasks accumulatively without forgetting remains a critical challenge in continual learning. Generative experience replay addresses this challenge by synthesizing pseudo-data points for past learned tasks and later replaying…

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…

Lifelong learning aims to develop machine learning systems that can learn new tasks while preserving the performance on previous learned tasks. In this paper we present a method to overcome catastrophic forgetting on convolutional neural…

Online reinforcement learning agents are currently able to process an increasing amount of data by converting it into a higher order value functions. This expansion of the information collected from the environment increases the agent's…