相关论文: Avoid Catastrophic Forgetting with Rank-1 Fisher f…

Continual reinforcement learning challenges agents to acquire new skills while retaining previously learned ones with the goal of improving performance in both past and future tasks. Most existing approaches rely on model-free methods with…

Bayesian neural networks (BNNs) demonstrate promising success in improving the robustness and uncertainty quantification of modern deep learning. However, they generally struggle with underfitting at scale and parameter efficiency. On the…

Training neural networks with many processors can reduce time-to-solution; however, it is challenging to maintain convergence and efficiency at large scales. The Kronecker-factored Approximate Curvature (K-FAC) was recently proposed as an…

Recent advancements in video generation have demonstrated the potential of using video diffusion models as world models, with autoregressive generation of infinitely long videos through masked conditioning. However, such models, usually…

To address the issue of catastrophic forgetting in neural networks, we propose a novel, simple, and effective solution called neuron-level plasticity control (NPC). While learning a new task, the proposed method preserves the knowledge for…

Neural networks are prone to catastrophic forgetting when trained incrementally on different tasks. Popular incremental learning methods mitigate such forgetting by retaining a subset of previously seen samples and replaying them during the…

In contemporary deep learning, a prevalent and effective workflow for solving low-data problems is adapting powerful pre-trained foundation models (FMs) to new tasks via parameter-efficient fine-tuning (PEFT). However, while empirically…

Class-Incremental Learning (CIL) trains a model to continually recognize new classes from non-stationary data while retaining learned knowledge. A major challenge of CIL arises when applying to real-world data characterized by non-uniform…

Catastrophic forgetting is a problem faced by many machine learning models and algorithms. When trained on one task, then trained on a second task, many machine learning models "forget" how to perform the first task. This is widely believed…

Continual learning of partially similar tasks poses a challenge for artificial neural networks, as task similarity presents both an opportunity for knowledge transfer and a risk of interference and catastrophic forgetting. However, it…

Sequential learning in deep models often suffers from challenges such as catastrophic forgetting and loss of plasticity, largely due to the permutation dependence of gradient-based algorithms, where the order of training data impacts the…

Continual learning in artificial neural networks is fundamentally limited by the stability--plasticity dilemma: systems that retain prior knowledge tend to resist acquiring new knowledge, and vice versa. Existing approaches, most notably…

Current robotic pick-and-place policies typically require consistent gripper configurations across training and inference. This constraint imposes high retraining or fine-tuning costs, especially for imitation learning-based approaches,…

In the scenario of class-incremental learning (CIL), deep neural networks have to adapt their model parameters to non-stationary data distributions, e.g., the emergence of new classes over time. However, CIL models are challenged by the…

Diffusion models have achieved remarkable results in image generation, and have similarly been used to learn high-performing policies in sequential decision-making tasks. Decision-making diffusion models can be trained on lower-quality…

Humans have the ability to accumulate knowledge of new tasks in varying conditions, but deep neural networks often suffer from catastrophic forgetting of previously learned knowledge after learning a new task. Many recent methods focus on…

Building learning agents that can progressively learn and accumulate knowledge is the core goal of the continual learning (CL) research field. Unfortunately, training a model on new data usually compromises the performance on past data. In…

To address the problem of catastrophic forgetting due to the invisibility of old categories in sequential input, existing work based on relatively simple categorization tasks has made some progress. In contrast, video captioning is a more…

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…

Autonomous machine learning systems that learn many tasks in sequence are prone to the catastrophic forgetting problem. Mathematical theory is needed in order to understand the extent of forgetting during continual learning. As a…