Reinforced Continual Learning

2018-05-31 · NeurIPS 2018 12 · Ju Xu, Zhanxing Zhu

Most artificial intelligence models have limiting ability to solve new tasks faster, without forgetting previously acquired knowledge. The recently emerging paradigm of continual learning aims to solve this issue, in which the model learns various tasks in a sequential fashion. In this work, a novel approach for continual learning is proposed, which searches for the best neural architecture for each coming task via sophisticatedly designed reinforcement learning strategies. We name it as Reinforced Continual Learning. Our method not only has good performance on preventing catastrophic forgetting but also fits new tasks well. The experiments on sequential classification tasks for variants of MNIST and CIFAR-100 datasets demonstrate that the proposed approach outperforms existing continual learning alternatives for deep networks.

📄 PDF Abstract BibTeX arXiv:1805.12369

Code (1)

xujinfan/Reinforced-Continual-Learning tf

Tasks

Continual Learning General Classification reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Reinforced Interactive Continual Learning via Real-time Noisy Human Feedback

2025-05-15 · Yutao Yang, Jie zhou, Junsong Li, Qianjun Pan 외

This paper introduces an interactive continual learning paradigm where AI models dynamically learn new skills from real-time human feedback while retaining prior knowledge. This paradigm distinctively addresses two major…

Continual Learning Contrastive Learning

HIPPOCAMPAL NEURONAL REPRESENTATIONS IN CONTINUAL LEARNING

2019-09-25 · Samia Mohinta, Rui Ponte Costa, Stephane Ciocchi

The hippocampus has long been associated with spatial memory and goal-directed spatial navigation. However, the region’s independent role in continual learning of navigational strategies has seldom been investigated. Her…

Continual Learning Deep Reinforcement Learning Hippocampus reinforcement-learning+2

Reinforced Continual Learning for Graphs

2022-09-04 · Appan Rakaraddi, Siew Kei Lam, Mahardhika Pratama, Marcus de Carvalho

Graph Neural Networks (GNNs) have become the backbone for a myriad of tasks pertaining to graphs and similar topological data structures. While many works have been established in domains related to node and graph classi…

class-incremental learning Class Incremental Learning Continual Learning Graph Classification+1

Continual Learning for Personalized Co-speech Gesture Generation

2023-01-01 · ICCV 2023 1 · Chaitanya Ahuja, Pratik Joshi, Ryo Ishii, Louis-Philippe Morency

Co-speech gestures are a key channel of human communication, making them important for personalized chat agents to generate. In the past, gesture generation models assumed that data for each speaker is available all …

Continual Learning Gesture Generation

VLM-Assisted Continual learning for Visual Question Answering in Self-Driving

2025-02-02 · Yuxin Lin, Mengshi Qi, Liang Liu, Huadong Ma

In this paper, we propose a novel approach for solving the Visual Question Answering (VQA) task in autonomous driving by integrating Vision-Language Models (VLMs) with continual learning. In autonomous driving, VQA plays…

Autonomous Driving Continual Learning Knowledge Distillation Question Answering+2