Bayesian Optimized Continual Learning with Attention Mechanism
It addresses the challenge of continual learning for AI systems that need to adapt to new tasks without forgetting old ones, representing an incremental improvement.
The paper tackles the problem of catastrophic forgetting in neural networks learning from continuous tasks by proposing a new model that dynamically expands capacity using Bayesian optimization and selectively uses previous knowledge via attention, achieving state-of-the-art performance on MNIST and CIFAR-100 variants.
Though neural networks have achieved much progress in various applications, it is still highly challenging for them to learn from a continuous stream of tasks without forgetting. Continual learning, a new learning paradigm, aims to solve this issue. In this work, we propose a new model for continual learning, called Bayesian Optimized Continual Learning with Attention Mechanism (BOCL) that dynamically expands the network capacity upon the arrival of new tasks by Bayesian optimization and selectively utilizes previous knowledge (e.g. feature maps of previous tasks) via attention mechanism. Our experiments on variants of MNIST and CIFAR-100 demonstrate that our methods outperform the state-of-the-art in preventing catastrophic forgetting and fitting new tasks better.