Self-Net: Lifelong Learning via Continual Self-Modeling
This addresses the challenge of lifelong learning for AI systems by reducing storage and retraining needs, though it is incremental as it builds on existing continual learning methods.
The paper tackles the problem of continual learning in deep neural networks by proposing Self-Net, a framework that uses autoencoders to learn low-dimensional representations of weights for different tasks, enabling new tasks to be incorporated with minimal retraining and storage, and it outperforms state-of-the-art methods on datasets like MNIST and CIFAR, achieving over 10X storage compression.
Learning a set of tasks over time, also known as continual learning (CL), is one of the most challenging problems in artificial intelligence. While recent approaches achieve some degree of CL in deep neural networks, they either (1) grow the network parameters linearly with the number of tasks, (2) require storing training data from previous tasks, or (3) restrict the network's ability to learn new tasks. To address these issues, we propose a novel framework, Self-Net, that uses an autoencoder to learn a set of low-dimensional representations of the weights learned for different tasks. We demonstrate that these low-dimensional vectors can then be used to generate high-fidelity recollections of the original weights. Self-Net can incorporate new tasks over time with little retraining and with minimal loss in performance for older tasks. Our system does not require storing prior training data and its parameters grow only logarithmically with the number of tasks. We show that our technique outperforms current state-of-the-art approaches on numerous datasets---including continual versions of MNIST, CIFAR10, CIFAR100, and Atari---and we demonstrate that our method can achieve over 10X storage compression in a continual fashion. To the best of our knowledge, we are the first to use autoencoders to sequentially encode sets of network weights to enable continual learning.