SpaceNet: Make Free Space for Continual Learning

نویسندگان

چکیده

The continual learning (CL) paradigm aims to enable neural networks learn tasks continually in a sequential fashion. fundamental challenge this is catastrophic forgetting previously learned when the model optimized for new task, especially their data not accessible. Current architectural-based methods aim at alleviating problem but expense of expanding capacity model. Regularization-based maintain fixed capacity; however, previous studies showed huge performance degradation these task identity available during inference (e.g. class incremental scenario). In work, we propose novel method referred as SpaceNet scenario where utilize intelligently. trains sparse deep from scratch an adaptive way that compresses connections each compact number neurons. training results representations reduce interference between tasks. Experimental show robustness our proposed against old and efficiency utilizing model, leaving space more be learned. particular, tested on well-known benchmarks CL: split MNIST, Fashion-MNIST, CIFAR-10/100, it outperforms regularization-based by big gap. Moreover, achieves better than without expansion achieved comparable with rehearsal-based methods, while offering memory reduction.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Continual Learning for Mobile Robots

Autonomous mobile robots should be able to learn incrementally and adapt to changes in the operating environment during their entire lifetime. This is referred to as continual learning. In this thesis, I propose an approach to continual learning which is based on adaptive state-space quantisation and reinforcement learning. Representational tools for continual learning should be constructive, a...

متن کامل

Variational Continual Learning

This paper develops variational continual learning (VCL), a simple but general framework for continual learning that fuses online variational inference (VI) and recent advances in Monte Carlo VI for neural networks. The framework can successfully train both deep discriminative models and deep generative models in complex continual learning settings where existing tasks evolve over time and enti...

متن کامل

Scalable Recollections for Continual Lifelong Learning

Given the recent success of Deep Learning applied to a variety of single tasks, it is natural to consider more human-realistic settings. Perhaps the most difficult of these settings is that of continual lifelong learning, where the model must learn online over a continuous stream of non-stationary data. A continual lifelong learning system must have three primary capabilities to succeed: it mus...

متن کامل

Episodic memory for continual model learning

Both the human brain and artificial learning agents operating in real-world or comparably complex environments are faced with the challenge of online model selection. In principle this challenge can be overcome: hierarchical Bayesian inference provides a principled method for model selection and it converges on the same posterior for both off-line (i.e. batch) and online learning. However, main...

متن کامل

Toward a Formal Framework for Continual Learning

This paper revisits the continual-learning paradigm I described at the previous workshop in 1995. It presents a framework that formally merges ideas from reinforcement learning and inductive transfer, potentially broadening the scope of each. Most research in RL assumes a stationary (non-changing) world, while research in transfer primarily focuses on supervised learning. Combining the two appr...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Neurocomputing

سال: 2021

ISSN: ['0925-2312', '1872-8286']

DOI: https://doi.org/10.1016/j.neucom.2021.01.078