Continual Learning for Recurrent Neural Networks: a Review and Empirical Evaluation

by   Andrea Cossu, et al.

Learning continuously during all model lifetime is fundamental to deploy machine learning solutions robust to drifts in the data distribution. Advances in Continual Learning (CL) with recurrent neural networks could pave the way to a large number of applications where incoming data is non stationary, like natural language processing and robotics. However, the existing body of work on the topic is still fragmented, with approaches which are application-specific and whose assessment is based on heterogeneous learning protocols and datasets. In this paper, we organize the literature on CL for sequential data processing by providing a categorization of the contributions and a review of the benchmarks. We propose two new benchmarks for CL with sequential data based on existing datasets, whose characteristics resemble real-world applications. We also provide a broad empirical evaluation of CL and Recurrent Neural Networks in class-incremental scenario, by testing their ability to mitigate forgetting with a number of different strategies which are not specific to sequential data processing. Our results highlight the key role played by the sequence length and the importance of a clear specification of the CL scenario.


Continual Learning with Gated Incremental Memories for sequential data processing

The ability to learn in dynamic, nonstationary environments without forg...

Continual Learning for Human State Monitoring

Continual Learning (CL) on time series data represents a promising but u...

Towards Continual Reinforcement Learning: A Review and Perspectives

In this article, we aim to provide a literature review of different form...

From MNIST to ImageNet and Back: Benchmarking Continual Curriculum Learning

Continual learning (CL) is one of the most promising trends in recent ma...

Continual Learning in Recurrent Neural Networks with Hypernetworks

The last decade has seen a surge of interest in continual learning (CL),...

Continual Domain Adaptation for Machine Reading Comprehension

Machine reading comprehension (MRC) has become a core component in a var...

Cooperative data-driven modeling

Data-driven modeling in mechanics is evolving rapidly based on recent ma...

Please sign up or login with your details

Forgot password? Click here to reset