iCaRL: Incremental Classifier and Representation Learning

Rebuffi, Sylvestre-Alvise; Kolesnikov, A. I.; Sperl, Georg; Lampert, Christoph H.

doi:10.48550/arxiv.1611.07725

Cited by 20 publications

(34 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Early attempts to mitigate catastrophic forgetting typically consisted of memory systems that store previous data and that regularly replay old samples interleaved with samples drawn from the new data (Robins 1993(Robins , 1995, and these methods are still used today (Gepperth & Karaoguz 2015, Rebuffi et al 2016). However, a general drawback of memory-based systems is that they require explicit storage of old information, leading to large working memory requirements.…”

Section: Lifelong Machine Learningmentioning

confidence: 99%

Continual lifelong learning with neural networks: A review

et al. 2019

View full text Add to dashboard Cite

Humans and animals have the ability to continually acquire, fine-tune, and transfer knowledge and skills throughout their lifespan. This ability, referred to as lifelong learning, is mediated by a rich set of neurocognitive mechanisms that together contribute to the development and specialization of our sensorimotor skills as well as to long-term memory consolidation and retrieval. Consequently, lifelong learning capabilities are crucial for computational systems and autonomous agents interacting in the real world and processing continuous streams of information. However, lifelong learning remains a long-standing challenge for machine learning and neural network models since the continual acquisition of incrementally available information from non-stationary data distributions generally leads to catastrophic forgetting or interference. This limitation represents a major drawback for state-of-the-art deep neural network models that typically learn representations from stationary batches of training data, thus without accounting for situations in which information becomes incrementally available over time. In this review, we critically summarize the main challenges linked to lifelong learning for artificial learning systems and compare existing neural network approaches that alleviate, to different extents, catastrophic forgetting. Although significant advances have been made in domain-specific learning with neural networks, extensive research efforts are required for the development of robust lifelong learning on autonomous agents and robots. We discuss well-established and emerging research motivated by lifelong learning factors in biological systems such as structural plasticity, memory replay, curriculum and transfer learning, intrinsic motivation, and multisensory integration.

show abstract

Section: Lifelong Machine Learningmentioning

confidence: 99%

Continual lifelong learning with neural networks: A review

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Other methods use an episodic memory, such as iCARL (incremental Classifier and Representation Learning) [29] and Memory Based Parameter Adaptation [35]. A special mention here goes to Gradient Episodic Memory for Continual Learning [20], as it moves a step forward towards the online setting: it assumes that the learner receives examples one by one but simplifies the scenario to locally i.i.d.…”

Section: Related Workmentioning

confidence: 99%

Task-Free Continual Learning

Aljundi

Kelchtermans²,

Tuytelaars

2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

268

177

View full text Add to dashboard Cite

Methods proposed in the literature towards continual deep learning typically operate in a task-based sequential learning setup. A sequence of tasks is learned, one at a time, with all data of current task available but not of previous or future tasks. Task boundaries and identities are known at all times. This setup, however, is rarely encountered in practical applications. Therefore we investigate how to transform continual learning to an online setup. We develop a system that keeps on learning over time in a streaming fashion, with data distributions gradually changing and without the notion of separate tasks. To this end, we build on the work on Memory Aware Synapses, and show how this method can be made online by providing a protocol to decide i) when to update the importance weights, ii) which data to use to update them, and iii) how to accumulate the importance weights at each update step. Experimental results show the validity of the approach in the context of two applications: (self-)supervised learning of a face recognition model by watching soap series and learning a robot to avoid collisions. * Rahaf Aljundi and Klaas Kelchtermans contributed equally to this work and are listed in alphabetical order.

show abstract

“…Their model added new neural units to the autoencoder to facilitate the addition of new MNIST digits. Rebuffi et al (2017) proposed the iCaRL approach which stores example data points that are used along with new data to dynamically adapt the weights of a feature extractor. By combining new and old data, they prevent catastrophic forgetting but at the expense of a higher memory footprint.…”

Section: Related Workmentioning

confidence: 99%

Lifelong Learning of Spatiotemporal Representations With Dual-Memory Recurrent Self-Organization

et al. 2018

View full text Add to dashboard Cite

Artificial autonomous agents and robots interacting in complex environments are required to continually acquire and fine-tune knowledge over sustained periods of time. The ability to learn from continuous streams of information is referred to as lifelong learning and represents a long-standing challenge for neural network models due to catastrophic forgetting in which novel sensory experience interferes with existing representations and leads to abrupt decreases in the performance on previously acquired knowledge. Computational models of lifelong learning typically alleviate catastrophic forgetting in experimental scenarios with given datasets of static images and limited complexity, thereby differing significantly from the conditions artificial agents are exposed to. In more natural settings, sequential information may become progressively available over time and access to previous experience may be restricted. Therefore, specialized neural network mechanisms are required that adapt to novel sequential experience while preventing disruptive interference with existing representations. In this paper, we propose a dual-memory self-organizing architecture for lifelong learning scenarios. The architecture comprises two growing recurrent networks with the complementary tasks of learning object instances (episodic memory) and categories (semantic memory). Both growing networks can expand in response to novel sensory experience: the episodic memory learns fine-grained spatiotemporal representations of object instances in an unsupervised fashion while the semantic memory uses task-relevant signals to regulate structural plasticity levels and develop more compact representations from episodic experience. For the consolidation of knowledge in the absence of external sensory input, the episodic memory periodically replays trajectories of neural reactivations. We evaluate the proposed model on the CORe50 benchmark dataset for continuous object recognition, showing that we significantly outperform current methods of lifelong learning in three different incremental learning scenarios.

show abstract

iCaRL: Incremental Classifier and Representation Learning

Cited by 20 publications

References 0 publications

Continual lifelong learning with neural networks: A review

Continual lifelong learning with neural networks: A review

Task-Free Continual Learning

Lifelong Learning of Spatiotemporal Representations With Dual-Memory Recurrent Self-Organization

Contact Info

Product

Resources

About