Pseudopatterns and dual-network memory models: Advantages and shortcomings

31 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Incremental Learning of Object Detectors without Catastrophic Forgetting (2017, background): “The problem of addressing these issues in neural networks has its origin in classical connectionist networks several years ago [2, 11–13, Li and Hoiem [23] use knowledge distillation for one of the classical vision tasks, image classiﬁcation, formulated in a deep learning framework.”
Sequential learning in neural networks: A review and a discussion of pseudorehearsal based methods (2004, unknown): “Similarly, French et al. [22] argue that where the density of the data varies over different regions of the function then the density of the pseudoitems generated should match this distribution.”
Pseudo-Rehearsal: Achieving Deep Reinforcement Learning without Catastrophic Forgetting (2018, methodology): “These methods are further extended by separating the learning agent into two parts, an idea which stems from early research into CF [14], [15], [16] and is still being utilised in recent algorithms such as Deep Generative Dual Memory Network [17] for incremental image classification and others (e.”