Lifelong Machine Learning Systems: Beyond Learning Algorithms

By Daniel L. Silver, Qiang Yang, Lianghao Li. 2013

379 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.

In Meta & Continual Learning

Citations in the corpus

Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges (2019, neutral): “, 2016; Pan and Yang, 2010), meta-learning and life-long learning (Thrun and Mitchell, 1995; Silver et al., 2013; Chen and Liu, 2016; Parisi et al., 2018; Golkar et al., 2019; Sodhani et al., 2018; Lopez-Paz et al., 2017).”
Learning from Dialogue after Deployment: Feed Yourself, Chatbot! (2019, background): “The general concepts of lifelong learning (Silver et al., 2013) and never-ending (language) learning (Carlson et al.”
Dynabench: Rethinking Benchmarking in NLP (2021, background): “, 2015) or in a never-ending or life-long learning setting (Silver et al., 2013; Mitchell et al., 2018).”
Progressive Neural Networks (2016, methodology): “Compared to DQN [12], the model simultaneously learns a policy and a value function for predicting expected future rewards.”
Advances and Open Problems in Federated Learning (2019, background): “Is it possible for other issues such as concept drift to also be analyzed in this way, for example as a problem in lifelong learning [359]?”
Overcoming Multi-Model Forgetting (2019, neutral): “This has been employed in transfer learning (Pan & Yang, 2010), multi-task learning (Caruana, 1997) and lifelong learning (Silver et al., 2013).”
Net2Net: Accelerating Learning via Knowledge Transfer (2015, background): “More ambitiously, real machine learning systems will eventually become lifelong learning systems (Thrun, 1995; Silver et al., 2013; Mitchell et al., 2015).”
Deep Meta-Learning: Learning to Learn in the Concept Space (2018, background): “Interestingly, this new deep meta-learning framework could be easily extended to a life-long learning system (Silver et al., 2013), which retains knowledge learned previously and adapts to new tasks over a lifelong time.”
Progress & Compress: A scalable framework for continual learning (2018, background): “Recent methods have tried to overcome this by sampling synthetic data from a generative model (Shin et al., 2017; Silver et al., 2013).”
Continual Learning of a Mixed Sequence of Similar and Dissimilar Tasks (2021, background): “Although there are also works using neural networks (Ke et al., 2020; Wang et al., 2018; Thrun, 1998; Silver et al., 2013), all of them (including those based on traditional learning methods) work on tasks that are very similar and thus there is almost no forgetting.”
Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning (2021, background): “Knowledge transfer in this paper is closely related to lifelong learning (LL), which aims to improve the new/last task learning without handling CF [56, 49, 5].”
Adapting BERT for Continual Learning of a Sequence of Aspect Sentiment Classification Tasks (2021, background): “LL is now regarded the same as CL, but early LL mainly aimed at improving the new task learning through forward transfer without tackling CF (Silver et al., 2013; Ruvolo and Eaton, 2013; Chen and Liu, 2018).”
Lifelong and Continual Learning Dialogue Systems: Learning during Conversation (2021, methodology): “The ﬁrst part of the deﬁnition is taken from (Chen and Liu 2018) based on the early work in (Thrun 1998; Silver, Yang, and Li 2013; Ruvolo and Eaton 2013; Chen and Liu 2014) and the second part of on-the-job learning is proposed in (Liu 2020).”
Layerwise Optimization by Gradient Decomposition for Continual Learning (2021, neutral): “Continual learning has been a long-standing research problem in the ﬁeld of machine learning [32, 45, 36, 47].”
Remembering for the Right Reasons: Explanations Reduce Catastrophic Forgetting (2020, background): “The ﬁeld of continual learning or lifelong learning (Thrun & Mitchell, 1995; Silver et al., 2013) aims at maintaining previous performance and avoiding so-called catastrophic forgetting of previous experience (McCloskey & Cohen, 1989; McClelland et al., 1995) when learning new skills.”
Task-Free Continual Learning (2018, background): “Inspired by biological systems, the ﬁeld of incremental learning, also referred to as continual learning or lifelong learning [24, 34, 37], aims at breaking this strong barrier between the training and testing phase.”
Memory Aware Synapses: Learning what (not) to forget (2017, background): “With tasks being dealt with in a sequential manner [25, 26], the absence of the data from the previous tasks introduces the risk of catastrophic forgetting [14, 20, 13, 6, 7] of the previously acquired knowledge.”