Explanation-based neural network learning a lifelong learning approach

By Sebastian Thrun. 1995

How researchers see this paper

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

Citations in the corpus

Progress & Compress: A scalable framework for continual learning (2018, methodology): “Examples making use of this idea are (Rebufﬁ et al., 2016; Schmidhuber, 2013; Thrun, 1996).”
Continual Learning with Adaptive Weights (CLAW) (2019, methodology): “(c) The memory-based approach relies on episodic memory to store data (or pseudo-data) from previous tasks (Ratcliff, 1990; Robins, 1993; 1995; Thrun, 1996; Schmidhuber, 2013; Hattori, 2014; Mocanu et al., 2016; Rebuffi et al., 2017; Kamra et al., 2017; Shin et al., 2017; Rolnick et al., 2018; van…”
Multi-task Deep Reinforcement Learning with PopArt (2018, background): “…of experience (Schmidhuber 1990; Sutton et al. 2011; Jaderberg et al. 2016), continual learning in a sequence of tasks (Ring 1994; Thrun 1996; Thrun 2012; Rusu et al. 2016), distillation of task-speciﬁc experts into a single shared model (Parisotto, Ba, and Salakhutdinov 2015; Rusu et al.…”
A Wholistic View of Continual Learning with Deep Neural Networks: Forgotten Lessons and the Bridge to Active and Open World Learning (2020, methodology): “Thrun - Lifelong Machine Learning [1], [2]: The system has performed N tasks.”
Efficient Representations for Lifelong Learning and Autoencoding (2014, background): “A natural approach for tackling this goal (called “life-long learning” [23, 25] or “transfer learning” [1, 19] or “learning to learn” [7, 24]) is to use information from previously-learned tasks to improve the underlying representation used by the learning algorithm, under the hope or belief that so”
Extracting comprehensible models from trained neural networks (1996, background): “First, one might want to transfer some part of the solution learned for one task to the process of learning a solution for a related task (Pratt et al., 1991; Caruana, 1996; Thrun, 1996).”
Towards Knowledgeable Supervised Lifelong Learning Systems (2020, background): “The main challenge posed by EBNN was the requirement to maintain the proposed invariance network perpetually.”
Lifelong Machine Learning Systems: Beyond Learning Algorithms (2013, background): “Alternatively, it may be necessary to retain characteristics of the learning process for each task (Thrun 1996).”
Machine Lifelong Learning: Challenges and Benefits for Artificial General Intelligence (2011, background): “Software agents and robots will make good use of lifelong learning systems, or at least provide useful test platforms for empirical studies [12].”
Multitask Learning (1997, methodology): “For example, EBNN [Thrun & Mitchell 1994; Thrun 1996] requires that the domain theory be differentiable, but the MTL approach to sequential transfer does not.”
Toward Training Recurrent Neural Networks for Lifelong Learning (2019, background): “This has several names and manifestations in the literature— incremental learning (Solomonoff, 1989), continual learning (Ring, 1997), explanation-based learning (Thrun, 1996, 2012), never-ending learning (Carlson et al., 2010), and others.”
Is Learning The n-th Thing Any Easier Than Learning The First? (1995, methodology): “The last method described here uses the explanation-based neural network learning algorithm (EBNN), which was originally proposed in the context of reinforcement learning [8, 17 ].”
ELLA: An Efficient Lifelong Learning Algorithm (2013, unknown): “ELLA: An Efficient Lifelong Learning Algorithm ral networks (Thrun, 1996).”
Transfer Learning for Activity Recognition: A Survey (2013, background): “In the field of machine learning, transfer learning is studied under a variety of different names including learning to learn, life-long learning, knowledge transfer, inductive transfer, context-sensitive learning, and meta-learning [3,19,64,65,70].”
Lifelong Learning: A Case Study. (1995, methodology): “This algorithm is a special version of both the Tangent-Prop algorithm [56] and the explanation-based neural network learning (EBNN) algorithm [34, 61].”
Incremental Evolution of Complex General Behavior (1997, background): “Incremental evaluation attempts to give the problem of learning complex general behavior a competitive orientation that, in spirit, constitutes a cognitively plausible model of continual (or lifelong) learning (Elman 1991; Ring 1994; Thrun 1996).”