Discovering Structure in Multiple Learning Tasks: The TC Algorithm

By Sebastian Thrun, Joseph O'Sullivan. 1996

Subfields: Representation & Self-Supervised Learning

How researchers see this paper

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

In Representation & Self-Supervised Learning

Citations in the corpus

An Overview of Multi-task Learning (2018, methodology): “The first task-clustering algorithm proposed in [28] decouples the task-clustering procedure and the model-learning procedure.”
A Survey on Multi-Task Learning (2017, methodology): “Thrun and Sullivan [53] propose the first task clustering”
Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks (2017, background): “Fast learning is likely to derive not just from trial-and-error, but also from mental models that can be applied to diverse problems, similarly to transfer learning (Thrun and Mitchell, 1995; Thrun and O’Sullivan, 1996; Pan and Yang, 2010).”
Towards Continual Reinforcement Learning: A Review and Perspectives (2020, background): “Continually learning agents must learn to solve problems so that they are able to find structure in the world that will benefit them later (Thrun and O’Sullivan, 1996).”
A Model of Inductive Bias Learning (2000, background): “In this context, see Silver and Mercer (1996), Thrun and O’Sullivan (1996).”
A Convex Formulation for Learning Task Relationships in Multi-Task Learning (2010, methodology): “Another widely studied approach for multi-task learning is the task clustering approach [25, 3, 26].”
Multi-Task Learning for Classification with Dirichlet Process Priors (2007, methodology): “…the machine learning community over the last decade (Bakker and Heskes, 2003; Baxter, 1995, 2000; Caruana, 1997; Lawrence and Platt, 2004; Thrun and O’Sullivan, 1996; Yu et al., 2003; Zhang et al., 2006) and has been applied successfully to computer vision (Fei-Fei et al., 2004; Thrun and…”
A Regularization Approach to Learning Task Relationships in Multitask Learning (2014, methodology): “As well, certain task clustering methods [Thrun and O’Sullivan 1996; Bakker and Heskes 2003; Xue et al. 2007; Jacob et al. 2008] may be viewed as a way to learn the task relationships from data.”
An Algorithm for Transfer Learning in a Heterogeneous Environment (2008, background): “Previous work on task clustering [5, 8, 12, 14] considers tasks to be related if the corresponding weight vectors are close to each other.”
Leveraging Domain Knowledge in Multitask Bayesian Network Structure Learning (2012, methodology): “…(Caruana 1997; Niculescu-Mizil and Caruana 2007); the similarity among tasks is estimated from the same data that is used to train the model (Thrun and O’Sullivan 1996; Eaton, desJardins, and Lane 2008); or the similarity between tasks is provided by another source such as task-specific…”
Reconciling meta-learning and continual learning with online mixtures of tasks (2018, background): “Moreover, explicitly estimating relatedness between tasks has the potential to aid the efﬁcacy of a meta-learning algorithm by modulating both positive and negative transfer [52, 59, 45, 61], and by identifying outlier tasks that require a more signiﬁcant degree of adaptation [56, 23].”
Data Poisoning Attacks on Multi-Task Relationship Learning (2018, unknown): “Task clustering approaches assume that different tasks form several task-clusters, each of which consists of similar tasks (Thrun and O’Sullivan 1996).”