Untitled

Mahadevan, Sridhar; Tadepalli, Prasad

doi:10.1023/a:1022605018507

Cited by 3 publications

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Untitled

Tadepalli

Russell

1998

Machine Learning

Self Cite

View full text Add to dashboard Cite

Abstract.It is well known that prior knowledge or bias can speed up learning, at least in theory. It has proved difficult to make constructive use of prior knowledge, so that approximately correct hypotheses can be learned efficiently. In this paper, we consider a particular form of bias which consists of a set of "determinations." A set of attributes is said to determine a given attribute if the latter is purely a function of the former. The bias is tree-structured if there is a tree of attributes such that the attribute at any node is determined by its children, where the leaves correspond to input attributes and the root corresponds to the target attribute for the learning problem. The set of allowed functions at each node is called the basis. The tree-structured bias restricts the target functions to those representable by a read-once formula (a Boolean formula in which each variable occurs at most once) of a given structure over the basis functions. We show that efficient learning is possible using a given tree-structured bias from random examples and membership queries, provided that the basis class itself is learnable and obeys some mild closure conditions. The algorithm uses a form of controlled experimentation in order to learn each part of the overall function, fixing the inputs to the other parts of the function at appropriate values. We present empirical results showing that when a tree-structured bias is available, our method significantly improves upon knowledge-free induction. We also show that there are hard cryptographic limitations to generalizing these positive results to structured determinations in the form of a directed acyclic graph.

show abstract

Untitled

Tadepalli

Russell

1998

Machine Learning

Self Cite

View full text Add to dashboard Cite

show abstract

Construction of a classifier with prior domain knowledge formalised as Bayesian network

Antal¹

IECON '98. Proceedings of the 24th Annual Conference of the IEEE Industrial Electronics Society (Cat. No.98CH36200)

View full text Add to dashboard Cite

Efficient combination of prior domain knowledge and examples are essential to classification. In the paper aThis problem introduces the following general pragmatic methodology is suggested which uses prior domain knowledge formalised as a Bayesian network to enhance various steps in the process of the construction of a classifier. It is shown that the Bayesian network methodology is not only an alternative to the "black box approach" of classifier construction, but it provides a general supplementary tool.

show abstract

Generalizing from a Few Examples: A Survey on Few-Shot Learning

Wang¹,

Yao²,

Kwok³

et al. 2019

Preprint

View full text Add to dashboard Cite

Machine learning has been highly successful in data-intensive applications, but is often hampered when the data set is small. Recently, Few-Shot Learning (FSL) is proposed to tackle this problem. Using prior knowledge, FSL can rapidly generalize to new tasks containing only a few samples with supervised information. In this paper, we conduct a thorough survey to fully understand FSL. Starting from a formal definition of FSL, we distinguish FSL from several relevant machine learning problems. We then point out that the core issue in FSL is that the empirical risk minimizer is unreliable. Based on how prior knowledge can be used to handle this core issue, we categorize FSL methods from three perspectives: (i) data, which uses prior knowledge to augment the supervised experience; (ii) model, which uses prior knowledge to reduce the size of the hypothesis space; and (iii) algorithm, which uses prior knowledge to alter the search for the best hypothesis in the given hypothesis space. With this taxonomy, we review and discuss the pros and cons of each category. Promising directions, in the aspects of the FSL problem setups, techniques, applications and theories, are also proposed to provide insights for future research. 1

show abstract

Untitled

Cited by 3 publications

References 36 publications

Untitled

Untitled

Construction of a classifier with prior domain knowledge formalised as Bayesian network

Generalizing from a Few Examples: A Survey on Few-Shot Learning

Contact Info

Product

Resources

About