#### Filter Results:

#### Publication Year

1985

2016

#### Publication Type

#### Co-author

#### Key Phrase

#### Publication Venue

#### Data Set Used

Learn More

Hybrid learning methods use theoretical knowledge of a domain and a set of classified examples to develop a method for accurately classifying examples not seen during training. The challenge of hybrid learning systems is to use the information provided by one source of information to offset information missing from the other source. By so doing, a hybrid… (More)

Concepts learned by neural networks are dif-cult to understand because they are represented using large assemblages of real-valued parameters. One approach to understanding trained neural networks is to extract symbolic rules that describe their classiica-tion behavior. There are several existing rule-extraction approaches that operate by searching for such… (More)

Markov Logic Networks (MLNs) have emerged as a powerful framework that combines statistical and logical reasoning; they have been applied to many data intensive problems including information extraction, entity resolution, and text mining. Current implementations of MLNs do not scale to large real-world data sets, which is preventing their widespread… (More)

A signiicant limitation of neural networks is that the representations they learn are usually incomprehensible to humans. We present a novel algorithm, Trepan, for extracting comprehensible, symbolic representations from trained neural networks. Our algorithm uses queries to induce a decision tree that approximates the concept represented by a given… (More)

Learning from reinforcements is a promising approach for creating intelligent agents. However, reinforcement learning usually requires a large number of training episodes. We present and evaluate a design that addresses this shortcoming by allowing a connectionist Q-learner to accept advice given, at any time and in a natural manner, by an external… (More)

Prior knowledge in the form of multiple polyhedral sets, each belonging to one of two categories, is introduced into a reformulation of a linear support vector machine classifier. The resulting formulation leads to a linear program that can be solved efficiently. Real world examples, from DNA sequencing and breast cancer prognosis, demonstrate the… (More)

The primary goal of inductive learning is to generalize well { that is, induce a function that accurately produces the correct output for future inputs. Hansen and Salamon showed that, under certain assumptions, combining the predictions of several separately trained neu-ral networks will improve generalization. One of their key assumptions is that the… (More)

Despite the fact that many symbolic and neural network (connectionist) learning algorithms address the same problem of learning from classified examples, very little is known regarding their comparative strengths and weaknesses. Experiments comparing the ID3 symbolic learning algorithm with the perception and backpropaga-tion neural learning algorithms have… (More)

Dependency networks approximate a joint probability distribution over multiple random variables as a product of conditional distributions. Relational Dependency Networks (RDNs) are graphical models that extend dependency networks to relational domains. This higher expressivity, however, comes at the expense of a more complex model-selection problem: an… (More)