Results 1 - 10 of 837

Greedy layer-wise training of deep networks

by Yoshua Bengio, Pascal Lamblin, Dan Popovici, Hugo Larochelle , 2006
"... Complexity theory of circuits strongly suggests that deep architectures can be much more efficient (sometimes exponentially) than shallow architectures, in terms of computational elements required to represent some functions. Deep multi-layer neural networks have many levels of non-linearities allow ..."
Abstract - Cited by 394 (48 self) - Add to MetaCart
and extend it to cases where the inputs are continuous or where the structure of the input dis-tribution is not revealing enough about the variable to be predicted in a supervised task. Our experiments also conrm the hypothesis that the greedy layer-wise unsu-pervised training strategy mostly helps

Predicting Outcomes of Case-based Legal Arguments

by Stefanie Brüninghaus , Kevin D. Ashley , 2003
"... In this paper, we introduce IBP, an algorithm that combines reasoning with an abstract domain model and case-based reasoning techniques to predict the outcome of case-based legal arguments. Unlike the predictions generated by statistical or machine-learning techniques, IBP’s predictions are accompan ..."
Abstract - Cited by 33 (5 self) - Add to MetaCart
In this paper, we introduce IBP, an algorithm that combines reasoning with an abstract domain model and case-based reasoning techniques to predict the outcome of case-based legal arguments. Unlike the predictions generated by statistical or machine-learning techniques, IBP’s predictions

Predicting Outcomes of Case-based Legal Arguments

by unknown authors
"... In this paper, we introduce IBP, an algorithm that combines reasoning with an abstract domain model and case-based reasoning techniques to predict the outcome of case-based legal arguments. Unlike the predictions generated by statistical or machine-learning techniques, IBP’s predictions are accompan ..."
Abstract - Add to MetaCart
In this paper, we introduce IBP, an algorithm that combines reasoning with an abstract domain model and case-based reasoning techniques to predict the outcome of case-based legal arguments. Unlike the predictions generated by statistical or machine-learning techniques, IBP’s predictions

Uncertainty in Abstract Argument Games: A Case Study on the Game for the Grounded Extension

by Davide Grossi, Wiebe Van Der Hoek , 2012
"... The paper argues for the equipment of argument games with richer game-theoretic features. Concretely, it tackles the question of what happens to argument games when proponent and opponent are uncertain about the attack graph upon which they are playing. This simple sort of uncertainty, we argue, cat ..."
Abstract - Cited by 2 (0 self) - Add to MetaCart
, caters for the modeling of several strategic phenomena of real-life arguments. Using the argument game for the grounded semantics as a case study, the paper studies the impact of uncertainty over the ability of argument games to deliver adequacy with respect to their corresponding semantics.

Advanced Procedures for Hard Problems in Abstract Argumentation

by Johannes Peter Wallner
"... Abstract argumentation is a central topic in Artificial Intelligence with a variety of applications. Many formal models in argumentation have their origin in Argumentation Frameworks (AFs) due to Dung in 1995, which can be represented by directed graphs. AFs have a high expressivity under several di ..."
Abstract - Add to MetaCart
Abstract argumentation is a central topic in Artificial Intelligence with a variety of applications. Many formal models in argumentation have their origin in Argumentation Frameworks (AFs) due to Dung in 1995, which can be represented by directed graphs. AFs have a high expressivity under several

Remembering over the short-term: The case against the standard model.

by James S Nairne - Annual Review of Psychology, , 2002
"... s Abstract Psychologists often assume that short-term storage is synonymous with activation, a mnemonic property that keeps information in an immediately accessible form. Permanent knowledge is activated, as a result of on-line cognitive processing, and an activity trace is established "in&quo ..."
Abstract - Cited by 74 (0 self) - Add to MetaCart
-but there is no simple way for the standard model to explain the large span differences found at matched articulation rates. Thus, the span advantage seen for words over nonwords, high-frequency over lowfrequency words, or concrete over abstract words must be attributable to factors other than those contained

Abstract Using a Diathesis Model for Semantic Parsing

by Jordi Atserias, Irene Castellón, Montse Civit, German Rigau , 2000
"... This paper presents a semantic parsing approach for unrestricted texts. Semantic parsing is one of the major bottlenecks of Natural Language Understanding (NLU) systems and usually requires building expensive resources not easily portable to other domains. Our approach obtains a case-role analysis, ..."
Abstract - Add to MetaCart
, in which the semantic roles of the verb are identified. In order to cover all the possible syntactic realisations of a verb, our system combines their argument structure with a set of general semantic labelled diatheses models. Combining them, the system builds a set of syntactic-semantic patterns

Whom You Know Matters: Venture Capital Networks and Investment Performance,

by Yael Hochberg , Alexander Ljungqvist , Yang Lu , Steve Drucker , Jan Eberly , Eric Green , Yaniv Grinstein , Josh Lerner , Laura Lindsey , Max Maksimovic , Roni Michaely , Maureen O'hara , Ludo Phalippou Mitch Petersen , Jesper Sorensen , Per Strömberg Morten Sorensen , Yael Hochberg , Johnson - Journal of Finance , 2007
"... Abstract Many financial markets are characterized by strong relationships and networks, rather than arm's-length, spot-market transactions. We examine the performance consequences of this organizational choice in the context of relationships established when VCs syndicate portfolio company inv ..."
Abstract - Cited by 138 (8 self) - Add to MetaCart
proxy for experience, our models explicitly control for a variety of dimensions of VC experience. Interestingly, once we control for VC networks, the beneficial effect of experience on performance is reduced, and in some specifications, eliminated. It is also not the case that the betternetworked VCs

Abstract dialectical frameworks

by Gerhard Brewka, Stefan Woltran - In Proc. KR-2010 , 2010
"... In this paper we introduce dialectical frameworks, a powerful generalization of Dung-style argumentation frameworks where each node comes with an associated acceptance condition. This allows us to model different types of dependencies, e.g. support and attack, as well as different types of nodes wit ..."
Abstract - Cited by 35 (6 self) - Add to MetaCart
In this paper we introduce dialectical frameworks, a powerful generalization of Dung-style argumentation frameworks where each node comes with an associated acceptance condition. This allows us to model different types of dependencies, e.g. support and attack, as well as different types of nodes

Uniform Argumentation Frameworks

by Katie Atkinson, Trevor Bench-capon, Paul E. Dunne
"... Abstract. We introduce a derivative of Dung’s seminal abstract argumentation frameworks (afs) through which distinctive features both of Dung’s semantics and so-called “value-based ” argumentation frameworks (vafs) may be captured. These frameworks, which we describe as uniform afs, thereby recognis ..."
Abstract - Cited by 2 (0 self) - Add to MetaCart
Abstract. We introduce a derivative of Dung’s seminal abstract argumentation frameworks (afs) through which distinctive features both of Dung’s semantics and so-called “value-based ” argumentation frameworks (vafs) may be captured. These frameworks, which we describe as uniform afs, thereby
Results 1 - 10 of 837