Results 1  10
of
2,359
Cryptographic Limitations on Learning Boolean Formulae and Finite Automata
 PROCEEDINGS OF THE TWENTYFIRST ANNUAL ACM SYMPOSIUM ON THEORY OF COMPUTING
, 1989
"... In this paper we prove the intractability of learning several classes of Boolean functions in the distributionfree model (also called the Probably Approximately Correct or PAC model) of learning from examples. These results are representation independent, in that they hold regardless of the syntact ..."
Abstract

Cited by 347 (14 self)
 Add to MetaCart
of the syntactic form in which the learner chooses to represent its hypotheses. Our methods reduce the problems of cracking a number of wellknown publickey cryptosystems to the learning problems. We prove that a polynomialtime learning algorithm for Boolean formulae, deterministic finite automata or constant
The Power of Amnesia: Learning Probabilistic Automata with Variable Memory Length
 Machine Learning
, 1996
"... . We propose and analyze a distribution learning algorithm for variable memory length Markov processes. These processes can be described by a subclass of probabilistic finite automata which we name Probabilistic Suffix Automata (PSA). Though hardness results are known for learning distributions gene ..."
Abstract

Cited by 226 (17 self)
 Add to MetaCart
. We propose and analyze a distribution learning algorithm for variable memory length Markov processes. These processes can be described by a subclass of probabilistic finite automata which we name Probabilistic Suffix Automata (PSA). Though hardness results are known for learning distributions
SIDEEFFECTS OF INCARCERATION
"... ONE of the unfortunate results of ambitious and costly efforts to use imprisonment to achieve positive improvement in prisoners ' characters has been the way in which these distracted attention from the unwanted effects of incarceration. Now that positive improvement is seen to be infrequent ..."
Abstract
 Add to MetaCart
of the remarkable features of nearly everything that has been written about unwanted sideeffects of incarceration is the assumption that any sideeffect which can be demonstrated or hypothesised must be permanent. Yet the writers who assume this are also capable of pointing out that one reason why custodial
SideEffects of CrossCertification
"... While many organizations lean towards crosscertification with bridge certification authorities (BCAs) for wider PKI interoperability, there are many hidden details that can affect operating capabilities as well as legal standings. The purpose of this paper is to share lessons learned to help the re ..."
Abstract
 Add to MetaCart
While many organizations lean towards crosscertification with bridge certification authorities (BCAs) for wider PKI interoperability, there are many hidden details that can affect operating capabilities as well as legal standings. The purpose of this paper is to share lessons learned to help
Inference of finite automata using homing sequences (Extended Abstract)
, 1989
"... We present new algorithms for inferring an unknown finitestate automaton from its input/output behavior in the absence of a means of re~rttinp the machine to a start date. A key technique used is inference of a homing sequence for the unknown automaton. Our infknrnce procedufes experiment with the ..."
Abstract

Cited by 194 (6 self)
 Add to MetaCart
with the unknown machine, and from time to time require a teacher to supply counterexamplea to incorrect conjectures about the structure of the unknown automaton. In this setting, we describe a learning algorithm which, with probability 1 6, outputs a correct deecription of the unknown machine in time polynomial
Finite State Automata and Simple Recurrent Networks
"... Figurel: The simple recurrent network (Elman 1988). In the SRN, the pattern of activation on the hidden units at time step t 1, together with the new input pattern, is allowed to influence the pattern of activation at time step t. This is achieved by copying the pattern of activation on the hidden ..."
Abstract

Cited by 166 (10 self)
 Add to MetaCart
learning procedure that is completely local in time (Fig. 1). In this paper, we show that the SRN can learn to mimic closely a finitestate automaton (FSA), both in its behavior and in its state representations.
Addressing the Curse of Imbalanced Training Sets: OneSided Selection
 In Proceedings of the Fourteenth International Conference on Machine Learning
, 1997
"... Adding examples of the majority class to the training set can have a detrimental effect on the learner's behavior: noisy or otherwise unreliable examples from the majority class can overwhelm the minority class. The paper discusses criteria to evaluate the utility of classifiers induced f ..."
Abstract

Cited by 234 (1 self)
 Add to MetaCart
from such imbalanced training sets, gives explanation of the poor behavior of some learners under these circumstances, and suggests as a solution a simple technique called onesided selection of examples. 1 Introduction The general topic of this paper is learning from examples described by pairs
The induction of dynamical recognizers
 Machine Learning
, 1991
"... A higher order recurrent neural network architecture learns to recognize and generate languages after being "trained " on categorized exemplars. Studying these networks from the perspective of dynamical systems yields two interesting discoveries: First, a longitudinal examination of the le ..."
Abstract

Cited by 225 (14 self)
 Add to MetaCart
A higher order recurrent neural network architecture learns to recognize and generate languages after being "trained " on categorized exemplars. Studying these networks from the perspective of dynamical systems yields two interesting discoveries: First, a longitudinal examination
Learning Automata  A survey
 IEEE Trans. Systems, Man., Cybernetics
, 1974
"... AbstractStochastic automata operating in an unknown random can be considered to show learning behavior. Tsypkin environment have been proposed earlier as models of learning. These [GT1] has recently argued that seemingly diverse problems automata update their action probabilities in accordance with ..."
Abstract

Cited by 62 (1 self)
 Add to MetaCart
AbstractStochastic automata operating in an unknown random can be considered to show learning behavior. Tsypkin environment have been proposed earlier as models of learning. These [GT1] has recently argued that seemingly diverse problems automata update their action probabilities in accordance
Syntactic representations as sideeffects of a sensorimotor mechanism
"... This paper describes a computational model of modern natural language syntax in which syntactic structures are defined as descriptions or traces of sensorimotor operations. The syntactic structure of a sentence describing a concrete state or event (e.g. There is a dog in the garden or The man grabbe ..."
Abstract
 Add to MetaCart
to observe, each accompanied by a sentence describing it, and must learn to generate appropriate sentences for similar situations. The agent processes each situation using a sensorimotor mechanism consisting of several different interacting components. Each of these components generates a sideeffect of its
Results 1  10
of
2,359