Results 121 to 130 of about 90,924 (159)
Some of the next articles are maybe not open access.
Neural Computation, 1989
What use can the brain make of the massive flow of sensory information that occurs without any associated rewards or punishments? This question is reviewed in the light of connectionist models of unsupervised learning and some older ideas, namely the cognitive maps and working models of Tolman and Craik, and the idea that redundancy is important for ...
openaire +1 more source
What use can the brain make of the massive flow of sensory information that occurs without any associated rewards or punishments? This question is reviewed in the light of connectionist models of unsupervised learning and some older ideas, namely the cognitive maps and working models of Tolman and Craik, and the idea that redundancy is important for ...
openaire +1 more source
Spicules for Unsupervised Learning
2009We present a new model of unsupervised competitive neural network, based on spicules. This model is capable of detecting topological information of an input space, determining its orientation and, in most case, its skeleton.
José Antonio Gómez-Ruiz +2 more
openaire +1 more source
Unsupervised Reinforcement Learning
International Joint Conference on Autonomous Agents and Multiagent Systems, 2020Conventionally, reinforcement learning algorithms are goal-directed: they aim to acquire policies that most effectively maximize a given reward signal. However, if we consider agents that must master very large repertoires of behaviors -- such as general-purpose robots that must perform a diverse array of tasks in the real world -- then it makes sense ...
openaire +2 more sources
Generalization in Unsupervised Learning
2015We are interested in the following questions. Given a finite data set S, with neither labels nor side information, and an unsupervised learning algorithm A, can the generalization of A be assessed on S? Similarly, given two unsupervised learning algorithms, A1 and A2, for the same learning task, can one assess whether one will generalize "better" on ...
Karim T. Abou-Moustafa, Dale Schuurmans
openaire +1 more source
Unsupervised learning with stochastic gradient
Neurocomputing, 2005A stochastic gradient is formulated based on deterministic gradient augmented with Cauchy simulated annealing capable to reach a global minimum with a convergence speed significantly faster then when simulated annealing is used alone. In order to solve space-time variant inverse problems known as blind source separation, a novel Helmholtz free energy ...
Harold Szu, Ivica Kopriva
openaire +2 more sources
Unsupervised Learning in Metagame
1999The Metagame approach to computer game playing, introduced by Pell, involves writing programs that can play many games from some laxge class, rather thein programs speciailised to play just a single game such as chess. Metagame programs take the rules of a randomly generated game as input, then do some analysis of that game, and then play the game ...
Graham E. Farr, David R. Powell
openaire +1 more source
Unsupervised learning of action primitives
2010 10th IEEE-RAS International Conference on Humanoid Robots, 2010Action representation is a key issue in imitation learning forhumanoids. With the recent finding of mirror neurons there has been agrowing interest in expressing actions as a combination meaningfulsubparts called primitives. Primitives could be thought of as analphabet for the human actions. In this paper we observe that humanactions and objects can be
San Mohan, Volker Krüger, Danica Kragic
openaire +1 more source
An Approach to Unsupervised Learning Classification
IEEE Transactions on Computers, 1975In this correspondence, an approach to unsupervised pattern classifiers is discussed. The classifiers discussed here have the ability of obtaining the consistent estimates of unknown statistics of input patterns without knowing the a priori probability of each category's occurrence where the input patterns are of a mixture distribution.
Riichiro Mizoguchi, Masamichi Shimura
openaire +2 more sources
Unsupervised learning, an essential component of machine learning, has a substantial impact on the advancement and implementation of generative AI. Incorporating unsupervised learning into generative AI models has the potential to transform businesses by automating and improving creative processes.
Akshay Bhuvaneswari Ramakrishnan +1 more
+6 more sources
Akshay Bhuvaneswari Ramakrishnan +1 more
+6 more sources
Unsupervised Learning of Relations
2010Learning processes allow the central nervous system to learn relationships between stimuli. Even stimuli from different modalities can easily be associated, and these associations can include the learning of mappings between observable parameters of the stimuli.
Matthew Cook 0001 +3 more
openaire +1 more source