Results 281 to 290 of about 476,790 (313)

Human Representation Learning

Annual Review of Neuroscience, 2021
The central theme of this review is the dynamic interaction between information selection and learning. We pose a fundamental question about this interaction: How do we learn what features of our experiences are worth learning about? In humans, this process depends on attention and memory, two cognitive functions that together constrain ...
Angela, Radulescu, Yeon Soon, Shin, Yael, Niv   +2 more
openaire   +2 more sources

Learning structured representations

Neurocomputing, 2003
Abstract SHRUTI is a connectionist model that demonstrates how a network of neuron-like elements can encode a large body of semantic, episodic, and causal knowledge, and rapidly make decisions and perform explanatory and predictive reasoning. To further ground this model in the functioning of the brain it must be shown that components of the model ...
Lokendra Shastri, Carter Wendelken
openaire   +1 more source

Learning predictive representations

Neurocomputing, 2000
Abstract We demonstrate by a schematic model of an unexperienced animal exploring an environment that it is possible to evolve structures for perception, representation and action simultaneously from a single criterion, namely the error in predicting future sensory inputs. In order to organize successful representations of the environment actions are
J. Michael Herrmann, Klaus Pawelzik, Theo Geisel   +2 more
openaire   +1 more source

Learning Transferable Representations

2019
A first contribution of this thesis is to propose causality as a language for problems of distribution shift. First, we consider domain generalisation, where no data from the test distribution are observed during training. What assumptions can be made regarding the relation between train and test distributions for transfer to succeed?
openaire   +2 more sources

Separating learning and representation

1996
Two of the most promising aspects of connectionist natural language research have been (i) the use of powerful statistical learning techniques to model language learning and (ii) the development of new representational theories. Often the two are treated together; some part of a grammar is induced by a net and the subsequent representations are ...
Noel E. Sharkey, Amanda J. C. Sharkey
openaire   +1 more source

Representations for Continuous Learning

Proceedings of the AAAI Conference on Artificial Intelligence, 2017
Systems deployed in unstructured environments must be able to adapt to novel situations. This requires the ability to perform in domains that may be vastly different from training domains. My dissertation focuses on the representations used in lifelong learning and how these representations enable predictions and knowledge sharing over ...
openaire   +1 more source

Neuron Learning Machine for Representation Learning

Proceedings of the AAAI Conference on Artificial Intelligence, 2017
This paper presents a novel neuron learning machine (NLM) which can extract hierarchical features from data. We focus on the single-layer neural network architecture and propose to model the network based on the Hebbian learning rule.
Jia Liu 0020, Maoguo Gong, Qiguang Miao
openaire   +1 more source

Data Representations in Learning

1996
This paper examines the effect of varying the coarse-ness (or fine-ness) in a data representation upon the learning or recognition accuracy achievable. This accuracy is quantified by the least probability of error in recognition or the Bayes error rate, for a finite-class pattern recognition problem.
Geetha Srikantan, Sargur N. Srihari
openaire   +1 more source

Learning representations with neuromodulators

2017
Neuronen im Kortex und in künstlichen neuronalen Netzwerken (z.B. “Multi-layer erceptrons”, MPLs) repräsentieren Inputs als ktivitätsmuster. In beiden Systemen ist die Natur des neuronalen Codes entscheidend und folglich sind die Mechanismen, die das Lernen von Repräsentationen beeinflussen, von großer Bedeutung.
openaire   +2 more sources

Semi-Supervised Multi-View Deep Discriminant Representation Learning

IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021
Xiaodong Jia, Xiao-Yuan Jing, Xiaoke Zhu   +2 more
exaly