Sentence examples for a distributed representation from inspiring English sources

We implemented these distributed factors in a unified semi-Markov temporal-difference-based reinforcement learning model using a distribution of µAgents, the set of which provide a distributed discounting factor and a distributed representation of the believed state.

Throughout these layers a distributed representation for entities is gradually constructed.

The proposed approach is based on a direct use of a computational substrate of modeled V1 complex cells that provide a distributed representation of binocular disparity information.

Compared to learning based on local generalizations, the number of patterns that can be obtained using a distributed representation scales quickly with the number of learnt factors.

A linguistic entity such as a phoneme, word, or phrase of a particular type may be represented within a layer either by a pattern of activation of units in that layer (a distributed representation) or by a single activated unit (a localist representation).

An evident advantage of such a distributed representation of information is its robustness to cell death.

An autoencoder, firstly introduced in Rumelhart et al. [72], is a feedforward network that can learn a compressed, distributed representation of data, usually with the goal of dimensionality reduction or manifold learning.

In the temporal lobe visual cortical areas, neurons represent which object is present using a sparse distributed representation (Rolls and Treves 2011).

The small number of neurons selected from layer 4 of VisNet might correspond to the most selective for this stimulus set in a sparse distributed representation (Rolls 2008; Rolls and Treves 2011).

Further, some inferior temporal visual cortex neurons respond with view-invariant object representations, in that they respond selectively to some objects or faces independently of view using a sparse distributed representation (Hasselmo et al. 1989; Booth and Rolls 1998; Logothetis et al. 1995; Rolls 2012a; Rolls and Treves 2011).

Local lateral inhibition within each layer allows each local area within a layer to respond to and learn whatever is present in that local region independently of how much information and contrast there may be in other parts of a layer, and this, together with the non-linear activation function of the neurons, enables a sparse distributed representation to be produced.