On the design of neural networks in the brain by genetic evolution.

By E. T. Rolls, Simon Maitland Stringer. 2000

60 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Cognitive Neuroscience

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Cognitive Neuroscience

Citations in the corpus

Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks (2017, methodology): “ lifetime. The implication is that error signals do not always need to be hand-designed but can be discovered by evolution to ﬁt a particular problem. A set of eight different local rules was used in Rolls and Stringer (2000) to investigate the evolution of rules in combination with the number of sy”
Invariant Visual Object and Face Recognition: Neural and Computational Bases, and a Model, VisNet (2012, background): “The correct, object, representation self-organizes itself given rather economically specified genetic rules for building the network (cf. Rolls and Stringer, 2000).”
Multiple neural systems controlling food intake and body weight. (2002, methodology): “Such acquired brain-internal information can be in the form of retrieval from (a) explicit, semantic or episodic memories from the hippocampal and parahippocampal formation, (b) memorial representations of rewards and punishments and stimulus–reinforcer associations from the orbitofrontal cortex [60”
The mechanisms for pattern completion and pattern separation in the hippocampus (2013, background): “…by enabling just two attributes of the connectivity to be specified (e.g., from a CA3 to another CA3 neuron chosen at random to specify the CA3 to CA3 RC connectivity), rather than which particular neuron should connect to which other particular neuron (Rolls and Stringer, 2000; Rolls, 2012a).”
Pattern separation, completion, and categorisation in the hippocampus and neocortex. (2016, background): “…just two attributes of the connectivity to be specified (e.g. from a CA3 to another CA3 neuron chosen at random to specify the CA3 to CA3 recurrent collateral connectivity), rather than which particular neuron should connect to which other particular neuron (Rolls, 2012a; Rolls & Stringer, 2000).”
Modelling brain emergent behaviours through coevolution of neural agents (2006, methodology): “Similar to a phylogenetic process, we employ an evolutionary approach to specify the computational details for each neural agent [35].”